Search

Background: The prevalence of depression among people with chronic pain remains unclear due to the heterogeneity of study samples and definitions of depression. We aimed to identify sources of variation in the prevalence of depression among people with chronic pain and generate clinical prediction models to estimate the probability of depression among individuals with chronic pain. Methods: Participants were from the UK Biobank. The primary outcome was a "lifetime" history of depression. The model's performance was evaluated using discrimination (optimism-corrected C statistic) and calibration (calibration plot). Results: Analyses included 24,405 patients with chronic pain (mean age 64.1 years). Among participants with chronic widespread pain, the prevalence of having a "lifetime" history of depression was 45.7% and varied (25.0–66.7%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.66; good calibration on the calibration plot) included age, BMI, smoking status, physical activity, socioeconomic status, gender, history of asthma, history of heart failure, and history of peripheral artery disease. Among participants with chronic regional pain, the prevalence of having a "lifetime" history of depression was 30.2% and varied (21.4–70.6%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.65; good calibration on the calibration plot) included age, gender, nature of pain, smoking status, regular opioid use, history of asthma, pain location that bothers you most, and BMI. Conclusions: There was substantial variability in the prevalence of depression among patients with chronic pain. Clinically relevant factors were selected to develop prediction models. Clinicians can use these models to assess patients' treatment needs. These predictors are convenient to collect during daily practice, making it easy for busy clinicians to use them. [ABSTRACT FROM AUTHOR]

Objective More than one-half of pregnant women experience pregnancy-related low back pain (LBP). Pregnancy-related LBP greatly affects activities of daily life, and although many interventions have been proposed, the optimal treatment for pregnancy-related LBP remains unclear. The purpose of this study was to compare conservative care strategies on their efficacy and safety for women with pregnancy-related LBP through systematic review with pairwise meta-analysis and network meta-analysis. Methods MEDLINE, Embase, the Cochrane Library, AMED, CINAHL, PEDro, PsycINFO, and ClinicalTrials.gov were searched from inception to November 2019. Randomized controlled trials and observational controlled studies were included without restriction to language, sample size, or duration of follow-up. Two independent investigators extracted the data and assessed the risk of bias. The quality of evidence was evaluated through Grading of Recommendations Assessment, Development and Evaluation. Results Twenty-three studies were included in the qualitative synthesis (18 randomized controlled trials were included in the network meta-analysis). For women with LBP during pregnancy, progressive muscle relaxation therapy (mean difference = −3.96; 95% CI = −7.19 to −0.74; moderate-quality evidence) and Kinesio Taping (mean difference = −3.71; 95% CI = −6.55 to −0.87; low-quality evidence) reduced pain intensity (Visual Analog Scale, range = 0 to 10) compared with placebo. Moderate-quality evidence suggested that transcutaneous electrical nerve stimulation improved physical function (mean difference = −6.33; 95% CI = −10.61 to −2.05; Roland Morris Disability Questionnaire, range = 0–24) compared with placebo. Conclusion For patients with LBP during pregnancy, progressive muscle relaxation therapy and Kinesio Taping may help to decrease pain, and transcutaneous electrical nerve stimulation may improve physical function. Impact This review helps fill the gap in evidence regarding optimal treatment for pregnancy-related LBP. Lay Summary If you have LBP during pregnancy, your physical therapist has evidence to support the use of progressive muscle relaxation therapy and Kinesio Taping to help decrease pain and the use of transcutaneous electrical nerve stimulation to help improve physical function. [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • The triterpenoids from Ganoderma resinaceum were analyzed by using UPLC-QTOF-MS. • A strategy for identification of triterpenoids has been developed. • Total 55 triterpenoids were identified from G. resinaceum. Abstract The triterpenoids from Ganoderma resinaceum were investigated by using UPLC-QTOF-MS and their fragmentation behaviors are summarized in detail. Based on the fragmentation pathways, a strategy for identification of triterpenoids has been developed. The main triterpenoids in G. resinaceum can be classified into 6 types (type 1-1, 1-2, 2-1, 2-2, 3-1, 3-2) in three steps. Each step was controlled by the characteristic ions, which are summarized from fragmentation pathways of 34 reference compounds. Total 55 triterpenoids were identified from G. resinaceum. Thirty-four of them were identified by using reference standards. The other unknown compounds were tentatively identified by using the developed identification strategy. This work is helpful for phytochemical investigation of G. resinaceum as well as quality control of materials containing triterpenoids. [ABSTRACT FROM AUTHOR]

Background The safety of front-line chemotherapies for the treatment of extensive stage small-cell lung cancer ( ED-SCLC) is uncertain. We carried out a network meta-analysis to compare the toxicity of different therapies for ED-SCLC. Methods We searched EMBASE, PubMed, CENTRAL and . We performed network meta-analysis on hematological (anemia, leukopenia, neutropenia, and thrombocytopenia) and non-hematological toxicities (diarrhea, infection, and nausea and vomiting). Results Nine studies with 2317 patients were included. Etoposide with carboplatin ( EC) was associated with a higher incidence of anemia (odds ratio [ OR] 2.02, 95% confidence interval [ CI] 1.13-3.63), leukopenia ( OR 2.67, 95% CI 1.25-5.72), neutropenia ( OR 12.08, 95% CI 2.13-68.66), and thrombocytopenia ( OR 2.73, 95% CI 1.27-5.85) compared with irinotecan with carboplatin ( IC). Similarly, etoposide with cisplatin ( EP) was associated with a higher incidence of anemia ( OR 1.70, 95% CI 1.13-2.56), leukopenia ( OR 2.65, 95% CI 1.34-5.28), neutropenia ( OR 5.70, 95% CI 2.93-11.10), and thrombocytopenia ( OR 3.26, 95% CI 1.66-6.38) compared with irinotecan with cisplatin ( IP). EC was associated with a lower incidence of diarrhea ( OR 0.26, 95% CI 0.10-0.68) compared with IC, and EP was associated with a lower incidence of diarrhea ( OR 0.09, 95% CI 0.03-0.25) and nausea and vomiting ( OR 0.53, 95% CI 0.33-0.84) than IP. Conclusions Hematological toxicities were most common in EC-treated patients, while the lowest incidence occurred with IP treatment. The IP regimen was associated with the highest incidence of toxicities of the digestive tract, while the lowest incidence occurred with EC treatment. [ABSTRACT FROM AUTHOR]

Densities and viscosities of binary mixtures of 8-hydrogen-1,8-diazabicyclo[5,4,0]-undec-7-enium imidazolide ([HDBU]IM) and 8-butyl-1,8-diazabicyclo[5,4,0]-undec-7-enium imidazolide ([BDBU]IM) ionic liquids (ILs) with water were measured at temperatures from T = (293.15 to 313.15) K. Excess molar volumes V E and viscosity deviations Δ η of the mixtures were calculated to study the intermolecular interactions and structural factors between ILs and water. The results show that the V E values of the two mixtures are negative over the whole composition range, while the Δ η values have positive deviations, indicating that the hydrogen bonding interactions between IL and water are dominant in the mixtures. Moreover, the absolute values of V E (| V E |) of {[HDBU]IM (1) + H 2 O (2)} system are larger than those of {[BDBU]IM (1) + H 2 O (2)} system at the same condition, indicating that the hydrogen bonding interactions between [HDBU]IM and water are stronger than those between [BDBU]IM and water. Both | V E | and Δ η values of the mixtures decrease with the increasing temperature, resulting from the decreasing the hydrogen bonding interactions between IL and water. Other derived properties of the studied systems, such as the apparent molar volumes, partial molar volumes, excess partial molar volumes, Gibbs free energy of activation for viscous flow, and excess Gibbs free energy of activation for viscous flow were also calculated from the experimental values. [ABSTRACT FROM AUTHOR]

Densities and viscosities of the pure ionic liquid 1,1,3,3-tetramethylguanidine imidazole ([TMG]IM) and its binary mixtures with methanol, ethanol, 1-propanol, and 1-butanol were measured at temperatures from T = (293.15 to 313.15) K. The thermal expansion coefficient, molecular volume, standard entropy, and lattice energy of [TMG]IM were obtained from the experimental density value. The temperature dependence of the viscosity of [TMG]IM was fitted to the fluidity equation. Excess molar volumes V E and viscosity deviations Δ η of the binary mixtures were calculated and fitted to the Redlich–Kister equation with satisfactory results. The result shows that the V E values of the binary mixtures are negative over the whole composition range, while Δ η values have an S-shape deviation. Temperature has little effect on the V E of the systems, but it has significant effect on the Δ η . Furthermore, the absolute values of V E for {[TMG]IM (1) + alcohol (2)} systems at the same temperature decrease with increasing carbon alkyl chain of the primary alcohol. Other derived properties, such as the apparent molar volumes, partial molar volumes, excess partial molar volumes, Gibbs free energy of activation for viscous flow, and excess Gibbs free energy of activation for viscous flow of the above-mentioned systems were also calculated. [ABSTRACT FROM AUTHOR]

Nonheading Chinese cabbage is an important leafy vegetable, and quantitative identification and automated analysis of nonheading Chinese cabbage leaves are crucial for cultivating new varieties with higher quality, yield, and resistance. Traditional leaf phenotypic analysis relies mainly on phenotypic observation and the practical experience of breeders, leading to issues such as time consumption, labor intensity, and low precision, which result in low breeding efficiency. Considering these issues, a method for the extraction and analysis of phenotypes of nonheading Chinese cabbage leaves is proposed, targeting four qualitative traits and ten quantitative traits from 1500 samples, by integrating deep learning and OpenCV image processing technology. First, a leaf classification model is trained using YOLOv8 to infer the qualitative traits of the leaves, followed by the extraction and calculation of the quantitative traits of the leaves using OpenCV image processing technology. The results indicate that the model achieved an average accuracy of 95.25%, an average precision of 96.09%, an average recall rate of 96.31%, and an average F1 score of 0.9620 for the four qualitative traits. From the ten quantitative traits, the OpenCV-calculated values for the whole leaf length, leaf width, and total leaf area were compared with manually measured values, showing RMSEs of 0.19 cm, 0.1762 cm, and 0.2161 cm2, respectively. Bland–Altman analysis indicated that the error values were all within the 95% confidence intervals, and the average detection time per image was 269 ms. This method achieved good results in the extraction of phenotypic traits from nonheading Chinese cabbage leaves, significantly reducing the personpower and time costs associated with genetic resource analysis. This approach provides a new technique for the analysis of nonheading Chinese cabbage genetic resources that is high-throughput, precise, and automated. [ABSTRACT FROM AUTHOR]

Background: Studies have reported an increase in the prevalence of depression during the COVID-19 pandemic. The accuracy of screening tools may change with the prevalence and distribution of a disease in a population or sample: the "Spectrum Effect". Methods: First, we selected commonly used screening tools and developed search strategies for the inclusion of original studies during the pandemic. Second, we searched PsycINFO, EMBASE, and MEDLINE from March 2020 to September 2022 to obtain original studies that investigated the accuracy of depression screening tools during the pandemic. We then searched these databases to identify meta-analyses summarizing the accuracy of these tools conducted before the pandemic and compared the optimal cut-offs for depression screening tools during the pandemic with those before. Result: Four original studies evaluating the optimal cut-offs for four screening tools (Beck Depression Inventory [BDI-II], Hospital Anxiety and Depression Scale-Depression [HADS-D], Patient Health Questionnaire-9 [PHQ-9], and Geriatric Depression Scale-4 [GDS-4]) were published during the pandemic. Four meta-analyses summarizing these tools before the pandemic. We found that the optimal cut-off of BDI-II was 14 during the pandemic (23.8% depression prevalence, screening patients with Type 2 diabetes) and 14.5 before the pandemic (17.6% depression prevalence, screening psychiatric, primary care, and healthy populations); HADS-D was 10 during the pandemic (23.8% depression prevalence, screening patients with type 2 diabetes) and 7 before the pandemic (15.0% depression prevalence, screening medically ill patients); PHQ-9 was 11 during the pandemic (14.5% depression prevalence, screening university students) and 8 before the pandemic (10.9% depression prevalence, screening the unrestricted population), and GDS-4 was 1.8 during the pandemic (29.0% depression prevalence, screening adults seen in a memory clinic setting) and 3 before the pandemic (18.5% depression prevalence, screening older adults). Conclusion: The optimal cut-off for different screening tools may be sensitive to changes in study populations and reference standards. And potential spectrum effects that should be considered in post-COVID time which aiming to improve diagnostic accuracy. [ABSTRACT FROM AUTHOR]

Background: There are debates in acupuncture related systematic reviews and meta-analyses on whether searching Chinese databases to get more Chinese-language studies may increase the risk of bias and overestimate the effect size, and whether the treatment effects of acupuncture differ between Chinese and non-Chinese populations. Methods: In this meta-epidemiological study, we searched the Cochrane library from its inception until December 2021, and identified systematic reviews and meta-analyses with acupuncture as one of the interventions. Paired reviewers independently screened the reviews and extracted the information. We repeated the meta-analysis of the selected outcomes to separately pool the results of Chinese- and non-Chinese-language acupuncture studies and presented the pooled estimates as odds ratios (OR) with 95% confidence interval (CI). We calculated the Ratio of ORs (ROR) by dividing the OR of the Chinese-language trials by the OR of the non-Chinese-language trials, and the ROR by dividing the OR of trials addressing Chinese population by the OR of trials addressing non-Chinese population. We explored whether the impact of a high risk of bias on the effect size differed between studies published in Chinese- and in non-Chinese-language, and whether the treatment effects of acupuncture differed between Chinese and non-Chinese population. Results: We identified 84 Cochrane acupuncture reviews involving 33 Cochrane groups, of which 31 reviews (37%) searched Chinese databases. Searching versus not searching Chinese databases significantly increased the contribution of Chinese-language literature both to the total number of included trials (54% vs. 15%) and the sample size (40% vs. 15%). When compared with non-Chinese-language trials, Chinese-language trials were associated with a larger effect size (pooled ROR 0.51, 95% CI 0.29 to 0.91). We also observed a higher risk of bias in Chinese-language trials in blinding of participants and personnel (97% vs. 51%) and blinding of outcome assessment (93% vs. 47%). The higher risk of bias was associated with a larger effect estimate in both Chinese-language (allocation concealment: high/unclear risk vs. low risk, ROR 0.43, 95% CI 0.21 to 0.87) and non-Chinese-language studies (blinding of participants and personnel: high/unclear risk vs. low risk, ROR 0.41, 95% CI 0.23 to 0.74). However, we found no evidence that the higher risk of bias would increase the effect size of acupuncture in Chinese-language studies more often than in non-Chinese-language studies (the confidence intervals of all ROR in the high-risk group included 1, Table 3). We further found acupuncture appeared to be more effective in Chinese than in non-Chinese population (Table 4). Conclusions: The findings of this study suggest the higher risk of bias may lead to an overestimation of the treatment effects of acupuncture but would not increase the treatment effects in Chinese-language studies more often than in other language studies. The difference in treatment effects of acupuncture was probably associated with differences in population characteristics. Trial registration: We registered our protocol on the Open Science Framework (OSF) (https://doi.org/10.17605/OSF.IO/PZ6XR). [ABSTRACT FROM AUTHOR]

As solvent-based coatings are gradually phasing out in China, the volatile organic compounds (VOCs) emission characteristics of surface-coating industries have changed rapidly. Sector-based field measurements were conducted to build VOCs emission factors and source profiles of surface-coating industries in Jiangsu Province. A VOCs emission inventory was developed, and the projections for 2020 to 2030 were set. It was found that VOCs content in water-based coatings is 50.8% of solvent-based coatings on average. VOCs emission factors of solvent-based coatings ranged from 0.40 to 0.51 kg kg−1, while those of water-based coatings ranged from 0.14 to 0.24 kg kg−1. Compared to solvent-based coatings, the proportion of aromatics emitted from water-based coatings was 44.2% lower, while the proportion of oxygenated VOCs (OVOCs) was 11.6% higher. The results showed that VOCs emissions were about 134 Gg in Jiangsu Province in 2020, of which the solvent-based coating sources contributed 79.6% of the total. Aromatics were the main species contributing 52.9% of VOCs emissions and 85.9% of ozone formation potential (OFP). According to emission prediction results of four scenarios, the emission reduction of implementing low-content VOCs coating substitution is 8.7% higher than that of adopting the best available end-of-pipe treatment measures by 2030. [ABSTRACT FROM AUTHOR]

Eyelid tumors are tumors that occur in the eye and its appendages, affecting vision and appearance, causing blindness and disability, and some having a high lethality rate. Pathological images of eyelid tumors are characterized by large pixels, multiple scales, and similar features. Solving the problem of difficult and time-consuming fine-grained classification of pathological images is important to improve the efficiency and quality of pathological diagnosis. The morphology of Basal Cell Carcinoma (BCC), Meibomian Gland Carcinoma (MGC), and Cutaneous Melanoma (CM) in eyelid tumors are very similar, and it is easy to be misdiagnosed among each category. In addition, the diseased area, which is decisive for the diagnosis of the disease, usually occupies only a relatively minor portion of the entire pathology section, and screening the area of interest is a tedious and time-consuming task. In this paper, deep learning techniques to investigate the pathological images of eyelid tumors. Inspired by the knowledge distillation process, we propose the Multiscale-Attention-Crop-ResNet (MAC-ResNet) network model to achieve the automatic classification of three malignant tumors and the automatic localization of whole slide imaging (WSI) lesion regions using U-Net. The final accuracy rates of the three classification problems of eyelid tumors on MAC-ResNet were 96.8%, 94.6%, and 90.8%, respectively. [ABSTRACT FROM AUTHOR]

The West Lake is a World Heritage site in the West Lake watershed in eastern China. In this study, the hydrogeological and dual isotopic approaches were integrated to evaluate the seasonal and spatial variations of nitrate (NO 3 − ) in the West Lake watershed, and to characterize NO 3 − sources and transformations. The results revealed that the geochemical facies of the water samples were dominated by Ca 2 + + Na + –HCO 3 − + SO 4 2 − in the surface water and transfer water, Ca 2 + + Na + –HCO 3 − and Ca 2 + + Na + –SO 4 2 − in the groundwater, which most likely reflect natural reactions and anthropogenic inputs. About 13% of the groundwater samples containing NO 3 − exceeded the World Health Organization (WHO) standard of 10 mg N L − 1 . NO 3 − was the dominant form of total nitrogen (TN) and was the main surface water contaminant in the West Lake watershed. The δ 15 N NO 3 and δ 18 O NO 3 values indicated that the dominant NO 3 − sources in surface water were soil nitrogen (soil N) and chemical fertilizers, while the main NO 3 − sources in groundwater were soil N from the forest, chemical fertilizers and manure in the tea garden, domestic sewage from the small, old residential area in the forest as well as urban areas. The distribution of NO 3 − in groundwater was strongly influenced by land use. Results also suggest that there was significant nitrification in surface water and groundwater in the West Lake watershed, and that there were also denitrification processes in groundwater. The annual net fluxes of TN, NO 3 − , and NH 4 + into the West Lake were 2.0 × 10 4 , 4.0 × 10 3 , and 1.31 × 10 4 kg as N, respectively. [ABSTRACT FROM AUTHOR]

Salmonella, as a zoonotic pathogen, has attracted widespread attention worldwide, especially in the transmission between household pets and humans. Therefore, we investigated the epidemic distribution of dog Salmonella from pet hospitals and breeding base in Xuzhou, Jiangsu Province, China, and used multilocus sequence typing (MLST) and clustered regularly interspaced short palindromic repeats (CRISPRs) to subtype Salmonella isolates. From April 2018 to November 2019, a total of 469 samples were collected from pet hospitals and breeding base, including 339 dog samples and 60 cat samples. S. Kentucky (40.74%) was the most prevalent serotype, but other, such as S. Typhimurium (18.52%) and S. Indiana (18.52%), were also widespread. Eight different sequence type (ST) patterns were identified by MLST and ST198 was the highest proportion of these isolates. CRISPRs analysis showed that 9 different Kentucky CRISPR types (KCTs) was identified from ST198. 48 spacers including 29 (6 News) for CRISPR1 and 19 (4 News) for CRISPR2 that proved the polymorphic of Salmonella genes in samples from different sources. The analysis demonstrated that the common serotypes were widely present in pet hosts in the same area. This analysis shows that CRISPR genes have better recognition ability in the same serotype, which has a positive effect on the traceability of Salmonella and the prevention and treatment of salmonellosis. [ABSTRACT FROM AUTHOR]

Accurate measurements of ophthalmic parameters and postoperative appearance prediction are essential for the diagnosis and treatment of many ophthalmic diseases. Nevertheless, it remains challenging due to (1) inconsistent ophthalmic image sampling standards, including ocular-camera distance, facial angle, and patient number, (2) complicated ocular morphology, such as subconjunctival hemorrhage, ocular movements, lighting effects, and morphological aging. It is difficult for a model to measure parameters and make predictions in variable sampling methods and morphology conditions. Therefore, the Global attention-based Ophthalmic Image Measurement and Postoperative Appearance Prediction System (GOMPS) is proposed, which quantifies ophthalmic image parameters to diagnose disease and simultaneously predict postoperative appearance of blepharoptosis. By perceiving the global structure of the ophthalmic image, GOMPS makes logical inference predictions of the sclera and cornea morphology, to overcome the above difficulties. Concretely, a global attention unit (GAU) and a novel global attention structure-aware network (GASA-Net) are designed to enhance GOMPS's global structure awareness ability to perform logical reasoning. Extensive experimental results on our collected ophthalmic dataset for diagnosis & prediction (OD2P) demonstrate that GOMPS surpasses the state-of-the-art methods in segmentation accuracy and achieves the current optimal performance in measurement and postoperative prediction under many clinical scenes. • Showcased GOMPS, the initial ophthalmic measurement & post-op look prediction system. • Presented the largest Ophthalmic Dataset for Diagnosis and Prediction OD2P. • Presented GASA-Net for accurate, robust segmentation in difficult ophthalmic images. • Investigated medial canthi & upper eyelid invariance in blepharoptosis treatment. • Realized in-depth ophthalmic surgery simulation using structural information. [ABSTRACT FROM AUTHOR]

In this work, densities and viscosities of aqueous solution of 1,1,3,3-tetramethylguanidine imidazolide ([TMG]IM) ionic liquid were measured at temperatures from T = (293.15 to 313.15) K. Volumetric properties including excess molar volumes V E , apparent molar volumes, partial molar volumes, and excess partial molar volumes were calculated from the experimental density. Viscosity deviations Δ η , Gibbs energy and excess Gibbs energy of activation for viscous flow were deduced from the viscosity. Moreover, electrical conductivities κ and refractive indices of binary mixtures of [TMG]IM with water and alcohols were determined at 298.15 K. The results show that V E values of {[TMG]IM (1) + water (2)} mixture are negative over the whole composition range, while Δ η and refractive index deviations Δ n D values exhibit positive deviations, indicating that the hydrogen bonding interaction between [TMG]IM and water is dominant. The absolute values of V E and Δ η of the mixture decrease with the increasing temperature. The V E , Δ η , and Δ n D can be fitted by the Redlich–Kister equation with satisfactory results. The concentration-dependent κ of the studied systems are fitted to Casteel–Amis equation, showing that the κ values of {[TMG]IM (1) + water (2)} mixture are much higher than those of {[TMG]IM (1) + ethanol (2)} mixture. [ABSTRACT FROM AUTHOR]

Objectives: Machine learning (ML) has been increasingly used in clinical medicine including studies focused on Clostridioides difficile infection (CDI) to inform to clinical decision making. We aimed to summarize ML choices in studies that used ML to predict CDI or CDI outcomes.Methods: We searched Ovid MEDLINE, Ovid EMBASE, Web of Science, medRxiv, bioRxiv and arXiv from inception to March 18, 2021. We included fully published studies that used ML where CDI constituted the study population, exposure or outcome. Two reviewers independently identified studies and abstracted outcomes. We summarized study characteristics and approaches to CDI definition and ML-specific modelling.Results: Forty-three studies of prediction (n = 21), classification (n = 17) or inference (n = 5) were included. Approaches to defining CDI were labelling during a clinical study or chart review (n = 21), electronic phenotyping (n = 13) or not specified (n = 9). None of the studies using an electronic phenotype described phenotype validation. Almost all studies (n = 41, 95%) conducted supervised ML and the most common ML algorithms were penalized logistic regression (n = 20, 47%) and classification tree (n = 17, 40%). Approaches to feature selection and dimension reduction were heterogeneous. Metrics were evaluated in a held-out test set in 16 (37%) studies; only seven used a time-based split. In terms of reporting quality assessment, the most poorly reported items were data leakage prevention (n = 0, 0%), code availability (n = 8, 19%) and class imbalance management (n = 12, 43%).Conclusions: While many studies have used ML to investigate CDI or CDI outcomes, electronic phenotyping of CDI was uncommon and phenotype validation was not reported in any study. Methodological approaches were heterogeneous. Validating CDI electronic phenotypes, evaluating performances of CDI models during a silent trial and deploying a CDI classifier to guide clinical practice are important future goals. [ABSTRACT FROM AUTHOR]