medRxiv - Health Informatics最新文献

{"title":"A case is not a case is not a case - challenges and solutions in determining urolithiasis caseloads using the digital infrastructure of a clinical data warehouse","authors":"Martin Schoenthaler, Noah Hempen, Maria Weymann, Maximilian Ferry von Bargen, Maximilian Glienke, Antonia Elsaesser, Max Behrens, Harald Binder, Nadine Binder","doi":"10.1101/2024.09.13.24313333","DOIUrl":"https://doi.org/10.1101/2024.09.13.24313333","url":null,"abstract":"Background:\u0000To provide more evidence in urolithiasis research, we have established the German Nationwide Register for RECurrent URolithiasis (RECUR) using local clinical data warehouses (CDWH). For RECUR and other registers relying on digitalized clinical data, it is crucial to ensure the data's reliability for answering scientific questions. In this work, we aim to compare the results of different CDWH-based queries on urolithiasis cases next to manual case extraction from the primary source.\u0000Methods:\u0000Sources for data extraction included the Medical Center University of Freiburg (MCUF) hospital information system (HIS), MCUF performance data (a clinical data set with merged data from patients including data from various time points throughout their treatment), and MCUF reimbursement data. We extracted data on caseloads in urolithiasis algorithmically (performance and reimbursement data) and compared those to a reference group compiled of manually extracted data from the local HIS and algorithmically extracted data.\u0000Results:\u0000Algorithmic extraction based on performance data resulted in correct and complete case identification as compared to the reference group. The case numbers from manual extraction from HIS data and algorithmic extraction from reimbursement data differed by 14% and 12%, respectively. The reasons for deviations in HIS data included human errors and a lack of data availability from different wards. Deviations in reimbursement data arose primarily due to the merging of cases in the context of reimbursement mechanisms. As the CDWH at MCUF is part of the German Medical Informatics Initiative (MII), the results can be transferred to other medical centers with similar CDWH structure.\u0000Conclusions:\u0000The current study provides firm evidence of the importance of clearly defining a studys target variable, e.g., urolithiasis cases, and a thorough understanding of the data sources and modes used to extract the target data. Our work clearly shows that, depending on various data sources, a case is not a case is not a case.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253360","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}

{"title":"Reliable Online Auditory Cognitive Testing: An observational study","authors":"Meher Lad, John-Paul Taylor, Timothy Griffiths","doi":"10.1101/2024.09.17.24313794","DOIUrl":"https://doi.org/10.1101/2024.09.17.24313794","url":null,"abstract":"Technological advances have allowed researchers to conduct research remotely. Online auditory testing has received interest since the Covid-19 pandemic. A number of web-based developments have improved the range of auditory tasks during remote participation. Most of these studies have been conducted in young, motivated individuals who are comfortable with technology. Such studies have also used stimuli testing auditory perceptual abilities. Research on auditory cognitive abilities in real-world older adults is lacking. In this study, we assess the reproducibility of a range of auditory cognitive abilities in older adults, with a range of hearing abilities, who took part in in-person and online experiments.\u0000Participants performed a questionnaire-based assessment and were asked to complete two verbal speech-in-noise perception tasks, for digits and sentences, and two auditory memory tasks, for different sound features. In the first part of the study, 58 Participants performed these tests in-person and online in order to test the reproducibility of the tasks. In the second part, 147 participants conducted all the tasks online in order to test if previously published findings from in-person research were reproducible. We found that older adults under the age of 70 and those with a better hearing were more likely to take part in online testing. The questionnaire-based test had significantly better reproducibility than the behavioural auditory tests but there were no differences in reproducibility between in-person and online auditory cognitive metrics. Relationships between relationships with age and hearing thresholds in an in-person or online setting were not significantly different. Furthermore, important relationships between auditory metrics, evidenced in literature previously, were reproducible online. This study suggests that auditory cognitive testing may be reliably conducted online.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253400","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}

{"title":"Characterizing the connection between Parkinson's disease progression and healthcare utilization","authors":"Lane Fitzsimmons, Francesca Frau, Sylvie Bozzi, Karen Chandross, Brett Beaulieu-Jones","doi":"10.1101/2024.09.15.24313708","DOIUrl":"https://doi.org/10.1101/2024.09.15.24313708","url":null,"abstract":"Background and Objectives: Parkinson's disease (PD) progression can be characterized in terms of healthcare utilization by analyzing clinical events across different stages of disease. Methods: PD progression was measured by the Hoehn & Yahr (H&Y) clinical rating scale and clinical events at each stage were evaluated. Natural language processing and a large language model were used to extract H&Y values from real-world data enabling a larger cohort than manually collected studies, and multi-state hidden Markov models were used for H&Y progression likelihood.\u0000Results: Within the one year, most patients in H&Y stages 2-5 remained in the same stage. Stage transitions, when they occurred, were most frequently to the next higher stage. Higher H&Y stages were associated with discharges into long term care and higher rates of additional clinical events.\u0000Conclusions: Stratifying key clinical events by H&Y score demonstrates the increases of health care utilization and economic burden with PD severity. Modelling the progression likelihood establishes a progression timeline and emphasizes the unmet need to identify treatment options that stop or slow these transitions.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253399","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}

{"title":"Federated Multiple Imputation for Variables that Are Missing Not At Random in Distributed Electronic Health Records","authors":"Yi Lian, Xiaoqian Jiang, Qi Long","doi":"10.1101/2024.09.15.24313479","DOIUrl":"https://doi.org/10.1101/2024.09.15.24313479","url":null,"abstract":"Large electronic health records (EHR) have been widely implemented and are available for research activities. The magnitude of such databases often requires storage and computing infrastructure that are distributed at different sites. Restrictions on data-sharing due to privacy concerns have been another driving force behind the development of a large class of distributed and/or federated machine learning methods. While missing data problem is also present in distributed EHRs, albeit potentially more complex, distributed multiple imputation (MI) methods have not received as much attention. An important advantage of distributed MI, as well as distributed analysis, is that it allows researchers to borrow information across data sites, mitigating potential fairness issues for minority groups that do not have enough volume at certain sites. In this paper, we propose a communication-efficient and privacy-preserving distributed MI algorithms for variables that are missing not at random.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253398","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}

{"title":"Generative AI and Large Language Models in Reducing Medication Related Harm and Adverse Drug Events - A Scoping Review","authors":"Jasmine Chiat Ling Ong, Michael Chen, Ning Ng, Kabilan Elangovan, Nichole Yue Ting Tan, Liyuan Jin, Qihuang Xie, Daniel Shu Wei Ting, Rosa Rodriguez-Monguio, David Bates, Nan Liu","doi":"10.1101/2024.09.13.24313606","DOIUrl":"https://doi.org/10.1101/2024.09.13.24313606","url":null,"abstract":"Background: Medication-related harm has a significant impact on global healthcare costs and patient outcomes, accounting for deaths in 4.3 per 1000 patients. Generative artificial intelligence (GenAI) has emerged as a promising tool in mitigating risks of medication-related harm. In particular, large language models (LLMs) and well-developed generative adversarial networks (GANs) showing promise for healthcare related tasks. This review aims to explore the scope and effectiveness of generative AI in reducing medication-related harm, identifying existing development and challenges in research. Methods: We searched for peer reviewed articles in PubMed, Web of Science, Embase, and Scopus for literature published from January 2012 to February 2024. We included studies focusing on the development or application of generative AI in mitigating risk for medication-related harm during the entire medication use process. We excluded studies using traditional AI methods only, those unrelated to healthcare settings, or concerning non-prescribed medication uses such as supplements. Extracted variables included study characteristics, AI model specifics and performance, application settings, and any patient outcome evaluated. Findings: A total of 2203 articles were identified, and 14 met the criteria for inclusion into final review. We found that generative AI and large language models were used in a few key applications: drug-drug interaction identification and prediction; clinical decision support and pharmacovigilance. While the performance and utility of these models varied, they generally showed promise in areas like early identification and classification of adverse drug events and support in decision-making for medication management. However, no studies tested these models prospectively, suggesting a need for further investigation into the integration and real-world application of generative AI tools to improve patient safety and healthcare outcomes effectively. Interpretation: Generative AI shows promise in mitigating medication-related harms, but there are gaps in research rigor and ethical considerations. Future research should focus on creation of high-quality, task-specific benchmarking datasets for medication safety and real-world implementation outcomes.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253401","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}

{"title":"Accuracy of Online Symptom-Assessment Applications, Large Language Models, and Laypeople for Self-Triage Decisions: A Systematic Review","authors":"Marvin Kopka, Niklas von Kalckreuth, Markus A. Feufel","doi":"10.1101/2024.09.13.24313657","DOIUrl":"https://doi.org/10.1101/2024.09.13.24313657","url":null,"abstract":"Symptom-Assessment Application (SAAs, e.g., NHS 111 online) that assist medical laypeople in deciding if and where to seek care (self-triage) are gaining popularity and their accuracy has been examined in numerous studies. With the public release of Large Language Models (LLMs, e.g., ChatGPT), their use in such decision-making processes is growing as well. However, there is currently no comprehensive evidence synthesis for LLMs, and no review has contextualized the accuracy of SAAs and LLMs relative to the accuracy of their users. Thus, this systematic review evaluates the self-triage accuracy of both SAAs and LLMs and compares them to the accuracy of medical laypeople. A total of 1549 studies were screened, with 19 included in the final analysis. The self-triage accuracy of SAAs was found to be moderate but highly variable (11.5 - 90.0%), while the accuracy of LLMs (57.8 - 76.0%) and laypeople (47.3 - 62.4%) was moderate with low variability. Despite some published recommendations to standardize evaluation methodologies, there remains considerable heterogeneity among studies. The use of SAAs should not be universally recommended or discouraged; rather, their utility should be assessed based on the specific use case and tool under consideration.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253403","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}

{"title":"The Breast Cancer Genetic Testing Experience: Probing the Potential Utility of an Online Decision Aid in Risk Perception and Decision Making","authors":"Anna Vaynrub, Brian Salazar, Yilin Eileen Feng, Harry West, Alissa Michel, Subiksha Umakanth, Katherine Crew, Rita Kukafka","doi":"10.1101/2024.09.13.24313647","DOIUrl":"https://doi.org/10.1101/2024.09.13.24313647","url":null,"abstract":"ABSTRACT (350/350 words) Background: Despite the role of pathogenic variants (PVs) in cancer predisposition genes conferring significantly increased risk of breast cancer (BC), uptake of genetic testing (GT) remains low, especially among ethnic minorities. Our prior study identified that a patient decision aid, RealRisks, improved patient-reported outcomes relative to standard educational materials. This study examined patients GT experience and its influence on subsequent actions. We also sought to identify areas for improvement in RealRisks that would expand its focus from improved GT decision-making to understanding results.\u0000Methods: Women enrolled in the parent randomized controlled trial were recruited and interviewed. Demographic data was collected from surveys in the parent study. Interviews were conducted, transcribed, and coded to identify recurring themes. Descriptive statistics were generated to compare the interviewed subgroup to the original study cohort of 187 women. Results: Of the 22 women interviewed, 11 (50%) had positive GT results, 2 (9.1%) with a BRCA1/2 PV, and 9 (40.9%) with variants of uncertain significance (VUS). Median age was 40.5 years and 15 (71.4%) identified as non-Hispanic. Twenty (90.9%) reported a family history of BC, and 2 (9.1%) reported a family history of BRCA1/2 PV. The emerging themes included a preference for structured communication of GT results and the need for more actionable knowledge to mitigate BC risk, especially among patients with VUS or negative results. Few patients reported lifestyle changes following the return of their results, although they did understand that their behaviors can impact their BC risk. Conclusions: Patients preferred a structured explanation of their GT results to facilitate a more personal testing experience. While most did not change lifestyle behaviors in response to their GT results, there was a consistent call for further guidance following the initial discussion of GT results. Empowering patients, especially those with negative or VUS results, with the knowledge and context to internalize the implications of their results and form accurate risk perception represents a powerful opportunity to mediate subsequent risk management strategies. Informed by this study, future work will expand RealRisks to foster an accurate perception of GT results and include decision support to navigate concrete next steps.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253402","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}

{"title":"Forecasting local surges in COVID-19 hospitalizations through adaptive decision tree classifiers","authors":"Rachel E Murray-Watson, Alyssa Bilinski, Reza Yaesoubi","doi":"10.1101/2024.09.12.24313570","DOIUrl":"https://doi.org/10.1101/2024.09.12.24313570","url":null,"abstract":"During the COVID-19 pandemic, many communities across the US experienced surges in hospitalizations, which strained the local hospital capacity and affected the overall quality of care. Even when effective vaccines became available, many communities remained at high risk of surges in COVID-19-related hospitalizations due to waning immunity, low uptake of booster vaccinations, and the continual emergence of new variations of SARS-CoV-2. Some risk metrics, such as the CDC's Community Levels, were developed to predict the impact of COVID-19 on the community-level healthcare system based on routine surveillance data. However, they had limited utility as they were not routinely updated based on accumulating data and were not directly linked to specific outcomes, such as surges in COVID-19 hospitalizations beyond local capacities. Regression models could resolve these limitations, but they have limited interpretability and do not convey the reasoning behind their predictions. In this paper, we evaluated decision tree classifiers that were developed in \"real-time\" to predict surges in local hospitalizations due to COVID-19 between July 2020 and November 2022. These classifiers would have provided visually intuitive and interpretable decision rules for local decision-makers to understand and act upon, and by being updated weekly, would have responded to changes in the epidemic. We showed that these classifiers exhibit reasonable predictive ability with the area under the receiver operating characteristic curve (auROC) >80%. These classifiers maintained their performance temporally (i.e, over the duration of the pandemic) and spatially (i.e., across US counties). We also showed that these classifiers outperformed the CDC's Community Levels for predicting high hospital occupancy.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253408","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}

{"title":"Gut-Brain Nexus: Mapping Multi-Modal Links to Neurodegeneration at Biobank Scale","authors":"Mohammad Shafieinouri, Samantha Hong, Artur Schuh, Mary B. Makarious, Rodrigo Sandon, Paul Suhwan Lee, Emily Simmonds, Hirotaka Iwaki, Gracelyn Hill, Cornelis Blauwendraat, Valentina Escott-Price, Yue A. Qi, Alastair J. Noyce, Armando Reyes-Palomares, Hampton Leonard, Malu Tansey, Andrew Singleton, Mike A. Nalls, Kristin S. Levine, Sara Bandres-Ciga","doi":"10.1101/2024.09.12.24313490","DOIUrl":"https://doi.org/10.1101/2024.09.12.24313490","url":null,"abstract":"Alzheimer's disease (AD) and Parkinson's disease (PD) are influenced by genetic and environmental factors. Using data from UK Biobank, SAIL Biobank, and FinnGen, we conducted an unbiased, population-scale study to: 1) Investigate how 155 endocrine, nutritional, metabolic, and digestive system disorders are associated with AD and PD risk prior to their diagnosis, considering known genetic influences; 2) Assess plasma biomarkers' specificity for AD or PD in individuals with these conditions; 3) Develop a multi-classification model integrating genetics, proteomics, and clinical data relevant to conditions affecting the gut-brain axis. Our findings show that certain disorders elevate AD and PD risk before AD and PD diagnosis including: insulin and non-insulin dependent diabetes mellitus, noninfective gastro-enteritis and colitis, functional intestinal disorders, and bacterial intestinal infections, among others. Polygenic risk scores revealed lower genetic predisposition to AD and PD in individuals with co-occurring disorders in the study categories, underscoring the importance of regulating the gut-brain axis to potentially prevent or delay the onset of neurodegenerative diseases. The proteomic profile of AD/PD cases was influenced by comorbid endocrine, nutritional, metabolic, and digestive systems conditions. Importantly, we developed multi-omics prediction models integrating clinical, genetic, proteomic and demographic data, the combination of which performs better than any single paradigm approach in disease classification. This work aims to illuminate the intricate interplay between various physiological factors involved in the gut-brain axis and the development of AD and PD, providing a multifactorial systemic understanding that goes beyond traditional approaches.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253404","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}

{"title":"Technology-Supported Self-Triage Decision Making: A Mixed-Methods Study","authors":"Marvin Kopka, Sonja Mei Wang, Samira Kunz, Christine Schmid, Markus A. Feufel","doi":"10.1101/2024.09.12.24313558","DOIUrl":"https://doi.org/10.1101/2024.09.12.24313558","url":null,"abstract":"Symptom-Assessment Application (SAAs) and Large Language Models (LLMs) are increasingly used by laypeople to navigate care options. Although humans ultimately make a final decision when using these systems, previous research has typically examined the performance of humans and SAAs/LLMs separately. Thus, it is unclear how decision-making unfolds in such hybrid human-technology teams and if SAAs/LLMs can improve laypeople's decisions. To address this gap, we conducted a convergent parallel mixed-methods study with semi-structured interviews and a randomized controlled trial. Our interview data revealed that in human-technology teams, decision-making is influenced by factors before, during, and after interaction. Users tend to rely on technology for information gathering and analysis but remain responsible for information integration and the final decision. Based on these results, we developed a model for technology-assisted self-triage decision-making. Our quantitative results indicate that when using a high-performing SAA, laypeople's decision accuracy improved from 53.2% to 64.5% (OR = 2.52, p < .001). In contrast, decision accuracy remained unchanged when using a LLM (54.8% before vs. 54.2% after usage, p = .79). These findings highlight the importance of studying SAAs/LLMs with humans in the loop, as opposed to analyzing them in isolation.","PeriodicalId":501454,"journal":{"name":"medRxiv - Health Informatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253405","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}