UNASSIGNED: The application of machine learning in health care often necessitates the use of hierarchical codes such as the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) systems. These codes classify diseases and medications, respectively, thereby forming extensive data dimensions. Unsupervised feature selection tackles the \"curse of dimensionality\" and helps to improve the accuracy and performance of supervised learning models by reducing the number of irrelevant or redundant features and avoiding overfitting. Techniques for unsupervised feature selection, such as filter, wrapper, and embedded methods, are implemented to select the most important features with the most intrinsic information. However, they face challenges due to the sheer volume of ICD and ATC codes and the hierarchical structures of these systems.
UNASSIGNED: The objective of this study was to compare several unsupervised feature selection methods for ICD and ATC code databases of patients with coronary artery disease in different aspects of performance and complexity and select the best set of features representing these patients.
UNASSIGNED: We compared several unsupervised feature selection methods for 2 ICD and 1 ATC code databases of 51,506 patients with coronary artery disease in Alberta, Canada. Specifically, we used the Laplacian score, unsupervised feature selection for multicluster data, autoencoder-inspired unsupervised feature selection, principal feature analysis, and concrete autoencoders with and without ICD or ATC tree weight adjustment to select the 100 best features from over 9000 ICD and 2000 ATC codes. We assessed the selected features based on their ability to reconstruct the initial feature space and predict 90-day mortality following discharge. We also compared the complexity of the selected features by mean code level in the ICD or ATC tree and the interpretability of the features in the mortality prediction task using Shapley analysis.
UNASSIGNED: In feature space reconstruction and mortality prediction, the concrete autoencoder-based methods outperformed other techniques. Particularly, a weight-adjusted concrete autoencoder variant demonstrated improved reconstruction accuracy and significant predictive performance enhancement, confirmed by DeLong and McNemar tests (P<.05). Concrete autoencoders preferred more general codes, and they consistently reconstructed all features accurately. Additionally, features selected by weight-adjusted concrete autoencoders yielded higher Shapley values in mortality prediction than most alternatives.
UNASSIGNED: This study scrutinized 5 feature selection methods in ICD and ATC code data sets in an unsupervised context. Our findings underscore the superiority of the concrete autoencoder method in selecting salient features that represent the entire data set, offering a potential asset for subsequent machine learning research. We also present a novel weight adjustment approach for the concrete autoencoders specifically tailored for ICD and ATC code data sets to enhance the generalizability and interpretability of the selected features.

BACKGROUND: The COVID-19 pandemic has sharpened the focus on health care safety and quality, underscoring the importance of using standardized metrics such as the International Classification of Diseases, Tenth Revision (ICD-10). In this regard, the ICD-10 cluster Y62-Y69 serves as a proxy assessment of safety and quality in health care systems, allowing researchers to evaluate medical misadventures. Thus far, extensive research and reports support the need for more attention to safety and quality in health care. The study aims to leverage the pandemic\'s unique challenges to explore health care safety and quality trends during prepandemic, intrapandemic, and postpandemic phases, using the ICD-10 cluster Y62-Y69 as a key tool for their evaluation.
OBJECTIVE: This research aims to perform a comprehensive retrospective analysis of incidence rates associated with ICD-10 cluster Y62-Y69, capturing both linear and nonlinear trends across prepandemic, intrapandemic, and postpandemic phases over an 8-year span. Therefore, it seeks to understand how these trends inform health care safety and quality improvements, policy, and future research.
METHODS: This study uses the extensive data available through the TriNetX platform, using an observational, retrospective design and applying curve-fitting analyses and quadratic models to comprehend the relationships between incidence rates over an 8-year span (from 2015 to 2023). These techniques will enable the identification of nuanced trends in the data, facilitating a deeper understanding of the impacts of the COVID-19 pandemic on medical misadventures. The anticipated results aim to outline complex patterns in health care safety and quality during the COVID-19 pandemic, using global real-world data for robust and generalizable conclusions. This study will explore significant shifts in health care practices and outcomes, with a special focus on geographical variations and key clinical conditions in cardiovascular and oncological care, ensuring a comprehensive analysis of the pandemic\'s impact across different regions and medical fields.
RESULTS: This study is currently in the data collection phase, with funding secured in November 2023 through the Ricerca Corrente scheme of the Italian Ministry of Health. Data collection via the TriNetX platform is anticipated to be completed in May 2024, covering an 8-year period from January 2015 to December 2023. This dataset spans pre-pandemic, intra-pandemic, and early post-pandemic phases, enabling a comprehensive analysis of trends in medical misadventures using the ICD-10 cluster Y62-Y69. The final analytics are anticipated to be completed by June 2024. The study\'s findings aim to provide actionable insights for enhancing healthcare safety and quality, reflecting on the pandemic\'s transformative impact on global healthcare systems.
CONCLUSIONS: This study is anticipated to contribute significantly to health care safety and quality literature. It will provide actionable insights for health care professionals, policy makers, and researchers. It will highlight critical areas for intervention and funding to enhance health care safety and quality globally by examining the incidence rates of medical misadventures before, during, and after the pandemic. In addition, the use of global real-world data enhances the study\'s strength by providing a practical view of health care safety and quality, paving the way for initiatives that are informed by data and tailored to specific contexts worldwide. This approach ensures the findings are applicable and actionable across different health care settings, contributing significantly to the global understanding and improvement of health care safety and quality.
UNASSIGNED: PRR1-10.2196/54838.

BACKGROUND: Computer-assisted clinical coding (CAC) tools are designed to help clinical coders assign standardized codes, such as the ICD-10 (International Statistical Classification of Diseases, Tenth Revision), to clinical texts, such as discharge summaries. Maintaining the integrity of these standardized codes is important both for the functioning of health systems and for ensuring data used for secondary purposes are of high quality. Clinical coding is an error-prone cumbersome task, and the complexity of modern classification systems such as the ICD-11 (International Classification of Diseases, Eleventh Revision) presents significant barriers to implementation. To date, there have only been a few user studies; therefore, our understanding is still limited regarding the role CAC systems can play in reducing the burden of coding and improving the overall quality of coding.
OBJECTIVE: The objective of the user study is to generate both qualitative and quantitative data for measuring the usefulness of a CAC system, Easy-ICD, that was developed for recommending ICD-10 codes. Specifically, our goal is to assess whether our tool can reduce the burden on clinical coders and also improve coding quality.
METHODS: The user study is based on a crossover randomized controlled trial study design, where we measure the performance of clinical coders when they use our CAC tool versus when they do not. Performance is measured by the time it takes them to assign codes to both simple and complex clinical texts as well as the coding quality, that is, the accuracy of code assignment.
RESULTS: We expect the study to provide us with a measurement of the effectiveness of the CAC system compared to manual coding processes, both in terms of time use and coding quality. Positive outcomes from this study will imply that CAC tools hold the potential to reduce the burden on health care staff and will have major implications for the adoption of artificial intelligence-based CAC innovations to improve coding practice. Expected results to be published summer 2024.
CONCLUSIONS: The planned user study promises a greater understanding of the impact CAC systems might have on clinical coding in real-life settings, especially with regard to coding time and quality. Further, the study may add new insights on how to meaningfully exploit current clinical text mining capabilities, with a view to reducing the burden on clinical coders, thus lowering the barriers and paving a more sustainable path to the adoption of modern coding systems, such as the new ICD-11.
BACKGROUND: clinicaltrials.gov NCT06286865; https://clinicaltrials.gov/study/NCT06286865.
UNASSIGNED: DERR1-10.2196/54593.

BACKGROUND: The International Classification of Diseases, Eleventh Revision (ICD-11) improved neoplasm classification.
OBJECTIVE: We aimed to study the alterations in the ICD-11 compared to the Chinese Clinical Modification of the International Classification of Diseases, Tenth Revision (ICD-10-CCM) for neoplasm classification and to provide evidence supporting the transition to the ICD-11.
METHODS: We downloaded public data files from the World Health Organization and the National Health Commission of the People\'s Republic of China. The ICD-10-CCM neoplasm codes were manually recoded with the ICD-11 coding tool, and an ICD-10-CCM/ICD-11 mapping table was generated. The existing files and the ICD-10-CCM/ICD-11 mapping table were used to compare the coding, classification, and expression features of neoplasms between the ICD-10-CCM and ICD-11.
RESULTS: The ICD-11 coding structure for neoplasms has dramatically changed. It provides advantages in coding granularity, coding capacity, and expression flexibility. In total, 27.4% (207/755) of ICD-10 codes and 38% (1359/3576) of ICD-10-CCM codes underwent grouping changes, which was a significantly different change (χ21=30.3; P<.001). Notably, 67.8% (2424/3576) of ICD-10-CCM codes could be fully represented by ICD-11 codes. Another 7% (252/3576) could be fully described by uniform resource identifiers. The ICD-11 had a significant difference in expression ability among the 4 ICD-10-CCM groups (χ23=93.7; P<.001), as well as a considerable difference between the changed and unchanged groups (χ21=74.7; P<.001). Expression ability negatively correlated with grouping changes (r=-.144; P<.001). In the ICD-10-CCM/ICD-11 mapping table, 60.5% (2164/3576) of codes were postcoordinated. The top 3 postcoordinated results were specific anatomy (1907/3576, 53.3%), histopathology (201/3576, 5.6%), and alternative severity 2 (70/3576, 2%). The expression ability of postcoordination was not fully reflected.
CONCLUSIONS: The ICD-11 includes many improvements in neoplasm classification, especially the new coding system, improved expression ability, and good semantic interoperability. The transition to the ICD-11 will inevitably bring challenges for clinicians, coders, policy makers and IT technicians, and many preparations will be necessary.

Although autopsy diagnosis includes routinely, a thorough evaluation of all available pathological results and also of any available clinical data, the contribution of this clinical information to the diagnostic yield of the autopsy has not been analyzed. We aimed to determine to which degree the use of clinical data improves the diagnostic accuracy of the complete diagnostic autopsy (CDA) and the minimally invasive autopsy (MIA), a simplified pathological postmortem procedure designed for low-income sites. A total of 264 coupled MIA and CDA procedures (112 adults, 57 maternal deaths, 54 children, and 41 neonates) were performed at the Maputo Hospital, Mozambique. We compared the diagnoses obtained by the MIA blind to clinical data (MIAb), the MIA adding the clinical information (MIAc), and the CDA blind to clinical information (CDAb), with the results of the gold standard, the CDA with clinical data, by comparing the International Classification of Diseases, Tenth Revision codes and the main diagnostic classes obtained with each evaluation strategy (MIAb, MIAc, CDAb, CDAc). The clinical data increased diagnostic coincidence to the MIAb with the gold standard in 30 (11%) of 264 cases and modified the CDAb diagnosis in 20 (8%) of 264 cases. The increase in concordance between MIAb and MIAc with the gold standard was significant in neonatal deaths (κ increasing from 0.404 to 0.618, P = .0271), adult deaths (κ increasing from 0.732 to 0.813, P = .0221), and maternal deaths (κ increasing from 0.485 to 0.836, 0.;P < .0001). In conclusion, the use of clinical information increases the precision of MIA and CDA and may strengthen the performance of the MIA in resource-limited settings.