@Article{info:doi/10.2196/54246,
author="Paiva, Bruno
and Gon{\c{c}}alves, Marcos Andr{\'e}
and da Rocha, Leonardo Chaves Dutra
and Marcolino, Milena Soriano
and Lana, Fernanda Cristina Barbosa
and Souza-Silva, Maira Viana Rego
and Almeida, Jussara M
and Pereira, Polianna Delfino
and de Andrade, Claudio Mois{\'e}s Valiense
and Gomes, Ang{\'e}lica Gomides dos Reis
and Ferreira, Maria Ang{\'e}lica Pires
and Bartolazzi, Frederico
and Sacioto, Manuela Furtado
and Boscato, Ana Paula
and Guimar{\~a}es-J{\'u}nior, Milton Henriques
and dos Reis, Priscilla Pereira
and Costa, Fel{\'i}cio Roberto
and Jorge, Alzira de Oliveira
and Coelho, Laryssa Reis
and Carneiro, Marcelo
and Sales, Tha{\'i}s Lorenna Souza
and Ara{\'u}jo, Silvia Ferreira
and Silveira, Daniel Vit{\'o}rio
and Ruschel, Karen Brasil
and Santos, Fernanda Caldeira Veloso
and Cenci, Evelin Paola de Almeida
and Menezes, Luanna Silva Monteiro
and Anschau, Fernando
and Bicalho, Maria Aparecida Camargos
and Manenti, Euler Roberto Fernandes
and Finger, Renan Goulart
and Ponce, Daniela
and de Aguiar, Filipe Carrilho
and Marques, Luiza Margoto
and de Castro, Lu{\'i}s C{\'e}sar
and Vietta, Giovanna Gr{\"u}newald
and Godoy, Mariana Frizzo de
and Vila{\c{c}}a, Mariana do Nascimento
and Morais, Vivian Costa",
title="A New Natural Language Processing--Inspired Methodology (Detection, Initial Characterization, and Semantic Characterization) to Investigate Temporal Shifts (Drifts) in Health Care Data: Quantitative Study",
journal="JMIR Med Inform",
year="2024",
month="Oct",
day="28",
volume="12",
pages="e54246",
keywords="health care; machine learning; data drifts; temporal drifts",
abstract="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. ",
issn="2291-9694",
doi="10.2196/54246",
url="https://medinform.jmir.org/2024/1/e54246",
url="https://doi.org/10.2196/54246"
}