medRxivPub Date : 2024-07-30DOI: 10.1101/2024.07.29.24311172
Marlene Franz, Valeria Kebets, Xaver Berg, F. Georgiadis, A. Burrer, Janis Brakowski, Stefan Kaiser, Erich Seifritz, Philipp Homan, Esther Walton, T. Erp, Jessica A. Turner, B. Misic, Sofie Valk, B. T. T. Yeo, Boris C. Bernhardt, Matthias Kirschner
{"title":"Orbitofrontal thickness and network associations as transdiagnostic signature of negative symptoms along the bipolar-schizophrenia spectrum","authors":"Marlene Franz, Valeria Kebets, Xaver Berg, F. Georgiadis, A. Burrer, Janis Brakowski, Stefan Kaiser, Erich Seifritz, Philipp Homan, Esther Walton, T. Erp, Jessica A. Turner, B. Misic, Sofie Valk, B. T. T. Yeo, Boris C. Bernhardt, Matthias Kirschner","doi":"10.1101/2024.07.29.24311172","DOIUrl":"https://doi.org/10.1101/2024.07.29.24311172","url":null,"abstract":"Negative symptoms are core features of schizophrenia (SCZ) and also prevalent in bipolar disorder (BD). While orbitofrontal cortex (OFC) alterations have been implicated in the development of negative symptoms, their contributions across disorders remain to be established. Here, we tested how OFC thickness and related network associations relate to severity of negative symptom dimensions across the BD-SCZ spectrum. We included 50 individuals with SCZ, 49 with BD, alongside 122 controls. We assessed amotivation and diminished expression and estimated thickness in the medial and lateral OFC as regions-of-interest as well as 64 other cortical regions. Across BD and SCZ, reduced right lateral and bilateral medial OFC thickness were specifically associated with amotivation, but not diminished expression or other clinical factors. We then generated OFC structural co-variation networks to evaluate how the system-level embedding of the OFC would link to brain-wide cortical maps of negative symptoms. We found that medial OFC co-variation networks spatially correlated with the cortical maps of both negative symptom dimensions. Confirmatory analyses in independent SCZ data from the ENIGMA consortium (n=4,474) revealed similar associations with lateral OFC co-variation networks. Finally, the brain-wide cortical alteration pattern of amotivation was significantly correlated with normative functional and structural white-matter connectivity profiles of the right medial and left lateral OFC as well as adjacent prefrontal and limbic regions. Our work identifies OFC alterations as a possible transdiagnostic signature of amotivation and provide insights into network associations underlying the system-wide cortical alterations of negative symptoms across SCZ and BD. Key words: Negative symptoms, Amotivation, Diminished expression, Orbitofrontal cortex, MRI, Structural covariance, Schizophrenia, Bipolar disorder","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"3 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.29.24311030
B. Tobin, A. Misko, V. Miller-Browne, M. Sangster, Y. Grishchuk, L. B. Wood
{"title":"Plasma Proteomic Signature of Mucolipidosis Type IV","authors":"B. Tobin, A. Misko, V. Miller-Browne, M. Sangster, Y. Grishchuk, L. B. Wood","doi":"10.1101/2024.07.29.24311030","DOIUrl":"https://doi.org/10.1101/2024.07.29.24311030","url":null,"abstract":"Mucolipidosis IV (MLIV) is an autosomal-recessive pediatric disease that leads to motor and cognitive deficits and loss of vision. It is caused by the loss of function of the lysosomal channel transient receptor potential mucolipin-1, TRPML1, and is associated with an early brain phenotype consisting of glial reactivity, hypomyelination, lysosomal abnormalities, and increased cytokine expression. Although the field is approaching the first translationally relevant therapy, we currently lack a molecular signature of disease that can be used to detect therapeutic efficacy. In the current study, we analyzed 7,322 proteins in the plasma proteome and compare protein profiles with clinical measures of disease severity (motor function, muscle tone, and age). To do so, we used aptamer-based protein profiling on plasma isolated from 18 MLIV patients and 37 aged-matched controls from a biorepository. We identified a total of 1,961 differentially expressed proteins between MLIV and control subjects, with functions spanning many major hallmarks of MLIV. Our analysis revealed a decrease in the abundance of neuronal proteins and an increase in muscle proteins, consistent with the neuronal dysfunction and muscle pathology observed in patients. In particular, lower levels of synaptic proteins (e.g., GABARAP) best correlated with disease severity. Next, we compared the plasma proteome of patients to the brain proteome from the mouse model of MLIV and identified shared alterations in 45 proteins. The up-regulated overlapping proteins were largely related to lysosomal function (e.g., ACTN2, GLB1), while the down-regulated proteins were largely related to myelination (e.g. TPPP3, CNTN2). Both signatures are consistent with our understanding of key disease hallmarks: impaired myelination and modified lysosomal function. Collectively, these data indicate that peripheral blood plasma protein signatures mirror changes found in the MLIV brain and suggest candidate markers relevant to MLIV pathology to be validated in future studies.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"13 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.26.24311057
M. Schipper, J. C. Ulirsch, D. Posthuma, S. Ripke, K. Heilbron
{"title":"Simplifying causal gene identification in GWAS loci","authors":"M. Schipper, J. C. Ulirsch, D. Posthuma, S. Ripke, K. Heilbron","doi":"10.1101/2024.07.26.24311057","DOIUrl":"https://doi.org/10.1101/2024.07.26.24311057","url":null,"abstract":"Genome-wide association studies (GWAS) help to identify disease-linked genetic variants, but pinpointing the most likely causal genes in GWAS loci remains challenging. Existing GWAS gene prioritization tools are powerful, but often use complex black box models trained on datasets containing unaddressed biases. Here we present CALDERA, a gene prioritization tool that achieves similar or better performance than state-of-the-art methods, but uses just 12 features and a simple logistic regression model with L1 regularization. We use a data-driven approach to construct a truth set of causal genes in 406 GWAS loci and correct for potential confounders. We demonstrate that CALDERA is well-calibrated in external datasets and prioritizes genes with expected properties, such as being mutation-intolerant (OR = 1.751 for pLI > 90%, P = 8.45x10-3). CALDERA facilitates the prioritization of potentially causal genes in GWAS loci and may help identify novel genetics-driven drug targets.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"18 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.28.24311130
F. Wang
{"title":"Comprehensive Analysis of Atypical chronic myeloid leukemia (aCML): Epidemiology, Clinical Features, and Survival Outcomes Based on SEER Database Insights","authors":"F. Wang","doi":"10.1101/2024.07.28.24311130","DOIUrl":"https://doi.org/10.1101/2024.07.28.24311130","url":null,"abstract":"Background: Atypical Chronic Myeloid Leukemia (aCML) is a rare and aggressive myelodysplastic syndrome/myeloproliferative neoplasm. This study aimed to provide a comprehensive understanding of the epidemiology, clinical characteristics, and survival outcomes of aCML patients. Methods: The study utilized data from the Surveillance, Epidemiology, and End Results (SEER) database from 2001 to 2020. The age-adjusted incidence rate (AIR) of aCML was calculated, and survival outcomes were analyzed using the Kaplan-Meier method and accelerated failure time (AFT) regression analysis. Results: The AIR of aCML was found to be 0.024 per 100,000 person-years, with the highest rate observed in 2020. The incidence of aCML increased with age and was higher in males. The study cohort predominantly consisted of elderly White individuals, with an average age at diagnosis of 68.2 years. The median overall survival (OS) and disease-specific survival (DSS) were 1.4 years and 1.7 years, respectively. Older age was independently associated with worse survival outcomes. Notably, treatment delay and chemotherapy did not significantly impact OS or DSS. Conclusions: This study provides comprehensive insights into the epidemiology, clinical characteristics, and survival outcomes of aCML, highlighting its rarity, aggressive nature, and poor prognosis. Further research is needed to validate these findings and explore novel therapeutic strategies for improving outcomes in this challenging hematologic malignancy.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"1 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.29.24311044
M. S. Bom, A. M. Brak, M. Raemaekers, N. F. Ramsey, M. Vansteensel, M. P. Branco
{"title":"Large-scale fMRI dataset for the design of motor-based Brain-Computer Interfaces","authors":"M. S. Bom, A. M. Brak, M. Raemaekers, N. F. Ramsey, M. Vansteensel, M. P. Branco","doi":"10.1101/2024.07.29.24311044","DOIUrl":"https://doi.org/10.1101/2024.07.29.24311044","url":null,"abstract":"Functional Magnetic Resonance Imaging (fMRI) data is commonly used to localise implantation sites for intracranial-based Brain-Computer Interfaces (BCIs). Functional data recorded during sensory and motor tasks from both adults and children specifically designed to map and localise BCI target areas is rare. Here, we describe a large-scale dataset collected from 155 human subjects during motor and sensory tasks involving the fingers, hands, arms, feet, legs, and mouth region. The dataset includes data from both adults and children (age range: 6-89 years) performing a restricted set of standardized tasks. This dataset is particularly relevant to study developmental patterns in motor representation on the cortical surface and for the design of paediatric motor-based implanted BCIs.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.27.24310746
C. Zhou, I. Doval, R. Liu
{"title":"Revamping the Day Hospital Program at North York General Hospital in response to COVID-related changes in patient demographics","authors":"C. Zhou, I. Doval, R. Liu","doi":"10.1101/2024.07.27.24310746","DOIUrl":"https://doi.org/10.1101/2024.07.27.24310746","url":null,"abstract":"Background The Dynamic Sustainability Framework emphasizes the need for improving programs after implementation in response to the evolving environment. This report illustrates said framework and describes significant changes made to the Psychiatric Day Hospital (DH) at North York General Hospital (NYGH) in response to pandemic-related changes in participant demographic. Patient and staff satisfaction pre- and post- program modification are compared. Problem The COVID-19 pandemic resulted in increased DH referral acuity and patient affect dysregulation. The program needed to adapt to these changes and better serve the new DH patient population. Methods DH participants and team member feedback was gathered. Five major areas of improvement were identified. Changes were systematically introduced from July 2021 to January 2022. Feedback post-implementation in 2022- 2023 from patients and DH team members were gathered for comparison. Interventions Dialectical Behavioral Therapy (DBT) was adopted as the theoretical basis of the revamped Day Hospital Program. All Day Hospital staff underwent training in DBT skills, with the creation of new treatment schedules and materials. Two separate streams were created for differing patient illness severity. The program continued to run during implementation of new changes, without disruption to the existing clinical workload. Results The program transitioned from a 3-week psychoeducational and rudimentary CBT program to a dual-stream 4-week DBT-based program to address patient acuity and higher prevalence of emotional dysregulation. Quantitative and qualitative feedback from new program participants have been positive. Conclusions The Day Hospital Program at NYGH made a successful transition in response to an evolving healthcare landscape. KEY WORDS: Mental Health/Psychiatry, Dynamic Sustainability, Program Improvement, Implementation Science","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"10 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.29.24311184
M. Laichapis, R. Sakulbumrungsil, K. Udomaksorn, N. Kessomboon, O. Nerapusee, C. Hongthong, S. Poonpolsub
{"title":"Financial Feasibility Study and policy recommendations of Incremental Modified Drugs Development by the Domestic Pharmaceutical Industry","authors":"M. Laichapis, R. Sakulbumrungsil, K. Udomaksorn, N. Kessomboon, O. Nerapusee, C. Hongthong, S. Poonpolsub","doi":"10.1101/2024.07.29.24311184","DOIUrl":"https://doi.org/10.1101/2024.07.29.24311184","url":null,"abstract":"The Thai pharmaceutical industry aims to strengthen its drug system in accordance with the National Strategic Master Plan, emphasizing sustainable development, particularly in biologics and herbal products, to achieve self-reliance. Current efforts are mainly focused on generic drug production, but there's a significant need for Research and Development (R&D) in Innovative Medicines (IMDs). This study explores the financial feasibility of locally developing an IMDs dosage form. To assess this feasibility, a mixed-methods approach was used, incorporating a literature review, surveys, and interviews. This process involved selecting types of IMDs, constructing financial models, determining cost structures, and conducting a thorough feasibility analysis. The results indicated that a sustained-release dosage form was the most viable option. The analysis took into account total development costs, payback periods, growth rates, and the revenue required to recoup investments. It was found that IMD development is associated with higher costs and longer durations compared to new generic drugs.The study identified several challenges, such as the high cost of clinical studies, extended development times, market feasibility, and drug selection difficulties. Policy recommendations were made to address these challenges, including incentives for clinical studies and fostering industry expertise through collaborative efforts and supportive government policies.In conclusion, the financial feasibility of developing IMDs requires strategic policies and collaboration to overcome these challenges and ensure sustainability. The findings of this study are intended to aid stakeholders in making informed R&D investment decisions.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"13 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.29.24311157
N. Holt, C. L. Smith, C. X. Gao, B. Borg, T. J. Lane, D. Brown, J. Ikin, A. Makar, T. McCrabb, M. Thomas, K. Nilsen, B. Thompson, M. Abramson
{"title":"Lung function may recover after exposure to smoke from a coal mine fire: cohort study","authors":"N. Holt, C. L. Smith, C. X. Gao, B. Borg, T. J. Lane, D. Brown, J. Ikin, A. Makar, T. McCrabb, M. Thomas, K. Nilsen, B. Thompson, M. Abramson","doi":"10.1101/2024.07.29.24311157","DOIUrl":"https://doi.org/10.1101/2024.07.29.24311157","url":null,"abstract":"Background and objective: The 2014 Hazelwood coalmine fire exposed residents in nearby Morwell to high concentrations of particulate matter <2.5 m (PM2.5) for approximately 6 weeks. This analysis aimed to evaluate the long-term impact on respiratory health. Methods: Adults from Morwell and the unexposed town of Sale completed validated respiratory questionnaires and performed spirometry, gas transfer and oscillometry 3.5-4 years (Round 1) and 7.3-7.8 years (Round 2) after the fire. Individual PM2.5 exposure levels were estimated using chemical transport models mapped onto participant-reported time-location data. Mixed-effects regression models were fitted to analyse associations between PM2.5 exposure and outcomes, controlling for key confounders. Results: From 519 (346 exposed) Round 1 participants, 329 (217 exposed) participated in Round 2. Spirometry and gas transfer in Round 2 were mostly lower compared with Round 1, excepting FVC (increased) and FEV1 (minimal change). The effect of mine fire-related PM2.5 exposure changed from a negative effect in Round 1 to no effect in Round 2 for both pre- (p=0.005) and post-bronchodilator FVC (p=0.032). PM2.5 was not associated with gas transfer in either round. For post-bronchodilator reactance and area under the curve, a negative impact of PM2.5 in Round 1 showed signs of recovery in Round 2 (both p<0.001). Conclusion: In this novel study evaluating long-term respiratory outcomes after medium-duration high concentration PM2.5 exposure, the attenuated associations between exposure and respiratory function may indicate some recovery in lung function. With increased frequency and severity of landscape fires observed globally, these results inform public health policies and planning.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"1 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.29.24311077
D. Wojcik, O. Adamiak, G. Czerepak, O. Tokarczuk, L. Szalewski
{"title":"A comparative analysis of the performance of chatGPT4, Gemini Gemini and Claude Claude for the Polish Medical Final Diploma Exam and Medical-Dental Verification Exam.","authors":"D. Wojcik, O. Adamiak, G. Czerepak, O. Tokarczuk, L. Szalewski","doi":"10.1101/2024.07.29.24311077","DOIUrl":"https://doi.org/10.1101/2024.07.29.24311077","url":null,"abstract":"In the realm of medical education, the utility of chatbots is being explored with growing interest. One pertinent area of investigation is the performance of these models on standardized medical examinations, which are crucial for certifying the knowledge and readiness of healthcare professionals. In Poland, dental and medical students have to pass crucial exams known as LDEK (Medical-Dental Final Examination) and LEK (Medical Final Examination) exams respectively. The primary objective of this study was to conduct a comparative analysis of chatbots: ChatGPT-4, Gemini and Claude to evaluate their accuracy in answering exam questions of the LDEK and the Medical-Dental Verification Examination (LDEW), using queries in both English and Polish. The analysis of Model 2, which compared chatbots within question groups, showed that the chatbot Claude achieved the highest probability of accuracy for all question groups except the area of prosthetic dentistry compared to ChatGPT-4 and Gemini. In addition, the probability of a correct answer to questions in the field of integrated medicine is higher than in the field of dentistry for all chatbots in both prompt languages. Our results demonstrate that Claude achieved the highest accuracy in all areas analysed and outperformed other chatbots. This suggests that Claude has significant potential to support the medical education of dental students. This study showed that the performance of chatbots varied depending on the prompt language and the specific field. This highlights the importance of considering language and specialty when selecting a chatbot for educational purposes.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"12 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
medRxivPub Date : 2024-07-29DOI: 10.1101/2024.07.28.24311154
O. S. Emam, M. Ebadi Jalal, B. Garcia-Zapirain, A. Elmaghraby
{"title":"Artificial Intelligence Algorithms in Nailfold Capillaroscopy Image Analysis: A Systematic Review","authors":"O. S. Emam, M. Ebadi Jalal, B. Garcia-Zapirain, A. Elmaghraby","doi":"10.1101/2024.07.28.24311154","DOIUrl":"https://doi.org/10.1101/2024.07.28.24311154","url":null,"abstract":"Background Non-invasive imaging modalities offer a great deal of clinically significant information that aid in the diagnosis of various medical conditions. Coupled with the never-before-seen capabilities of Artificial Intelligence (AI), uncharted territories that offer novel innovative diagnostics are reached. This systematic review compiled all studies that utilized AI in Nailfold Capillaroscopy as a future diagnostic tool. Methods and Findings Five databases for medical publications were searched using the keywords artificial intelligence, machine learning, deep learning and nailfold capillaroscopy to return 105 studies. After applying the eligibility criteria, 10 studies were selected for the final analysis. Data was extracted into tables that addressed population characteristics, AI model development and nature and results of their respective performance. We found supervised deep learning approaches to be the most commonly used (n = 8). Systemic Sclerosis was the most commonly studied disease (n = 6). Sample size ranged from 17,126 images obtained from 289 participants to 50 images from 50 participants. Ground truth was determined either by experts labelling (n = 6) or known clinical status (n = 4). Significant variation was noticed in model training, testing and feature extraction, and therefore the reporting of model performance. Recall, precision and Area Under the Curve were the most used metrics to report model performance. Execution times ranged from 0.064 to 120 seconds per image. Only two models offered future predictions besides the diagnostic output. Conclusions AI has demonstrated a truly remarkable potential in the interpretation of Nailfold Capillaroscopy by providing physicians with an intelligent decision-supportive tool for improved diagnostics and prediction. With more validation studies, this potential can be translated to daily clinical practice.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":"7 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141796547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}