TY - JOUR AU - Paiva, Bruno AU - Gonçalves, Marcos André AU - da Rocha, Leonardo Chaves Dutra AU - Marcolino, Milena Soriano AU - Lana, Fernanda Cristina Barbosa AU - Souza-Silva, Maira Viana Rego AU - Almeida, Jussara M AU - Pereira, Polianna Delfino AU - de Andrade, Claudio Moisés Valiense AU - Gomes, Angélica Gomides dos Reis AU - Ferreira, Maria Angélica Pires AU - Bartolazzi, Frederico AU - Sacioto, Manuela Furtado AU - Boscato, Ana Paula AU - Guimarães-Júnior, Milton Henriques AU - dos Reis, Priscilla Pereira AU - Costa, Felício Roberto AU - Jorge, Alzira de Oliveira AU - Coelho, Laryssa Reis AU - Carneiro, Marcelo AU - Sales, Thaís Lorenna Souza AU - Araújo, Silvia Ferreira AU - Silveira, Daniel Vitório AU - Ruschel, Karen Brasil AU - Santos, Fernanda Caldeira Veloso AU - Cenci, Evelin Paola de Almeida AU - Menezes, Luanna Silva Monteiro AU - Anschau, Fernando AU - Bicalho, Maria Aparecida Camargos AU - Manenti, Euler Roberto Fernandes AU - Finger, Renan Goulart AU - Ponce, Daniela AU - de Aguiar, Filipe Carrilho AU - Marques, Luiza Margoto AU - de Castro, Luís César AU - Vietta, Giovanna Grünewald AU - Godoy, Mariana Frizzo de AU - Vilaça, Mariana do Nascimento AU - Morais, Vivian Costa PY - 2024 DA - 2024/10/28 TI - A New Natural Language Processing–Inspired Methodology (Detection, Initial Characterization, and Semantic Characterization) to Investigate Temporal Shifts (Drifts) in Health Care Data: Quantitative Study JO - JMIR Med Inform SP - e54246 VL - 12 KW - health care KW - machine learning KW - data drifts KW - temporal drifts AB - Background: Proper analysis and interpretation of health care data can significantly improve patient outcomes by enhancing services and revealing the impacts of new technologies and treatments. Understanding the substantial impact of temporal shifts in these data is crucial. For example, COVID-19 vaccination initially lowered the mean age of at-risk patients and later changed the characteristics of those who died. This highlights the importance of understanding these shifts for assessing factors that affect patient outcomes. Objective: This study aims to propose detection, initial characterization, and semantic characterization (DIS), a new methodology for analyzing changes in health outcomes and variables over time while discovering contextual changes for outcomes in large volumes of data. Methods: The DIS methodology involves 3 steps: detection, initial characterization, and semantic characterization. Detection uses metrics such as Jensen-Shannon divergence to identify significant data drifts. Initial characterization offers a global analysis of changes in data distribution and predictive feature significance over time. Semantic characterization uses natural language processing–inspired techniques to understand the local context of these changes, helping identify factors driving changes in patient outcomes. By integrating the outcomes from these 3 steps, our results can identify specific factors (eg, interventions and modifications in health care practices) that drive changes in patient outcomes. DIS was applied to the Brazilian COVID-19 Registry and the Medical Information Mart for Intensive Care, version IV (MIMIC-IV) data sets. Results: Our approach allowed us to (1) identify drifts effectively, especially using metrics such as the Jensen-Shannon divergence, and (2) uncover reasons for the decline in overall mortality in both the COVID-19 and MIMIC-IV data sets, as well as changes in the cooccurrence between different diseases and this particular outcome. Factors such as vaccination during the COVID-19 pandemic and reduced iatrogenic events and cancer-related deaths in MIMIC-IV were highlighted. The methodology also pinpointed shifts in patient demographics and disease patterns, providing insights into the evolving health care landscape during the study period. Conclusions: We developed a novel methodology combining machine learning and natural language processing techniques to detect, characterize, and understand temporal shifts in health care data. This understanding can enhance predictive algorithms, improve patient outcomes, and optimize health care resource allocation, ultimately improving the effectiveness of machine learning predictive algorithms applied to health care data. Our methodology can be applied to a variety of scenarios beyond those discussed in this paper. SN - 2291-9694 UR - https://medinform.jmir.org/2024/1/e54246 UR - https://doi.org/10.2196/54246 DO - 10.2196/54246 ID - info:doi/10.2196/54246 ER -