Search

Objective . The clinical diagnosis of Parkinson's disease (PD) relying on medical history, clinical symptoms, and signs is subjective and lacks sensitivity. Resting-state fMRI (rs-fMRI) has been demonstrated to be an effective biomarker for diagnosing PD. Approach. This study proposes a deep learning approach for the automatic diagnosis of PD using rs-fMRI, named PD-ARnet. Specifically, PD-ARnet utilizes Amplitude of Low Frequency Fluctuations and Regional Homogeneity extracted from rs-fMRI as inputs. The inputs are then processed through a developed dual-branch 3D feature extractor to perform advanced feature extraction. During this process, a Correlation-Driven weighting module is applied to capture complementary information from both features. Subsequently, the Attention-Enhanced fusion module is developed to effectively merge two types of features, and the fused features are input into a fully connected layer for automatic diagnosis classification. Main results. Using 145 samples from the PPMI dataset to evaluate the detection performance of PD-ARnet, the results indicated an average classification accuracy of 91.6% (95% confidence interval [CI]: 90.9%, 92.4%), precision of 94.7% (95% CI: 94.2%, 95.1%), recall of 86.2% (95% CI: 84.9%, 87.4%), F1 score of 90.2% (95% CI: 89.3%, 91.1%), and AUC of 92.8% (95% CI: 91.1%, 95.0%). Significance. The proposed method has the potential to become a clinical auxiliary diagnostic tool for PD, reducing subjectivity in the diagnostic process, and enhancing diagnostic efficiency and consistency., (© 2024 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.)

Purpose of Review: We review recent evidence on Illness Anxiety Disorder (IAD), including risk factors and precipitants, diagnostic classification, clinical characteristics of the disorder, and assessment and treatment in both children and adults., Recent Findings: IAD places a substantial burden on both individuals and society. Despite its impact, understanding of the disorder is lacking and debates remain about whether IAD should be classified as an anxiety disorder and whether it is distinct from Somatic Symptom Disorder. Cognitive behavioural therapy (CBT) is an effective treatment for IAD and there are multiple validated measures of health anxiety available. However, research on health anxiety in children and youth is limited. IAD is chronic, and debilitating, but when identified, it can be effectively treated with CBT. Research using DSM-5 IAD criteria is lacking, and more research is needed to better understand the disorder, particularly in children and youth., (© 2024. The Author(s).)

Modern natural language processing (NLP) methods provide ways to objectively quantify language disturbances for potential use in diagnostic classification. We performed computerized language analysis in speech samples of 82 Turkish-speaking subjects, including 44 patients with schizophrenia spectrum disorders (SSD) and 38 healthy controls (HC). Exploratory analysis of speech samples involved 16 sentence-level semantic similarity features using SBERT (Sentence Bidirectional Encoder Representation from Text) as well as 8 generic and 8 part-of-speech (POS) features. The random forest classifier using SBERT-derived semantic similarity features achieved a mean accuracy of 85.6 % for the classification of SSD and HC. When semantic similarity features were combined with generic and POS features, the classifier's mean accuracy reached to 86.8 %. Our analysis reflected increased sentence-level semantic similarity scores in SSD. Generic and POS analyses revealed an increase in the use of verbs, proper nouns and pronouns in SSD while our results showed a decrease in the utilization of conjunctions, determiners, and both average and maximum sentence length in SSD compared to HC. Quantitative language features were correlated with the expressive deficit domain of BNSS (Brief Negative Symptom Scale) as well as with the duration of illness. These findings from Turkish-speaking interviews contribute to the growing evidence-based NLP-derived assessments in non-English-speaking patients., Competing Interests: Declaration of competing interest The authors have no conflicts of interest regarding subject of this manuscript., (Copyright © 2024 Elsevier B.V. All rights reserved.)

Aim: To develop and validate an automated electronic health record (EHR)-based algorithm to suggest a periodontal diagnosis based on the 2017 World Workshop on the Classification of Periodontal Diseases and Conditions., Materials and Methods: Using material published from the 2017 World Workshop, a tool was iteratively developed to suggest a periodontal diagnosis based on clinical data within the EHR. Pertinent clinical data included clinical attachment level (CAL), gingival margin to cemento-enamel junction distance, probing depth, furcation involvement (if present) and mobility. Chart reviews were conducted to confirm the algorithm's ability to accurately extract clinical data from the EHR, and then to test its ability to suggest an accurate diagnosis. Subsequently, refinements were made to address limitations of the data and specific clinical situations. Each refinement was evaluated through chart reviews by expert periodontists at the study sites., Results: Three-hundred and twenty-three charts were manually reviewed, and a periodontal diagnosis (healthy, gingivitis or periodontitis including stage and grade) was made by expert periodontists for each case. After developing the initial version of the algorithm using the unmodified 2017 World Workshop criteria, accuracy was 71.8% for stage alone and 64.7% for stage and grade. Subsequently, 16 modifications to the algorithm were proposed and 14 were accepted. This refined version of the algorithm had 79.6% accuracy for stage alone and 68.8% for stage and grade together., Conclusions: Our findings suggest that a rule-based algorithm for suggesting a periodontal diagnosis using EHR data can be implemented with moderate accuracy in support of chairside clinical diagnostic decision making, especially for inexperienced clinicians. Grey-zone cases still exist, where clinical judgement will be required. Future applications of similar algorithms with improved performance will depend upon the quality (completeness/accuracy) of EHR data., (© 2024 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)

Objective: For adolescents, DSM-5 differentiates anorexia nervosa (AN) and atypical AN with the 5th BMI-centile-for-age. We hypothesized that the diagnostic weight cut-off yields (i) lower weight loss in atypical AN and (ii) discrepant premorbid BMI distributions between the two disorders. Prior studies demonstrate that premorbid BMI predicts admission BMI and weight loss in patients with AN. We explore these relationships in atypical AN., Method: Based on admission BMI-centile < or ≥5th, participants included 411 female adolescent inpatients with AN and 49 with atypical AN from our registry study. Regression analysis and t-tests statistically addressed our hypotheses and exploratory correlation analyses compared interrelationships between weight loss, admission BMI, and premorbid BMI in both disorders., Results: Weight loss in atypical AN was 5.6 kg lower than in AN upon adjustment for admission age, admission height, premorbid weight and duration of illness. Premorbid BMI-standard deviation scores differed by almost one between both disorders. Premorbid BMI and weight loss were strongly correlated in both AN and atypical AN., Discussion: Whereas the weight cut-off induces discrepancies in premorbid weight and adjusted weight loss, AN and atypical AN overall share strong weight-specific interrelationships that merit etiological consideration. Epidemiological and genetic associations between AN and low body weight may reflect a skewed premorbid BMI distribution. In combination with prior findings for similar psychological and medical characteristics in AN and atypical AN, our findings support a homogenous illness conceptualization. We propose that diagnostic subcategorization based on premorbid BMI, rather than admission BMI, may improve clinical validity., Public Significance: Because body weights of patients with AN must drop below the 5th BMI-centile per DSM-5, they will inherently require greater weight loss than their counterparts with atypical AN of the same sex, age, height and premorbid weight. Indeed, patients with atypical AN had a 5.6 kg lower weight loss after controlling for these variables. In comparison to the reference population, we found a lower and higher mean premorbid weight in patients with AN and atypical AN, respectively. Considering previous psychological and medical comparisons showing little differences between AN and atypical AN, we view a single disorder as the most parsimonious explanation. Etiological models need to particularly account for the strong relationship between weight loss and premorbid body weight., (© 2024 The Authors. International Journal of Eating Disorders published by Wiley Periodicals LLC.)

Objective: Anorexia nervosa (AN) and atypical AN are conceptualized as distinct illnesses, despite similar characteristics and sequelae. Whereas DSM-5 differentiates youth with AN and atypical AN by the presence of clinical 'underweight' (i.e., 5th BMI percentile for age-and-sex (BMI%)), we hypothesized that using this weight cut-off to discern diagnoses creates a skewed distribution for premorbid weight., Method: Participants included hospitalized youth with AN (n = 165, 43.1%) and atypical AN (n = 218, 56.9%). Frequency analyses and chi-square tests assessed the distribution of premorbid BMI z-scores (BMIz) for diagnosis. Non-parametric Spearman correlations and Stepwise Linear regressions examined relationships between premorbid BMIz, admission BMIz, and weight loss in kg., Results: Premorbid BMIz distributions differed significantly for diagnosis (p < .001), with an underrepresentation of 'overweight/obesity' (i.e., BMI% ≥ 85th) in AN. Despite commensurate weight loss in AN and atypical AN, patients with premorbid 'overweight/obesity' were 8.31 times more likely to have atypical AN than patients with premorbid BMI% < 85th. Premorbid BMIz explained 57% and 39% of the variance in admission BMIz and weight loss, respectively., Discussion: Findings support a homogenous model of AN and atypical AN, with weight loss predicted by premorbid BMI in both illnesses. Accordingly, premorbid BMI and weight loss (versus presenting BMI) may better denote the presence of an AN-like phenotype across the weight spectrum. Findings also suggest that differentiating diagnoses with BMI% < 5th requires that youth with higher BMIs lose disproportionately more weight for an AN diagnosis. This is problematic given unique treatment barriers experienced in atypical AN., Public Significance: Anorexia nervosa (AN) and atypical AN are considered distinct conditions in youth, with differential diagnosis hinging upon a presenting weight status of 'underweight' (i.e., BMI percentile for age-and-sex (BMI%) < 5th). In our study, youth with premorbid 'overweight/obesity' (BMI% ≥ 85th) disproportionately remained above this threshold, despite similar weight loss. Coupled with prior evidence for commensurate characteristics and sequelae in both diagnoses, we propose that DSM-5 differentiation of AN and atypical AN inadvertently reinforces weight stigma and may contribute to treatment disparities in atypical AN., (© 2024 Wiley Periodicals LLC.)

Objective: Panoramic radiographs (PRs) provide a comprehensive view of the oral and maxillofacial region and are used routinely to assess dental and osseous pathologies. Artificial intelligence (AI) can be used to improve the diagnostic accuracy of PRs compared to bitewings and periapical radiographs. This study aimed to evaluate the advantages and challenges of using publicly available datasets in dental AI research, focusing on solving the novel task of predicting tooth segmentations, FDI numbers, and tooth diagnoses, simultaneously., Materials and Methods: Datasets from the OdontoAI platform (tooth instance segmentations) and the DENTEX challenge (tooth bounding boxes with associated diagnoses) were combined to develop a two-stage AI model. The first stage implemented tooth instance segmentation with FDI numbering and extracted regions of interest around each tooth segmentation, whereafter the second stage implemented multi-label classification to detect dental caries, impacted teeth, and periapical lesions in PRs. The performance of the automated tooth segmentation algorithm was evaluated using a free-response receiver-operating-characteristics (FROC) curve and mean average precision (mAP) metrics. The diagnostic accuracy of detection and classification of dental pathology was evaluated with ROC curves and F1 and AUC metrics., Results: The two-stage AI model achieved high accuracy in tooth segmentations with a FROC score of 0.988 and a mAP of 0.848. High accuracy was also achieved in the diagnostic classification of impacted teeth (F1 = 0.901, AUC = 0.996), whereas moderate accuracy was achieved in the diagnostic classification of deep caries (F1 = 0.683, AUC = 0.960), early caries (F1 = 0.662, AUC = 0.881), and periapical lesions (F1 = 0.603, AUC = 0.974). The model's performance correlated positively with the quality of annotations in the used public datasets. Selected samples from the DENTEX dataset revealed cases of missing (false-negative) and incorrect (false-positive) diagnoses, which negatively influenced the performance of the AI model., Conclusions: The use and pooling of public datasets in dental AI research can significantly accelerate the development of new AI models and enable fast exploration of novel tasks. However, standardized quality assurance is essential before using the datasets to ensure reliable outcomes and limit potential biases., (© 2024. The Author(s).)

Background: The high heterogeneity of depression prevents us from obtaining reproducible and definite anatomical maps of brain structural changes associated with the disorder, which limits the individualized diagnosis and treatment of patients. In this study, we investigated the clinical issues related to depression according to individual deviations from normative ranges of gray matter volume., Methods: We enrolled 1092 participants, including 187 patients with depression and 905 healthy control participants. Structural magnetic resonance imaging data of healthy control participants from the Human Connectome Project (n = 510) and REST-meta-MDD Project (n = 229) were used to establish a normative model across the life span in adults 18 to 65 years old for each brain region. Deviations from the normative range for 187 patients and 166 healthy control participants recruited from two local hospitals were captured as normative probability maps, which were used to identify the disease risk and treatment-related latent factors., Results: In contrast to case-control results, our normative modeling approach revealed highly individualized patterns of anatomic abnormalities in depressed patients (less than 11% extreme deviation overlapping for any regions). Based on our classification framework, models trained with individual normative probability maps (area under the receiver operating characteristic curve range, 0.7146-0.7836) showed better performance than models trained with original gray matter volume values (area under the receiver operating characteristic curve range, 0.6800-0.7036), which was verified in an independent external test set. Furthermore, different latent brain structural factors in relation to antidepressant treatment were revealed by a Bayesian model based on normative probability maps, suggesting distinct treatment response and inclination., Conclusions: Capturing personalized deviations from a normative range could help in understanding the heterogeneous neurobiology of depression and thus guide clinical diagnosis and treatment of depression., (Copyright © 2023 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.)

There is scarce evidence to demonstrate the pattern of antibiotic use in children in China. We aimed to describe antibiotic prescribing practices among children in primary healthcare institutions (PHIs) in China. We described outpatient antibiotic prescriptions for children in PHIs from January 2017 to December 2019 at both the national and diagnostic levels, utilizing the antibiotic prescribing rate (APR), multi-antibiotic prescribing rate (MAPR), and broad-spectrum prescribing rate (BAPR). Generalized estimating equations were adopted to analyze the factors associated with antibiotic use. Among the total 155,262.2 weighted prescriptions for children, the APR, MAPR, and BAPR were 43.5%, 9.9%, and 84.8%. At the national level, J01DC second-generation cephalosporins were the most prescribed antibiotic category (21.0%, N = 15,313.0), followed by J01DD third-generation cephalosporins (17.4%, N = 12,695.8). Watch group antibiotics accounted for 55.0% of the total antibiotic prescriptions (N = 52,056.3). At the diagnostic level, respiratory tract infections accounted for 67.4% of antibiotic prescriptions, among which prescriptions with diagnoses classified as potentially bacterial RTIs occupied the highest APR (55.0%). For each diagnostic category, the MAPR and BAPR varied. Age, region, and diagnostic categories were associated with antibiotic use. Concerns were raised regarding the appropriateness of antibiotic use, especially for broad-spectrum antibiotics.

Background: Individuals with bipolar disorder are commonly correctly diagnosed a decade after symptom onset. Machine learning techniques may aid in early recognition and reduce the disease burden. As both individuals at risk and those with a manifest disease display structural brain markers, structural magnetic resonance imaging may provide relevant classification features., Methods: Following a pre-registered protocol, we trained linear support vector machine (SVM) to classify individuals according to their estimated risk for bipolar disorder using regional cortical thickness of help-seeking individuals from seven study sites ( N = 276). We estimated the risk using three state-of-the-art assessment instruments (BPSS-P, BARS, EPI bipolar )., Results: For BPSS-P, SVM achieved a fair performance of Cohen's κ of 0.235 (95% CI 0.11-0.361) and a balanced accuracy of 63.1% (95% CI 55.9-70.3) in the 10-fold cross-validation. In the leave-one-site-out cross-validation, the model performed with a Cohen's κ of 0.128 (95% CI -0.069 to 0.325) and a balanced accuracy of 56.2% (95% CI 44.6-67.8). BARS and EPI bipolar could not be predicted. In post hoc analyses, regional surface area, subcortical volumes as well as hyperparameter optimization did not improve the performance., Conclusions: Individuals at risk for bipolar disorder, as assessed by BPSS-P, display brain structural alterations that can be detected using machine learning. The achieved performance is comparable to previous studies which attempted to classify patients with manifest disease and healthy controls. Unlike previous studies of bipolar risk, our multicenter design permitted a leave-one-site-out cross-validation. Whole-brain cortical thickness seems to be superior to other structural brain features.

Autism spectrum disorder (ASD) is diagnosed on the basis of speech and communication differences, amongst other symptoms. Since conversations are essential for building connections with others, it is important to understand the exact nature of differences between autistic and non-autistic verbal behaviour and evaluate the potential of these differences for diagnostics. In this study, we recorded dyadic conversations and used automated extraction of speech and interactional turn-taking features of 54 non-autistic and 26 autistic participants. The extracted speech and turn-taking parameters showed high potential as a diagnostic marker. A linear support vector machine was able to predict the dyad type with 76.2% balanced accuracy (sensitivity: 73.8%, specificity: 78.6%), suggesting that digitally assisted diagnostics could significantly enhance the current clinical diagnostic process due to their objectivity and scalability. In group comparisons on the individual and dyadic level, we found that autistic interaction partners talked slower and in a more monotonous manner than non-autistic interaction partners and that mixed dyads consisting of an autistic and a non-autistic participant had increased periods of silence, and the intensity, i.e. loudness, of their speech was more synchronous., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The author(s) declared that they were an editorial board member of Frontiers, at the time of submission. This had no impact on the peer review process and the final decision., (Copyright © 2023 Plank, Koehler, Nelson, Koutsouleris and Falter-Wagner.)

Cognitive diagnosis models (CDMs) are used in educational, clinical, or personnel selection settings to classify respondents with respect to discrete attributes, identifying strengths and needs, and thus allowing to provide tailored training/treatment. As in any assessment, an accurate reliability estimation is crucial for valid score interpretations. In this sense, most CDM reliability indices are based on the posterior probabilities of the estimated attribute profiles. These posteriors are traditionally computed using point estimates for the model parameters as approximations to their populational values. If the uncertainty around these parameters is unaccounted for, the posteriors may be overly peaked, deriving into overestimated reliabilities. This article presents a multiple imputation (MI) procedure to integrate out the model parameters in the estimation of the posterior distributions, thus correcting the reliability estimation. A simulation study was conducted to compare the MI procedure with the traditional reliability estimation. Five factors were manipulated: the attribute structure, the CDM model (DINA and G-DINA), test length, sample size, and item quality. Additionally, an illustration using the Examination for the Certificate of Proficiency in English data was analyzed. The effect of sample size was studied by sampling subsets of subjects from the complete data. In both studies, the traditional reliability estimation systematically provided overestimated reliabilities, whereas the MI procedure offered more accurate results. Accordingly, practitioners in small educational or clinical settings should be aware that the reliability estimation using model parameter point estimates may be positively biased. R codes for the MI procedure are made available., (© 2022. The Author(s).)

In recent years, deep neural networks have enabled countless innovations in the field of image classification. Encouraged by success in this field, researchers worldwide have demonstrated how to use Convolutional Neural Network techniques in medical imaging problems. In this article, the results were obtained through the use of the EfficientNet in the task of classifying 14 different diseases based on chest X-ray images coming from the NIH (National Institutes of Health) ChestX-ray14 dataset. The approach addresses dataset imbalances by introducing a custom split to ensure fair representation. Binary cross entropy loss is utilized to handle the multi-label difficulty. The model architecture comprises an EfficientNet backbone for feature extraction, succeeded by sequential layers including GlobalAveragePooling, Dense, and BatchNormalization. The main contribution of this paper is a proposed solution that outperforms previous state-of-the-art deep learning models average area under the receiver operating characteristic curve-AUC-ROC (score: 84.28%). The usage of the transfer-learning technique and traditional deep learning engineering techniques was shown to enable us to obtain such results on consumer-class GPUs (graphics processing units).

Background: The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation., Methods: Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses., Results: A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R 2 adj  = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF 10  > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance., Conclusions: Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice., (© 2023. The Author(s).)

In this article, a testlet hierarchical diagnostic classification model (TH-DCM) was introduced to take both attribute hierarchies and item bundles into account. The expectation-maximization algorithm with an analytic dimension reduction technique was used for parameter estimation. A simulation study was conducted to assess the parameter recovery of the proposed model under varied conditions, and to compare TH-DCM with testlet higher-order CDM (THO-DCM; Hansen, M. (2013). Hierarchical item response models for cognitive diagnosis (Unpublished doctoral dissertation). UCLA; Zhan, P., Li, X., Wang, W.-C., Bian, Y., & Wang, L. (2015). The multidimensional testlet-effect cognitive diagnostic models. Acta Psychologica Sinica, 47(5), 689. https://doi.org/10.3724/SP.J.1041.2015.00689). Results showed that (1) ignoring large testlet effects worsened parameter recovery, (2) DCMs assuming equal testlet effects within each testlet performed as well as the testlet model assuming unequal testlet effects under most conditions, (3) misspecifications in joint attribute distribution had an differential impact on parameter recovery, and (4) THO-DCM seems to be a robust alternative to TH-DCM under some hierarchical structures. A set of real data was also analyzed for illustration., Competing Interests: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article., (© The Author(s) 2023.)

Changes made to the DSM Eating Disorders over the years have aimed to reduce the prevalence of the residual DSM Eating Disorder categories (e.g., Other Specified Eating Disorder). Atypical Anorexia Nervosa (AN), included since DSM-IV as an example of a presentation not meeting criteria for a specific eating disorder, appears to be more prevalent than AN. It is defined as meeting all of the criteria for AN except that, after significant weight loss, weight is at or above normal. As suggested by the Walsh et al. review, lack of definitional precision will likely complicate efforts to determine whether atypical AN is best considered a variant of AN or a distinct category. Problems with the current definition of atypical AN include (1) a lack of precision regarding what constitutes "significant" weight loss; (2) whether the weight loss can occur at any point in the individual's lifetime; and (3) whether there an upper limit to weight being above normal. It is suggested that researchers develop consensus diagnostic criteria and assessment tools to facilitate the collection of empirical data about atypical AN in order to lay the groundwork for future decisions about its nosological status., (© 2023 Wiley Periodicals LLC.)

Carotid atherosclerotic stenosis of the carotid artery is an important cause of ischemic cerebrovascular disease. The aim of this study was to predict the presence or absence of clinical symptoms in unknown patients by studying the existence or lack of symptoms of patients with carotid atherosclerotic stenosis. First, a deep neural network prediction model based on brain MRI imaging data of patients with multiple modalities is constructed; it uses the multi-modality features extracted from the neural network as inputs and the incidence of diagnosis as output to train the model. Then, a machine learning-based classification algorithm is developed to utilize the clinical features for comparison and evaluation. The experimental results showed that the deep learning model using imaging data could better predict the clinical symptom classification of patients. As part of preventive medicine, this study could help patients with carotid atherosclerosis narrowing to prepare for stroke prevention based on the prediction results., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Lv, Yang, Wang, Guo, Tang, Magnier, Lin and Zhou.)

Objective. The objective of this study is to explore new imaging techniques with the use of the deep learning method for the identification of cardiac abnormalities present in electrocardiogram (ECG) signals with 2, 3, 4, 6 and 12-lead in the framework of the PhysioNet/Computing in Cardiology Challenge 2021. The training set is a public database of 88,253 twelve-lead ECG recordings lasting from 6 s to 60 s. Each ECG recording has one or more diagnostic labels. The six-lead, four-lead, three-lead, and two-lead are reduced-lead versions of the original twelve-lead data. Approach. The deep learning method considers images that are built from raw ECG signals. This technique considers innovative 3D display of the entire ECG signal, observing the regional constraints of the leads, obtaining time-spatial images of the 12 leads, where the x-axis is the temporal evolution of ECG signal, the y-axis is the spatial location of the leads, and the z-axis (color) the amplitude. These images are used for training Convolutional Neural Networks with GoogleNet for ECG diagnostic classification. Main results. The official results of the classification accuracy of our team named 'Gio&#95;new&#95;img' received scores of 0.4, 0.4, 0.39, 0.4 and 0.4 (ranked 18th, 18th, 18th,18th, 18th out of 39 teams) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set with the Challenge evaluation metric. Significance. The results indicated that all these algorithms have similar behaviour in the various lead groups, and the most surprising and interesting point is the fact that the 2-lead scores are similar to those obtained with the analysis of 12 leads. It permitted to test the diagnostic potential of the reduced-lead ECG recordings. These aspects can be related to the pattern recognition capacity and generalizability of the deep learning approach and/or to the fact that the characteristics of the considered cardiac abnormalities can be extracted also from a reduced set of leads., (Creative Commons Attribution license.)

Orthorexia nervosa (ON) is a proposed psychological disorder characterized by a pathological preoccupation with healthy eating. The purpose of the current study was to clarify the relationships between ON and related forms of psychopathology. In addition, we sought to explore whether there may be subtypes of ON and if ON is associated with BMI, gender, or social media use. The sample included 333 undergraduate students (72% female, M age  = 20.91) who completed measures of ON, eating disorder (ED) symptoms, obsessive compulsive disorder (OCD), obsessive compulsive personality disorder (OCPD), and health anxiety. Latent profile analysis detected three distinct groups with high ON scores. The ON/ED combined group (n = 16) was characterized by high levels of psychopathology, particularly in the areas of ON and eating disorder symptoms. In comparison, the ON/ED combined, without weight/shape concerns group (n = 35) had fewer body-related concerns. The ON only group (n = 23) reported minimal ED pathology. Regression analyses revealed those in the ON only group were more likely to be male, while the ON/ED group was associated with higher BMI. Being in the ON/ED combined, without weight/shape concerns was associated with viewing and sharing healthy eating content on social media. Our findings suggest that ON has the most overlap with ED pathology as compared to OCD, OCPD, and health anxiety, and that there may be three subtypes of ON. The first two share significant overlap with ED symptomatology while the third appears relatively distinct, characterized by less disordered eating and fewer positive emotions related to healthy eating. Future research should examine these subtypes more closely to determine whether they are clinically meaningful, potentially requiring different interventions., Competing Interests: Declarations of competing interest None., (Copyright © 2022. Published by Elsevier Ltd.)

The term sexual addiction is used to describe a range of behaviors involving compulsive and maladaptive sexual behavior. There are mixed opinions in the medical literature regarding whether sexual addiction represents a valid psychiatric diagnosis or instead pathologizes behaviors in the expected range of human behavior. The opinions on sexual addiction in case law are similarly mixed. The condition has at times been used as a successful mitigating factor and at other times been rejected for lack of scientific evidence. The authors searched the LexisNexis database for legal cases that involved the use of sexual addiction as a mitigating or aggravating factor to provide an overview of the available case law. This article is focused on the uncertainty surrounding the diagnosis of sexual addiction and how it has been interpreted by the legal system., (© 2022 American Academy of Psychiatry and the Law.)

Background: The 20th century has seen great developments in the concept of disease. Marked by the biopsychosocial paradigm, several strategies for disease definition were added to previous descriptive organic views, but a final concept is still out of reach., Method: A critical review was carried out on thorough analysis of articles and textbooks to describe the main concepts and definitions of disease., Results: The concept 'disease' is a pragmatic construct, not a natural kind. Three main ways to define disease were identified, and characterized: Biological (disease as a lesion, disadvantage/deviation from normal and dysfunction), Psychosocial (distress and disability, existential potentials, descriptive prototype, and prototype typification), and values-based definition., Conclusion: All the paradigms have advantages and flaws, but progressive use of all criteria in disease definition adds validity and reliability to diagnostic constructs. Such constructs must be, above all, useful for practice and research. Biological paradigm is relevant, but fails to cover all the complexity that involves human illness and the treatment process. An emphasis on distress, dysfunction, and carefully selected value-laden characteristics might be the right direction for useful diagnostic construct conceptions., (© 2021 John Wiley & Sons Ltd.)

Fine-needle aspiration biopsies (FNA) represent the gold standard to exclude the malignant nature of thyroid nodules. After cytomorphology, 20-30% of cases are deemed "indeterminate for malignancy" and undergo surgery. However, after thyroidectomy, 70-80% of these nodules are benign. The identification of tools for improving FNA's diagnostic performances is explored by matrix-assisted laser-desorption ionization mass spectrometry imaging (MALDI-MSI). A clinical study was conducted in order to build a classification model for the characterization of thyroid nodules on a large cohort of 240 samples, showing that MALDI-MSI can be effective in separating areas with benign/malignant cells. The model had optimal performances in the internal validation set ( n = 70), with 100.0% (95% CI = 83.2-100.0%) sensitivity and 96.0% (95% CI = 86.3-99.5%) specificity. The external validation ( n = 170) showed a specificity of 82.9% (95% CI = 74.3-89.5%) and a sensitivity of 43.1% (95% CI = 30.9-56.0%). The performance of the model was hampered in the presence of poor and/or noisy spectra. Consequently, restricting the evaluation to the subset of FNAs with adequate cellularity, sensitivity improved up to 76.5% (95% CI = 58.8-89.3). Results also suggest the putative role of MALDI-MSI in routine clinical triage, with a three levels diagnostic classification that accounts for an indeterminate gray zone of nodules requiring a strict follow-up.

The majority of radiology studies in neurodegenerative conditions infer group-level imaging traits from group comparisons. While this strategy is helpful to define phenotype-specific imaging signatures for academic use, the meaningful interpretation of single scans of individual subjects is more important in everyday clinical practice. Accordingly, we present a computational method to evaluate individual subject diffusion tensor data to highlight white matter integrity alterations. Fifty white matter tracts were quantitatively evaluated in 132 patients with amyotrophic lateral sclerosis (ALS) with respect to normative values from 100 healthy subjects. Fractional anisotropy and radial diffusivity alterations were assessed individually in each patient. The approach was validated against standard tract-based spatial statistics and further scrutinised by the assessment of 78 additional data sets with a blinded diagnosis. Our z-score-based approach readily detected white matter degeneration in individual ALS patients and helped to categorise single subjects with a 'blinded diagnosis' as likely 'ALS' or 'control'. The group-level inferences from the z-score-based approach were analogous to the standard TBSS output maps. The benefit of the z-score-based strategy is that it enables the interpretation of single DTI datasets as well as the comparison of study groups. Outputs can be summarised either visually by highlighting the affected tracts, or, listing the affected tracts in a text file with reference to normative data, making it particularly useful for clinical applications. While individual diffusion data cannot be visually appraised, our approach provides a viable framework for single-subject imaging data interpretation., (Copyright © 2021 The Authors. Published by Elsevier B.V. All rights reserved.)

Purpose: This study was conducted in order to compare the diagnostic classification of Bruch's membrane opening-minimum rim width (BMO-MRW) and RNFL thickness in normal myopic subjects by using optical coherence tomography (OCT). Methods: This cross-sectional study involved 75 healthy myopic subjects [spherical equivalent (SE) ≤ -0.5D] from April 2019 to January 2020. One eye of each subject was randomly selected for examination. BMO-MRW and peripapillary RNFL thickness were measured by spectral-domain OCT (Spectralis, Heidelberg Engineering GmbH, Heidelberg, Germany). All the subjects were divided into three groups: low myopic group (SE > -3D), moderate myopic group (-6D < SE ≤ -3D), and high myopic group (SE ≤ -6D). A nonparametric test was used to analyze the difference among groups. Linear regression was used to analyze the relationship between BMO-MRW/RNFL thickness and axial length/spherical equivalent. McNemar test was used to compare the diagnostic classification between BMO-MRW and RNFL thickness. Results: The RNFL thickness classified a significantly higher percentage of eyes as outside normal limits/borderline in at least 1 quadrant (BMO-MRW, 4%; RNFL thickness, 34.67%; p < 0.01). There was no significant correlation between BMO-MRW/RNFL thickness and AL/SE. The low myopia (SE > -3D) had a significantly lower percentage of eyes classified as outside normal limits/borderline in at least 1 quadrant than the moderate myopia (-6D < SE ≤ -3D) and high myopia (SE ≤ -6D) (low myopia, 12.5%; moderate/high myopia, 42.42%/50%; p < 0.05). Conclusion: BMO-MRW had a lower percentage of eyes classified as outside normal limits/borderline in at least 1 quadrant than RNFL thickness in normal myopic subjects. When referring to the diagnostic classification of RNFL thickness in myopic subjects, caution should be exercised in interpreting positive results. Further studies are needed to compare the diagnostic accuracy of these two measurements in myopic glaucoma patients., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Wang, Zhen, Liu, Qiu, Liu, Wang and Zhang.)

Interstitial lung diseases (ILDs) are challenging to diagnose, requiring integration of multiple complex features that are often difficult to interpret. This article reviews a pragmatic approach to ILD diagnosis and classification, focusing on diagnostic tools and strategies that are used to separate different subtypes and identify the most appropriate management. We discuss the evolution of ILD classification and the contemporary approach that integrates routinely used diagnostic tools in a multidisciplinary discussion. We highlight the increasing importance of taking a multipronged approach to ILD classification that reflects the recent emphasis on disease behavior while also considering etiopathogenesis and morphologic features., Competing Interests: Conflict of Interest Disclosures A. Adegunsoye is supported by a career development award from the National Heart, Lung, and Blood Institute (K23HL146942), and has received speaking and advisory board fees from Boehringer Ingelheim and grant funding for interstitial lung disease research from the Pulmonary Fibrosis Foundation. C.J. Ryerson is supported by a Health Professional Investigator Award from the Michael Smith Foundation for Health Research., (Copyright © 2021 Elsevier Inc. All rights reserved.)

Despite the increasing popularity, cognitive diagnosis models have been criticized for limited utility for small samples. In this study, the authors proposed to use Bayes modal (BM) estimation and monotonic constraints to stabilize item parameter estimation and facilitate person classification in small samples based on the generalized deterministic input noisy "and" gate (G-DINA) model. Both simulation study and real data analysis were used to assess the utility of the BM estimation and monotonic constraints. Results showed that in small samples, (a) the G-DINA model with BM estimation is more likely to converge successfully, (b) when prior distributions are specified reasonably, and monotonicity is not violated, the BM estimation with monotonicity tends to produce more stable item parameter estimates and more accurate person classification, and (c) the G-DINA model using the BM estimation with monotonicity is less likely to overfit the data and shows higher predictive power., Competing Interests: Declaration of Conflicting Interests: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article., (© The Author(s) 2020.)

The pathogen exposure history of an individual is recorded in their T-cell repertoire and can be accessed through the study of T-cell receptors (TCRs) if the tools to identify them were available. For each T-cell, the TCR loci undergoes genetic rearrangement that creates a unique DNA sequence. In theory these unique sequences can be used as biomarkers for tracking T-cell responses and cataloging immunological history. We developed the immune Cell Analysis Tool (iCAT), an R software package that analyzes TCR sequencing data from exposed (positive) and unexposed (negative) samples to identify TCR sequences statistically associated with positive samples. The presence and absence of associated sequences in samples trains a classifier to diagnose pathogen-specific exposure. We demonstrate the high accuracy of iCAT by testing on three TCR sequencing datasets. First, iCAT successfully diagnosed smallpox vaccinated versus naïve samples in an independent cohort of mice with 95% accuracy. Second, iCAT displayed 100% accuracy classifying naïve and monkeypox vaccinated mice.  Finally, we demonstrate the use of iCAT on human samples before and after exposure to SARS-CoV-2, the virus behind the COVID-19 global pandemic. We were able to correctly classify the exposed samples with perfect accuracy. These experimental results show that iCAT capitalizes on the power of TCR sequencing to simplify infection diagnostics. iCAT provides the option of a graphical, user-friendly interface on top of usual R interface allowing it to reach a wider audience., Competing Interests: No competing interests were disclosed., (Copyright: © 2021 Rajeh A et al.)

The pathogen exposure history of an individual is recorded in their T-cell repertoire and can be accessed through the study of T-cell receptors (TCRs) if the tools to identify them were available. For each T-cell, the TCR loci undergoes genetic rearrangement that creates a unique DNA sequence. In theory these unique sequences can be used as biomarkers for tracking T-cell responses and cataloging immunological history. We developed the immune Cell Analysis Tool (iCAT), an R software package that analyzes TCR sequencing data from exposed (positive) and unexposed (negative) samples to identify TCR sequences statistically associated with positive samples. The presence and absence of associated sequences in samples trains a classifier to diagnose pathogen-specific exposure. We demonstrate the high accuracy of iCAT by testing on three TCR sequencing datasets. First, iCAT successfully diagnosed smallpox vaccinated versus naïve samples in an independent cohort of mice with 95% accuracy. Second, iCAT displayed 100% accuracy classifying naïve and monkeypox vaccinated mice. Finally, we demonstrate the use of iCAT on human samples before and after exposure to SARS-CoV-2, the virus behind the COVID-19 global pandemic. We were able to correctly classify the exposed samples with perfect accuracy. These experimental results show that iCAT capitalizes on the power of TCR sequencing to simplify infection diagnostics. iCAT provides the option of a graphical, user-friendly interface on top of usual R interface allowing it to reach a wider audience., Competing Interests: No competing interests were disclosed., (Copyright: © 2021 Rajeh A et al.)

Objective: To characterize the nature and prevalence of cognitive disorders in older adults with temporal lobe epilepsy (TLE) and compare their cognitive profiles to patients with amnestic mild cognitive impairment (ie, aMCI)., Methods: Seventy-one older patients with TLE, 77 aMCI, and 69 normal aging controls (NACs), all 55-80 years of age, completed neuropsychological measures of memory, language, executive function, and processing speed. An actuarial neuropsychological method designed to diagnose MCI was applied to individual patients to identify older adults with TLE who met diagnostic criteria for MCI (TLE-MCI). A linear classifier was performed to evaluate how well the diagnostic criteria differentiated patients with TLE-MCI from aMCI. In TLE, the contribution of epilepsy-related and vascular risk factors to cognitive impairment was evaluated using multiple regression., Results: Forty-three TLE patients (60%) met criteria for TLE-MCI, demonstrating marked deficits in both memory and language. When patients were analyzed according to age at seizure onset, 63% of those with an early onset (<50 years) versus 56% of those with late onset (≥ 50 years) met criteria for TLE-MCI. A classification model between TLE-MCI and aMCI correctly classified 81.1% (90.6% specificity, 61.3% sensitivity) of the cohort based on neuropsychological scores. Whereas TLE-MCI showed greater deficits in language relative to aMCI, patients with aMCI showed greater rapid forgetting on memory measures. Both epilepsy-related risk factors and the presence of leukoaraiosis on MRI contributed to impairment profiles in TLE-MCI., Significance: Cognitive impairment is a common comorbidity in epilepsy and it presents in a substantial number of older adults with TLE. Although the underlying etiologies are unknown in many patients, the TLE-MCI phenotype may be secondary to an accumulation of epilepsy and vascular risk factors, signal the onset of a neurodegenerative disease, or represent a combination of factors., (© 2020 International League Against Epilepsy.)

There are growing concerns about the generalizability of machine learning classifiers in neuroimaging. In order to evaluate this aspect across relatively large heterogeneous populations, we investigated four disorders: Autism spectrum disorder (N = 988), Attention deficit hyperactivity disorder (N = 930), Post-traumatic stress disorder (N = 87) and Alzheimer's disease (N = 132). We applied 18 different machine learning classifiers (based on diverse principles) wherein the training/validation and the hold-out test data belonged to samples with the same diagnosis but differing in either the age range or the acquisition site. Our results indicate that overfitting can be a huge problem in heterogeneous datasets, especially with fewer samples, leading to inflated measures of accuracy that fail to generalize well to the general clinical population. Further, different classifiers tended to perform well on different datasets. In order to address this, we propose a consensus-classifier by combining the predictive power of all 18 classifiers. The consensus-classifier was less sensitive to unmatched training/validation and holdout test data. Finally, we combined feature importance scores obtained from all classifiers to infer the discriminative ability of connectivity features. The functional connectivity patterns thus identified were robust to the classification algorithm used, age and acquisition site differences, and had diagnostic predictive ability in addition to univariate statistically significant group differences between the groups. A MATLAB toolbox called Machine Learning in NeuroImaging (MALINI), which implements all the 18 different classifiers along with the consensus classifier is available from Lanka et al. (2019) The toolbox can also be found at the following URL: https://github.com/pradlanka/malini .

Determining the boundaries around processes of 'normal' ageing and pathological cognitive deterioration associated with Alzheimer's disease (AD) is a difficult process, complicated further by the expansion of the disease category to include mild cognitive impairment (MCI). MCI is a label used to identify individuals with the symptoms of cognitive deterioration not attributable to 'normal ageing' but deemed to be 'at risk' of developing AD despite clinical uncertainty around whether individuals will go on to develop the condition in the future. Drawing on qualitative data gathered across an out-patient memory service, this article examines practitioners' accounts of the complexity associated with constructing the boundaries around MCI, AD and age in the clinic. Practitioners utilise uncertainty by classifying patients with MCI to keep them on for review to account for the possibility that patients may go on to develop AD but they also recognise the difficulty in predicting future progression to AD. Negotiating classification boundaries in the clinic is, however, not only about managing uncertainty regarding potential future risk but also about navigating the wider social and political context in which ageing and cognitive deterioration intersect, and are constructed and managed., (© 2019 The Author. Sociology of Health & Illness published by John Wiley & Sons Ltd on behalf of Foundation for SHIL.)

Accurate diagnostic classification of cancers can greatly help physicians to choose surveillance and treatment strategies for patients. Following the explosive growth of huge amounts of biological data, the shift from traditional biostatistical methods to computer-aided means has made machine-learning methods as an integral part of today's cancer prognosis prediction. In this work, we proposed a classification model by leveraging the power of extreme gradient boosting (XGBoost) and using increasingly complex multi-omics data with the aim to separate early stage and late stage cancers. We applied XGBoost model to four kinds of cancer data downloaded from TCGA and compared its performance with other popular machine-learning methods. The experimental results showed that our method obtained statistically significantly better or comparable predictive performance. The results of this study also revealed that DNA methylation outperforms other molecular data (mRNA expression and miRNA expression) in terms of accuracy and stability for discriminating between early stage and late stage groups. Furthermore, integration of multi-omics data by autoencoder can enhance the classification accuracy of cancer stage. Finally, we conducted bioinformatics analyses to assess the medical utility of the significant genes ranked by their importance using XGBoost algorithm. Extensively comparative experiments demonstrated that the XGBoost method has a remarkable performance in predicting the stage of cancer patients with multi-omics data. Moreover, identification of novel candidate genes associated with cancer stages would contribute to further elucidate disease pathogenesis and develop novel therapeutics., Competing Interests: Declaration of competing interest None., (Copyright © 2020 Elsevier Ltd. All rights reserved.)

Resting-state functional Magnetic Resonance Imaging (rs-fMRI) has been extensively used for diagnostic classification because it does not require task compliance and is easier to pool data from multiple imaging sites, thereby increasing the sample size. A MATLAB-based toolbox called Machine Learning in NeuroImaging (MALINI) for feature extraction and disease classification is presented. The MALINI toolbox extracts functional and effective connectivity features from preprocessed rs-fMRI data and performs classification between healthy and disease groups using any of 18 popular and widely used machine learning algorithms that are based on diverse principles. A consensus classifier combining the power of multiple classifiers is also presented. The utility of the toolbox is illustrated by accompanying data consisting of resting-state functional connectivity features from healthy controls and subjects with various brain-based disorders: autism spectrum disorder from autism brain imaging data exchange (ABIDE), Alzheimer's disease and mild cognitive impairment from Alzheimer's disease neuroimaging initiative (ADNI), attention deficit hyperactivity disorder from ADHD-200, and post-traumatic stress disorder and post-concussion syndrome acquired in-house. Results of classification performed on the above datasets can be obtained from the main article titled "Supervised machine learning for diagnostic classification from large-scale neuroimaging datasets" [1]. The data was divided into homogeneous and heterogeneous splits, such that 80% could be used for training, model building and cross-validation, while the remaining 20% of the data could be used as a hold-out independent test data for replication of the classification performance, to ensure the robustness of the classifiers to population variance in image acquisition site and age of the sample., (© 2020 The Authors.)

Machine learning techniques have been implemented to reveal brain features that distinguish people with autism spectrum disorders (ASDs) from typically developing (TD) peers. However, it remains unknown whether different neuroimaging modalities are equally informative for diagnostic classification. We combined anatomical magnetic resonance imaging (aMRI), diffusion weighted imaging (DWI), and functional connectivity MRI (fcMRI) using conditional random forest (CRF) for supervised learning to compare how informative each modality was in diagnostic classification. In-house data ( N  = 93) included 47 TD and 46 ASD participants, matched on age, motion, and nonverbal IQ. Four main analyses consistently indicated that fcMRI variables were significantly more informative than anatomical variables from aMRI and DWI. This was found (1) when the top 100 variables from CRF (run separately in each modality) were combined for multimodal CRF; (2) when only 19 top variables reaching >67% accuracy in each modality were combined in multimodal CRF; and (3) when the large number of initial variables (before dimension reduction) potentially biasing comparisons in favor of fcMRI was reduced using a less granular region of interest scheme. Consistent superiority of fcMRI was even found (4) when 100 variables per modality were randomly selected, removing any such potential bias. Greater informative value of functional than anatomical modalities may relate to the nature of fcMRI data, reflecting more closely behavioral condition, which is also the basis of diagnosis, whereas brain anatomy may be more reflective of neurodevelopmental history.

Cognitive diagnosis models (CDMs) have been used as psychometric tools in educational assessments to estimate students' proficiency profiles. However, most CDMs assume that all students adopt the same strategy when approaching problems in an assessment, which may not be the case in practice. This study develops a generalized multiple-strategy CDM for dichotomous response data. The proposed model provides a unified framework to accommodate various condensation rules (e.g., conjunctive, disjunctive, and additive) and different strategy selection approaches (i.e., probability-matching, over-matching, and maximizing). Model parameters are estimated using the marginal maximum likelihood estimation via expectation-maximization algorithm. Simulation studies showed that the parameters of the proposed model can be adequately recovered and that the proposed model was relatively robust to some types of model misspecifications. A set of real data was analysed as well to illustrate the use of the proposed model in practice., (© 2019 The British Psychological Society.)

Anorexia nervosa (AN) and body dysmorphic disorder (BDD) are serious psychiatric conditions, both of which are associated with a disturbance of body image. The aim of this paper was to review those studies that have directly compared groups of individuals with AN and BDD, to determine similarities and differences in presentation between the two conditions. The literature was searched to September 2018, and studies were included if they were English language, empirical research papers published in peer-reviewed journals, specifically comparing AN and BDD patients. Fifteen relevant studies were identified. The results suggested that individuals with AN and BDD share a number of similarities, including their degree of body dissatisfaction. Differences between the conditions included primary concerns with body shape and weight in AN, and much more diffuse concerns (but predominantly the face) in BDD. The small number of studies, along with the limited replication of results emphasises the need for greater research in this area. However, the studies undertaken to date highlight the high degree of overlap between AN and BDD and suggests that the conditions may represent similar body image disorders. This has implications for the nosological status of AN and BDD., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Frontal-subcortical circuit dysfunction is commonly associated with apathy, a neuropsychiatric sequelae of human immunodeficiency virus type-1 (HIV-1). Behavioral and neurochemical indices of apathy in the nucleus accumbens (NAc), a key brain region involved in frontal-subcortical circuitry, are influenced by the factor of biological sex. Despite evidence of sex differences in HIV-1, the effect of biological sex on medium spiny neurons (MSNs), which are central integrators of frontal-subcortical input, has not been systematically evaluated. In the present study, a DiOlistic labeling technique was used to investigate the role of long-term HIV-1 viral protein exposure, the factor of biological sex, and their possible interaction, on synaptic dysfunction in MSNs of the NAc in the HIV-1 transgenic (Tg) rat. HIV-1 Tg rats, independent of biological sex, displayed profound alterations in synaptic connectivity, evidenced by a prominent shift in the distribution of dendritic spines. Female HIV-1 Tg rats, but not male HIV-1 Tg rats, exhibited alterations in dendritic branching and neuronal arbor complexity relative to control animals, supporting an alteration in glutamate neurotransmission. Morphologically, HIV-1 Tg male, but not female HIV-1 Tg rats, displayed a population shift towards decreased dendritic spine volume, suggesting decreased synaptic area, relative to control animals. Synaptic dysfunction accurately identified presence of the HIV-1 transgene, dependent upon biological sex, with at least 80% accuracy (i.e., Male: 80%; Female: 90%). Collectively, these results support a primary alteration in circuit connectivity, the mechanism of which is dependent upon biological sex. Understanding the effect of biological sex on the underlying neural mechanism for HIV-1 associated apathy is vital for the development of sex-based therapeutics and cure strategies.

Internet gaming disorder (IGD) is often diagnosed on the basis of nine underlying criteria from the latest version of the Diagnostic and Statistical Manual of Mental Disorders (DSM-5). Here, we examined whether such symptom-based categorization could be translated into computation-based classification. Structural MRI (sMRI) and diffusion-weighted MRI (dMRI) data were acquired in 38 gamers diagnosed with IGD, 68 normal gamers diagnosed as not having IGD, and 37 healthy non-gamers. We generated 108 features of gray matter (GM) and white matter (WM) structure from the MRI data. When regularized logistic regression was applied to the 108 neuroanatomical features to select important ones for the distinction between the groups, the disordered and normal gamers were represented in terms of 43 and 21 features, respectively, in relation to the healthy non-gamers, whereas the disordered gamers were represented in terms of 11 features in relation to the normal gamers. In support vector machines (SVM) using the sparse neuroanatomical features as predictors, the disordered and normal gamers were discriminated successfully, with accuracy exceeding 98%, from the healthy non-gamers, but the classification between the disordered and normal gamers was relatively challenging. These findings suggest that pathological and non-pathological gamers as categorized with the criteria from the DSM-5 could be represented by sparse neuroanatomical features, especially in the context of discriminating those from non-gaming healthy individuals.

Complex disorders like Gulf War illness (GWI) often defy diagnosis on the basis of a single biomarker and may only be distinguishable by considering the co-expression of multiple markers measured in response to a challenge. We demonstrate the practical application of such an approach using an example where blood was collected from 26 GWI, 13 healthy control subjects, and 9 unhealthy controls with chronic fatigue at three points during a graded exercise challenge. A 3-way multivariate projection model based on 12 markers of endocrine and immune function was constructed using a training set of n = 10 GWI and n = 11 healthy controls. These groups were separated almost completely on the basis of two co-expression patterns. In a separate test set these same features allowed for discrimination of new GWI subjects (n = 16) from unhealthy (n = 9) and healthy control subjects with a sensitivity of 70% and a specificity of 90%.

Functional diagnostic examinations such as clinical functional analysis and manual structural analysis ('orthopedic tests') allow the dentist to establish a structured diagnosis. Previously, the process of correlating findings with the appropriate diagnoses was guided by human thought processes alone. The experimental diagnostic randomized controlled trial (RCT) in this study investigated whether computer-aided diagnosis (CADx) of temporomandibular disorders (TMD) offers quality advantages over traditional diagnosis (TRAD)., Subjects and Methods: Thirty-nine 5th-year dental students (examiners) at a university in Hamburg, Germany, received joint training in the diagnosis of TMD by clinical functional analysis and manual structural analysis ('orthopedic tests'). This study is based on anonymized data from 10 patients who were consecutively recruited at a specialized TMJ treatment center. The examiners were randomly allocated to two groups. Each examiner established a structured diagnosis through a traditional diagnostic method and by computer-aided diagnosis (CMDfact 4 functional diagnostics software) of five cases, each using the AB/BA crossover design. The diagnoses established by each individual examiner were then compared with the corresponding reference diagnoses (gold standard) and with those of the other examiners., Results: Cohen's kappa coefficient analysis showed that median agreement with the reference diagnoses was significantly higher (P < 0.001) with computer assistance (median 0.692) than without it (0.553). Fleiss' kappa showed that the median interexaminer consistency of diagnoses was significantly higher (P < 0.001) with computer assistance (0.497) than with traditional diagnostic methods alone (0.271). Likewise, the number of false-positive and false-negative diagnoses was significantly lower with computer assistance (P < 0.001)., Conclusions: This study determined that dentists who are less experienced and not specialized in dental functional diagnostics achieve a significantly better and more consistent diagnostic quality with computer assistance by means of the system used in this study. Therefore, it seems advisable to extend computer-aided diagnostics to further functional examination techniques (condylar position analysis and jaw motion analysis).

Hepatitis E virus (HEV) is one of the major pathogens that cause acute viral hepatitis. The human (genotypes 1 and 2) and zoonotic (genotypes 3 and 4) groups of HEV present different epidemiology and clinical features. In this study, we developed a classification method for rapidly classifying HEV into human or zoonotic groups that combines a general antigen test with a zoonotic group-specific antigen test. Evaluation of serial samples from HEV-infected rhesus monkeys indicated that HEV antigen-positive samples can be classified using the antigen-based classification method. The antigen-based classification method was evaluated further on 55 genotyped samples from acute hepatitis E patients, including 9 human and 46 zoonotic groups. The novel method was completely consistent with the sequencing results: 9/9 for the human groups (100%, 95% confidence interval [CI] 66.4-100%) and 46/46 for the zoonotic groups (100%, 95% CI 92.3-100%). This method was also successfully used for the clustering of some samples that could not be clustered by sequencing. Compared with the sequencing-based method, this method is less time-consuming, less expensive, and less technically complex and is therefore ideal for large numbers of samples. In conclusion, this study provides a convenient and sensitive method for classifying different groups of HEV, and it has potentially important public health applications, especially in underdeveloped areas that cannot afford the high cost of nucleic acid testing.

Objectives: Combinations of resting-state fMRI and machine-learning techniques are increasingly employed to develop diagnostic models for mental disorders. However, little is known about the neurobiological heterogeneity of depression and diagnostic machine learning has mainly been tested in homogeneous samples. Our main objective was to explore the inherent structure of a diverse unipolar depression sample. The secondary objective was to assess, if such information can improve diagnostic classification., Materials and Methods: We analyzed data from 360 patients with unipolar depression and 360 non-depressed population controls, who were subdivided into two independent subsets. Cluster analyses (unsupervised learning) of functional connectivity were used to generate hypotheses about potential patient subgroups from the first subset. The relationship of clusters with demographical and clinical measures was assessed. Subsequently, diagnostic classifiers (supervised learning), which incorporated information about these putative depression subgroups, were trained., Results: Exploratory cluster analyses revealed two weakly separable subgroups of depressed patients. These subgroups differed in the average duration of depression and in the proportion of patients with concurrently severe depression and anxiety symptoms. The diagnostic classification models performed at chance level., Limitations: It remains unresolved, if subgroups represent distinct biological subtypes, variability of continuous clinical variables or in part an overfitting of sparsely structured data., Conclusions: Functional connectivity in unipolar depression is associated with general disease effects. Cluster analyses provide hypotheses about potential depression subtypes. Diagnostic models did not benefit from this additional information regarding heterogeneity., (Copyright © 2017 Elsevier B.V. All rights reserved.)

Focusing on the case of medically unexplained symptoms (MUS), this article explores diagnostic classification in the absence of biomedical evidence or other strong medical warrants for diagnosis. The data are from three focus group interviews with Norwegian general practitioners (GPs) conducted in 2015, that centred on the issue of what diagnoses to use (or not) for MUS. The qualitative analysis reconstructs the logic underlying GPs' diagnostic accounts, which centred on the meaning of diagnostic categories and on anticipating how 'generalised others' would respond to those meanings (called 'diagnosing by anticipation'). The analysis suggests that GPs confer diagnoses by balancing unwarranted medical accuracy and anticipated harmful diagnostic consequences; the goal of diagnosis was finding categories in the International Classification of Primary Care that would yield acceptable results, without making a liar of the GP in the process. Drawing on the distinction between diagnosis as colligation and classification, the findings and their relevance for medical sociology are discussed. Counter to frequent descriptions as 'illness that cannot be diagnosed', the analysis shows how GPs can diagnose MUS in the bureaucratic sense of diagnosis as classification - a sense that has been missing from sociological view., (© 2017 Foundation for the Sociology of Health & Illness.)

Background: The approach to apply multivariate pattern analyses based on neuro imaging data for outcome prediction holds out the prospect to improve therapeutic decisions in mental disorders. Patients suffering from panic disorder with agoraphobia (PD/AG) often exhibit an increased perception of bodily sensations. The purpose of this investigation was to assess whether multivariate classification applied to a functional magnetic resonance imaging (fMRI) interoception paradigm can predict individual responses to cognitive behavioral therapy (CBT) in PD/AG., Methods: This analysis is based on pretreatment fMRI data during an interoceptive challenge from a multicenter trial of the German PANIC-NET. Patients with DSM-IV PD/AG were dichotomized as responders ( n  = 30) or non-responders ( n  = 29) based on the primary outcome (Hamilton Anxiety Scale Reduction ≥50%) after 6 weeks of CBT (2 h/week). fMRI parametric maps were used as features for response classification with linear support vector machines (SVM) with or without automated feature selection. Predictive accuracies were assessed using cross validation and permutation testing. The influence of methodological parameters and the predictive ability for specific interoception-related symptom reduction were further evaluated., Results: SVM did not reach sufficient overall predictive accuracies (38.0-54.2%) for anxiety reduction in the primary outcome. In the exploratory analyses, better accuracies (66.7%) were achieved for predicting interoception-specific symptom relief as an alternative outcome domain. Subtle information regarding this alternative response criterion but not the primary outcome was revealed by post hoc univariate comparisons., Conclusion: In contrast to reports on other neurofunctional probes, SVM based on an interoception paradigm was not able to reliably predict individual response to CBT. Results speak against the clinical applicability of this technique.

The underlying structure of problematic gambling behaviors, such as those assessed by the South Oaks Gambling Screen (SOGS), remain unknown: Can problem gambling be assessed unidimensionally or should multiple qualitatively different dimensions be taken into account, and if so, what do these qualitative dimensions indicate? How significant are the deviations from unidimensionality in practice? A cross-sectional random sample of Finns aged 15-74 (n = 4,484) was drawn from the Population Information Registry and surveyed in 2011-2012. Analyses were conducted using descriptive statistics, Confirmatory factor analysis (CFA) and multidimensional item response theory (MIRT) models. Altogether, 14.9% of the population endorsed at least one of the 20 SOGS items, but nine items had low endorsement rates (≤ 0.2%). CFA and MIRT techniques suggested that individuals differed from each other in two positively correlated (r = 0.70) underlying dimensions: "impact on self primarily" and "impact on others also". This two-factor correlated-factors model can be reinterpreted as a bifactor model with one general gambling-problem factor and two specific factors with similar interpretation as in the correlated-factors model but with non-overlapping items. The two specific factors may provide clinically useful information without extra costs of assessment., (© 2017 Scandinavian Psychological Associations and John Wiley & Sons Ltd.)

Introduction: We established a method for diagnostic harmonization across multiple studies of preclinical Alzheimer's disease and validated the method by examining its relationship with clinical status and cognition., Methods: Cognitive and clinical data were used from five studies ( N  = 1746). Consensus diagnoses established in each study used criteria to identify progressors from normal cognition to mild cognitive impairment. Correspondence was evaluated between these consensus diagnoses and three algorithmic classifications based on (1) objective cognitive impairment in 2+ tests only; (2) a Clinical Dementia Rating (CDR) of ≥0.5 only; and (3) both. Associations between baseline cognitive performance and cognitive change were each tested in relation to progression to algorithm-based classifications., Results: In each study, an algorithmic classification based on both cognitive testing cutoff scores and a CDR ≥0.5 provided optimal balance of sensitivity and specificity (areas under the curve: 0.85-0.95). Over an average 6.6 years of follow-up (up to 28 years), N  = 186 initially cognitively normal participants aged on average 64 years at baseline progressed (incidence rate: 15.3 people/1000 person-years). Baseline cognitive scores and cognitive change were associated with future diagnostic status using this algorithmic classification., Discussion: Both cognitive tests and CDR ratings can be combined across multiple studies to obtain a reliable algorithmic classification with high specificity and sensitivity. This approach may be applicable to large cohort studies and to clinical trials focused on preclinical Alzheimer's disease because it provides an alternative to implementation of a time-consuming adjudication panel.