Search

Detecting voice disorders from voice recordings could allow for frequent, remote, and low-cost screening before costly clinical visits and a more invasive laryngoscopy examination. Our goals were to detect unilateral vocal fold paralysis (UVFP) from voice recordings using machine learning, to identify which acoustic variables were important for prediction to increase trust, and to determine model performance relative to clinician performance. Patients with confirmed UVFP through endoscopic examination (N = 77) and controls with normal voices matched for age and sex (N = 77) were included. Voice samples were elicited by reading the Rainbow Passage and sustaining phonation of the vowel "a". Four machine learning models of differing complexity were used. SHapley Additive exPlanations (SHAP) was used to identify important features. The highest median bootstrapped ROC AUC score was 0.87 and beat clinician's performance (range: 0.74-0.81) based on the recordings. Recording durations were different between UVFP recordings and controls due to how that data was originally processed when storing, which we can show can classify both groups. And counterintuitively, many UVFP recordings had higher intensity than controls, when UVFP patients tend to have weaker voices, revealing a dataset-specific bias which we mitigate in an additional analysis. We demonstrate that recording biases in audio duration and intensity created dataset-specific differences between patients and controls, which models used to improve classification. Furthermore, clinician's ratings provide further evidence that patients were over-projecting their voices and being recorded at a higher amplitude signal than controls. Interestingly, after matching audio duration and removing variables associated with intensity in order to mitigate the biases, the models were able to achieve a similar high performance. We provide a set of recommendations to avoid bias when building and evaluating machine learning models for screening in laryngology.

Background and purpose: Magnetic Resonance Imaging (MRI)-guided Stereotactic body radiotherapy (SBRT) treatment to prostate bed after radical prostatectomy has garnered growing interests. The aim of this study is to evaluate intra-fractional anatomic and dose/volume metric variations for patients receiving this treatment. Materials and methods: Nineteen patients who received 30–34 Gy in 5 fractions on a 0.35T MR-Linac were included. Pre- and post-treatment MRIs were acquired for each fraction (total of 75 fractions). The Clinical Target Volume (CTV), bladder, rectum, and rectal wall were contoured on all images. Volumetric changes, Hausdorff distance, Mean Distance to Agreement (MDA), and Dice similarity coefficient (DSC) for each structure were calculated. Median value and Interquartile range (IQR) were recorded. Changes in target coverage and Organ at Risk (OAR) constraints were compared and evaluated using Wilcoxon rank sum tests at a significant level of 0.05. Results: Bladder had the largest volumetric changes, with a median volume increase of 48.9 % (IQR 28.9–76.8 %) and a median MDA of 5.1 mm (IQR 3.4–7.1 mm). Intra-fractional CTV volume remained stable with a median volume change of 1.2 % (0.0–4.8 %). DSC was 0.97 (IQR 0.94–0.99). For the dose/volume metrics, there were no statistically significant changes observed except for an increase in bladder hotspot and a decrease of bladder V32.5 Gy and mean dose. The CTV V95% changed from 99.9 % (IQR 98.8–100 %) to 99.6 % (IQR 93.9–100 %). Conclusion: Despite intra-fractional variations of OARs, CTV coverage remained stable during MRI-guided SBRT treatments for the prostate bed.

Background : : Surgically altered anatomy remains a challenge when performing advanced endoscopic procedures, including endoscopic retrograde cholangiopancreatography (ERCP). While ERCP maintains a success rate of 90% to 95% in patients with native anatomy, the data are less robust for patients with post-pancreaticoduodenectomy (PD) anatomy. We conducted a retrospective analysis of the technical success (TS) and clinical success (CS) rates of ERCP in post-PD patients. In addition, we describe our experience using novel rigidizing overtubes to facilitate post-PD ERCP. Methods : : Patients with PD referred to our institution between 2006 and 2021 for ERCP were included. Major outcomes included the TS rate (successful biliary intervention) and the CS rate (improvement in patient symptomatology with or without normalization of bilirubin levels). Results : : In total, 47 patients underwent 102 ERCPs for biliary (n = 98) and pancreatic (n = 4) indications. The overall TS and CS rates were 82.4% and 75.5%, respectively. Rigidizing overtubes were utilized in 5 patients who underwent 11 ERCPs, with TS and CS rates of 90.9% and 90.9%, respectively. The overall adverse event rate was 4.9%, with no adverse events noted in cases with rigidizing overtubes. Conclusion : : Despite the challenges in ERCP in patients with surgically altered anatomy, this retrospective analysis demonstrates a moderately high TS rate with minimal adverse events. A rigidizing overtube may be utilized to improve TS and CS in patients with post-surgical anatomy.

Abstract In the face of the global pandemic caused by the disease COVID-19, researchers have increasingly turned to simple measures to detect and monitor the presence of the disease in individuals at home. We sought to determine if measures of neuromotor coordination, derived from acoustic time series, as well as phoneme-based and standard acoustic features extracted from recordings of simple speech tasks could aid in detecting the presence of COVID-19. We further hypothesized that these features would aid in characterizing the effect of COVID-19 on speech production systems. A protocol, consisting of a variety of speech tasks, was administered to 12 individuals with COVID-19 and 15 individuals with other viral infections at University Hospital Galway. From these recordings, we extracted a set of acoustic time series representative of speech production subsystems, as well as their univariate statistics. The time series were further utilized to derive correlation-based features, a proxy for speech production motor coordination. We additionally extracted phoneme-based features. These features were used to create machine learning models to distinguish between the COVID-19 positive and other viral infection groups, with respiratory- and laryngeal-based features resulting in the highest performance. Coordination-based features derived from harmonic-to-noise ratio time series from read speech discriminated between the two groups with an area under the ROC curve (AUC) of 0.94. A longitudinal case study of two subjects, one from each group, revealed differences in laryngeal based acoustic features, consistent with observed physiological differences between the two groups. The results from this analysis highlight the promise of using nonintrusive sensing through simple speech recordings for early warning and tracking of COVID-19.

PurposeRecent advancements in obtaining image-based biomarkers from CT images have enabled lung function characterization, which could aid in lung interventional planning. However, the regional heterogeneity in these biomarkers has not been well documented, yet it is critical to several procedures for lung cancer and COPD. The purpose of this paper is to analyze the interlobar and intralobar heterogeneity of tissue elasticity and study their relationship with COPD severity.MethodsWe retrospectively analyzed a set of 23 lung cancer patients for this study, 14 of whom had COPD. For each patient, we employed a 5DCT scanning protocol to obtain end-exhalation and end-inhalation images and semi-automatically segmented the lobes. We calculated tissue elasticity using a biomechanical property estimation model. To obtain a measure of lobar elasticity, we calculated the mean of the voxel-wise elasticity values within each lobe. To analyze interlobar heterogeneity, we defined an index that represented the properties of the least elastic lobe as compared to the rest of the lobes, termed the Elasticity Heterogeneity Index (EHI). An index of 0 indicated total homogeneity, and higher indices indicated higher heterogeneity. Additionally, we measured intralobar heterogeneity by calculating the coefficient of variation of elasticity within each lobe.ResultsThe mean EHI was 0.223 ± 0.183. The mean coefficient of variation of the elasticity distributions was 51.1% ± 16.6%. For mild COPD patients, the interlobar heterogeneity was low compared to the other categories. For moderate-to-severe COPD patients, the interlobar and intralobar heterogeneities were highest, showing significant differences from the other groups.ConclusionWe observed a high level of lung tissue heterogeneity to occur between and within the lobes in all COPD severity cases, especially in moderate-to-severe cases. Heterogeneity results demonstrate the value of a regional, function-guided approach like elasticity for procedures such as surgical decision making and treatment planning.

PurposeFor a cohort of prostate cancer patients treated on an MR-guided radiotherapy (MRgRT) system, we retrospectively analyzed urethral interfractional geometric and dosimetric variations based on onboard MRIs acquired at different timepoints and evaluated onboard prostatic urethra visualization for urethra-focused online adaptive RT.MethodsTwenty-six prostate cancer patients were prospectively scanned on a 0.35-T MRgRT system using an optimized T2-weighted HASTE sequence at simulation and final fraction. Two radiation oncologists (RO1 and RO2) contoured the urethras on all HASTE images. The simulation and final fraction HASTE images were rigidly registered, and urethral interobserver and interfractional geometric variation was evaluated using the 95th percentile Hausdorff distance (HD95), mean distance to agreement (MDA), center-of-mass shift (COMS), and DICE coefficient. For dosimetric analysis, simulation and final fraction HASTE images were registered to the 3D bSSFP planning MRI and 3D bSSFP final setup MRI, respectively. Both ROs’ urethra contours were transferred from HASTE images for initial treatment plan optimization and final fraction dose estimation separately. Stereotactic body radiotherapy (SBRT) plans, 40 Gy in 5 fractions, were optimized to meet clinical constraints, including urethral V42Gy ≤0.03 cc, on the planning MRI. The initial plan was then forward calculated on the final setup MRI to estimate urethral dose on the final fraction and evaluate urethral dosimetric impact due to anatomy change.ResultsThe average interobserver HD95, MDA, COMS, and DICE were 2.85 ± 1.34 mm, 1.02 ± 0.36 mm, 3.16 ± 1.61 mm, and 0.58 ± 0.15, respectively. The average interfractional HD95, MDA, COMS, and DICE were 3.26 ± 1.54 mm, 1.29 ± 0.54 mm, 3.34 ± 2.01 mm, and 0.49 ± 0.18, respectively. All patient simulation MRgRT plans met all clinical constraints. For RO1 and RO2, 23/26 (88%) and 21/26 (81%) patients’ final fraction estimated urethral dose did not meet the planned constraint. The average urethral V42Gy change was 0.48 ± 0.58 cc.ConclusionUrethral interfractional motion and anatomic change can result in daily treatment violating urethral constraints. Onboard MRI with good visualization of the prostatic urethra can be a valuable tool to help better protect the urethra through patient setup or online adaptive RT.

When reading a sentence, individual words can be combined to create more complex meaning. In this study, we sought to uncover brain regions that reflect the representation of the meaning of sentences at the topic level, as opposed to the meaning of their individual constituent words when considered irrespective of their context. Using fMRI, we recorded the neural activity of participants while reading sentences. We constructed a topic-level sentence representations using the final layer of a convolutional neural network (CNN) trained to classify Wikipedia sentences into broad semantic categories. This model was contrasted with word-level sentence representations constructed using the average of the word embeddings constituting the sentence. Using representational similarity analysis, we found that the medial prefrontal cortex, lateral anterior temporal lobe, precuneus, and angular gyrus more strongly represent sentence topic-level, compared to word-level, meaning, uncovering the important role of these semantic system regions in the representation of topic-level meaning. Results were comparable when sentence meaning was modelled with a multilayer perceptron that was not sensitive to word order within a sentence, suggesting that the learning objective, in the terms of the topic being modelled, is the critical factor in capturing these neural representational spaces.

Background and study aims Colonoscopy completion reduces post-colonoscopy colorectal cancer. As a result, there have been attempts at implementing artificial intelligence to automate the detection of the appendiceal orifice (AO) for quality assurance. However, the utilization of these algorithms has not been demonstrated in suboptimal conditions, including variable bowel preparation. We present an automated computer-assisted method using a deep convolutional neural network to detect the AO irrespective of bowel preparation. Methods A total of 13,222 images (6,663 AO and 1,322 non-AO) were extracted from 35 colonoscopy videos recorded between 2015 and 2018. The images were labelled with Boston Bowel Preparation Scale scores. A total of 11,900 images were used for training/validation and 1,322 for testing. We developed a convolutional neural network (CNN) with a DenseNet architecture pre-trained on ImageNet as a feature extractor on our data and trained a classifier uniquely tailored for identification of AO and non-AO images using binary cross entropy loss. Results The deep convolutional neural network was able to correctly classify the AO and non-AO images with an accuracy of 94 %. The area under the receiver operating curve of this neural network was 0.98. The sensitivity, specificity, positive predictive value, and negative predictive value of the algorithm were 0.96, 0.92, 0.92 and 0.96, respectively. AO detection was > 95 % regardless of BBPS scores, while non-AO detection improved from BBPS 1 score (83.95 %) to BBPS 3 score (98.28 %). Conclusions A deep convolutional neural network was created demonstrating excellent discrimination between AO from non-AO images despite variable bowel preparation. This algorithm will require further testing to ascertain its effectiveness in real-time colonoscopy.

Abstract Objective There are many barriers to accessing mental health assessments including cost and stigma. Even when individuals receive professional care, assessments are intermittent and may be limited partly due to the episodic nature of psychiatric symptoms. Therefore, machine‐learning technology using speech samples obtained in the clinic or remotely could one day be a biomarker to improve diagnosis and treatment. To date, reviews have only focused on using acoustic features from speech to detect depression and schizophrenia. Here, we present the first systematic review of studies using speech for automated assessments across a broader range of psychiatric disorders. Methods We followed the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis (PRISMA) guidelines. We included studies from the last 10 years using speech to identify the presence or severity of disorders within the Diagnostic and Statistical Manual of Mental Disorders (DSM‐5). For each study, we describe sample size, clinical evaluation method, speech‐eliciting tasks, machine learning methodology, performance, and other relevant findings. Results 1395 studies were screened of which 127 studies met the inclusion criteria. The majority of studies were on depression, schizophrenia, and bipolar disorder, and the remaining on post‐traumatic stress disorder, anxiety disorders, and eating disorders. 63% of studies built machine learning predictive models, and the remaining 37% performed null‐hypothesis testing only. We provide an online database with our search results and synthesize how acoustic features appear in each disorder. Conclusion Speech processing technology could aid mental health assessments, but there are many obstacles to overcome, especially the need for comprehensive transdiagnostic and longitudinal studies. Given the diverse types of data sets, feature extraction, computational methodologies, and evaluation criteria, we provide guidelines for both acquiring data and building machine learning models with a focus on testing hypotheses, open science, reproducibility, and generalizability. Level of Evidence 3a

Purpose: The clinical efficacy of radiation therapy is mechanistically linked to ionization-induced free radicals that cause cell and tissue injury through direct and indirect mechanisms. Free radical reaction dynamics are influenced by many factors and can be manipulated by static weak magnetic fields (WMF) that perturb singlet-triplet state interconversion. Our study exploits this phenomenon to directly increase ionizing radiation (IR) dose absorption in tumors by combining WMF with radiation therapy as a new and effective method to improve treatment. Methods and Materials: Coils were custom made to produce both homogeneous and gradient magnetic fields. The gradient coil enabled simultaneous in vitro assessment of free radical/reactive oxygen species reactivity across multiple field strengths from 6 to 66 G. First, increases in IR-induced free radical concentrations using oxidant-sensitive fluorescent dyes in a cell-free system were measured and verified. Next, human and murine cancer cell lines were evaluated in in vitro and in vivo models after exposure to clinically relevant doses of IR in combination with WMF. Results: Cellular responses to IR and WMF were field strength and cell line dependent. WMF was able to enhance IR effects on reactive oxygen species formation, DNA double-strand break formation, cell death, and tumor growth. Conclusions: We demonstrate that the external presence of a magnetic field enhances radiation-induced cancer cell injury and death in vitro and in vivo. The effect extends beyond the timeframe when free radicals are induced in the presence of radiation into the window when endogenous free radicals are produced and therefore extends the applicability of this novel adjunct to cancer therapy in the context of radiation treatment.

In the past few years, radiotherapy (RT) has experienced a major technological innovation with the development of hybrid machines combining magnetic resonance (MR) imaging and linear accelerators. This new technology for MR-guided cancer treatment has the potential to revolutionize the field of adaptive RT due to the opportunity to provide high-resolution, real-time MR imaging before and during treatment application. However, from a technical point of view, several challenges remain which need to be tackled to ensure safe and robust real-time adaptive MR-guided RT delivery. In this manuscript, several technical challenges to MR-guided RT are discussed. Starting with magnetic field strength tradeoffs, the potential and limitations for purely MR-based RT workflows are discussed. Furthermore, the current status of real-time 3D MR imaging and its potential for real-time RT are summarized. Finally, the potential of quantitative MR imaging for future biological RT adaptation is highlighted.

PURPOSE: Health system constraints limit access to HIV and cancer treatment programs in sub-Saharan Africa. Limited access and continuity of care affect morbidity and mortality of patients with cancer and HIV. We assessed barriers in the care cascade of comorbid HIV and cancer. PATIENTS AND METHODS: Structured interviews were conducted with 100 adult patients with HIV infection and new diagnoses of cancer at the Uganda Cancer Institute. Participants completed follow-up questionnaires after 1 year to assess ongoing engagement with and barriers to care. RESULTS: The median time from new-onset cancer symptoms to initiation of cancer care at the Uganda Cancer Institute was 209 days (interquartile range, 113 to 384 days). Persons previously established in HIV care waited less overall to initiate cancer care (P = .04). Patients established in HIV care experienced shorter times from initial symptoms to seeking of cancer care (P = .02) and from seeking of care to cancer diagnosis (P = .048). Barriers to receiving care for HIV and cancer included difficulty traveling to multiple clinics/hospitals (46%), conflicts between HIV and cancer appointments (23%), prohibitive costs (21%), and difficulty adhering to medications (15%). Reporting of any barriers to care was associated with premature discontinuation of cancer treatment (P = .003). CONCLUSION: Patients with HIV-associated malignancies reported multiple barriers to receiving care for both conditions, although knowledge of HIV status and engagement in HIV care before presentation with malignancy reduced subsequent time to the start of cancer treatment. This study provides evidence to support creation and evaluation of integrated HIV and cancer care models.

Purpose: Dosimetric predictors of toxicity after Stereotactic Body Radiation Therapy (SBRT) are not well-established. We sought to develop a multivariate model that predicts Common Terminology Criteria for Adverse Events (CTCAE) late grade 2 or greater genitourinary (GU) toxicity by interrogating the entire dose-volume histogram (DVH) from a large cohort of prostate cancer patients treated with SBRT on prospective trials.Methods: Three hundred and thirty-nine patients with late CTCAE toxicity data treated with prostate SBRT were identified and analyzed. All patients received 40 Gy in five fractions, every other day, using volumetric modulated arc therapy. For each patient, we examined 910 candidate dosimetric features including maximum dose, volumes of each organ [CTV, organs at risk (OARs)], V100%, and other granular volumetric/dosimetric indices at varying volumetric/dosimetric values from the entire DVH as well as ADT use to model and predict toxicity from SBRT. Training and validation subsets were generated with 90 and 10% of the patients in our cohort, respectively. Predictive accuracy was assessed by calculating the area under the receiver operating curve (AROC). Univariate analysis with student t-test was first performed on each candidate DVH feature. We subsequently performed advanced machine-learning multivariate analyses including classification and regression tree (CART), random forest, boosted tree, and multilayer neural network.Results: Median follow-up time was 32.3 months (range 3–98.9 months). Late grade ≥2 GU toxicity occurred in 20.1% of patients in our series. No single dosimetric parameter had an AROC for predicting late grade ≥2 GU toxicity on univariate analysis that exceeded 0.599. Optimized CART modestly improved prediction accuracy, with an AROC of 0.601, whereas other machine learning approaches did not improve upon univariate analyses.Conclusions: CART-based machine learning multivariate analyses drawing from 910 dosimetric features and ADT use modestly improves upon clinical prediction of late GU toxicity alone, yielding an AROC of 0.601. Biologic predictors may enhance predictive models for identifying patients at risk for late toxicity after SBRT.

Purpose: To compare early pain relief and late quadriceps function after anterior cruciate ligament reconstruction (ACLR) with hamstring autograft in adolescent patients treated with either a continuous femoral nerve block (cFNB) or continuous adductor canal block (cACB). Methods: We retrospectively reviewed a consecutive series of adolescent patients who underwent ACLR and received either a cACB or cFNB for postoperative pain management. Over a 1-year period, all patients underwent ACLR with cFNBs. Over the subsequent 9 months, all patients underwent their ACLR with cACBs. Patient demographics, postoperative pain scores, opioid consumption, satisfaction and complications, and dates and results of quadriceps function derived at the Return to Sports evaluation were compared. Results: Ninety-one patients (53 cFNB, 38 cACB) were reviewed. There were no differences in the demographics of the 2 groups. There were no statistically significant differences between groups in variations in postoperative pain scores (P = .21), or satisfaction with the blocks (P = .93). Patients in the cFNB group consumed a greater number of opioid doses on postoperative day 3 (2.2 ± 2.1 doses cFNB, 1.1 ± 1.6 doses cACB, P = .03) and a greater number of opioid doses overall for postoperative days 1 to 3 (mean 6.8 ± 5.3 doses cFNB, 3.8 ± 2.1 doses cACB, P = .03). There was no difference in time to return of acceptable quadriceps strength and function when comparing the 2 groups (30.9 ± 7.7 weeks cFNB, 28.9 ± 6.6 weeks cACB, P = .087). Conclusions: We found few differences in postoperative analgesic requirements when comparing patients who underwent ACLR with hamstring autograft with a cACB to those who underwent a similar procedure with a cFNB. Return of quadriceps strength and function by six months did not appear to vary with regional technique, either cACB or cFNB, employed at surgery. Level of Evidence: III, Retrospective comparative study.

Purpose: To report a single-institutional experience using magnetic resonance imaging (MRI) guided radiation therapy for the reirradiation of recurrent and second cancers of the head and neck. Methods and materials: Between October 2014 and August 2016, 13 consecutive patients with recurrent or new primary cancers of the head and neck that occurred in a previously irradiated field were prospectively enrolled in an institutional registry trial to investigate the feasibility and efficacy of MRI guided radiation therapy using a 0.35-T MRI scanner with a cobalt-60 radiation therapy source called the ViewRay system (ViewRay Inc., Cleveland, OH). Eligibility criteria included biopsy-proven evidence of recurrent or new primary squamous cell carcinoma of the head and neck, measurable disease, and previous radiation to >60 Gy. MRI guided reirradiation was delivered either using intensity modulated radiation therapy with conventional fractionation to a median dose of 66 Gy or stereotactic body radiation therapy (SBRT) using 7 to 8 Gy fractions on nonconsecutive days to a median dose of 40 Gy. Two patients (17%) received concurrent chemotherapy. Results: The 1- and 2-year estimates of in-field control were 72% and 72%, respectively. A total of 227 daily MRI scans were obtained to guide reirradiation. The 2-year estimates of overall survival and progression-free survival were 53% and 59%, respectively. There were no treatment-related fatalities or hospitalizations. Complications included skin desquamation, odynophagia, otitis externa, keratitis and/or conjunctivitis, and 1 case of aspiration pneumonia. Conclusions: Our preliminary findings show that reirradiation with MRI guided radiation therapy results in effective disease control with relatively low morbidity for patients with recurrent and second primary cancers of the head and neck. The superior soft tissue resolution of the MRI scans that were used for planning and delivery has the potential to improve the therapeutic ratio.

Reading comprehension is a fundamental resource for educational and social development. It is a skill that brings into play a diverse and complex set of processes and cognitive functions based on building a mental representation of a given text. We set out to study how different domain-general and linguistic abilities explain text comprehension in a population of secondary school students with low educational opportunities. The sample consisted of 45 adolescents between the ages of 13 and 15 from two secondary schools in the Province of Buenos Aires, Argentina. Each participant was evaluated both in-group and individually for three sessions during school hours. A text comprehension screening test and a battery of tasks that measure different underlying cognitive processes were administered. Using multiple linear regression, we found that vocabulary, non-word reading, and verbal inhibition are the skills that best explain reading comprehension skills. Understanding how much different domain-general and linguistic subprocesses are associated with text comprehension is key to designing effective interventions that are also grounded in theory.