RESUMEN
OBJECTIVE: We developed and externally validated a machine-learning model to predict postpartum depression (PPD) using data from electronic health records (EHRs). Effort is under way to implement the PPD prediction model within the EHR system for clinical decision support. We describe the pre-implementation evaluation process that considered model performance, fairness, and clinical appropriateness. MATERIALS AND METHODS: We used EHR data from an academic medical center (AMC) and a clinical research network database from 2014 to 2020 to evaluate the predictive performance and net benefit of the PPD risk model. We used area under the curve and sensitivity as predictive performance and conducted a decision curve analysis. In assessing model fairness, we employed metrics such as disparate impact, equal opportunity, and predictive parity with the White race being the privileged value. The model was also reviewed by multidisciplinary experts for clinical appropriateness. Lastly, we debiased the model by comparing 5 different debiasing approaches of fairness through blindness and reweighing. RESULTS: We determined the classification threshold through a performance evaluation that prioritized sensitivity and decision curve analysis. The baseline PPD model exhibited some unfairness in the AMC data but had a fair performance in the clinical research network data. We revised the model by fairness through blindness, a debiasing approach that yielded the best overall performance and fairness, while considering clinical appropriateness suggested by the expert reviewers. DISCUSSION AND CONCLUSION: The findings emphasize the need for a thorough evaluation of intervention-specific models, considering predictive performance, fairness, and appropriateness before clinical implementation.
Asunto(s)
Depresión Posparto , Registros Electrónicos de Salud , Aprendizaje Automático , Humanos , Femenino , Medición de Riesgo/métodos , Sistemas de Apoyo a Decisiones ClínicasRESUMEN
BACKGROUND: Elder mistreatment (EM) is associated with adverse health outcomes and healthcare utilization patterns that differ from other older adults. However, the association of EM with healthcare costs has not been examined. Our goal was to compare healthcare costs between legally adjudicated EM victims and controls. METHODS: We used Medicare insurance claims to examine healthcare costs of EM victims in the 2 years surrounding initial mistreatment identification in comparison to matched controls. We adjusted costs using the Centers for Medicare and Medicaid Services Hierarchical Condition Categories (CMS-HCC) risk score. RESULTS: We examined healthcare costs in 114 individuals who experienced EM and 410 matched controls. Total Medicare Parts A and B healthcare costs were similar between cases and controls in the 12 months prior to initial EM detection ($11,673 vs. $11,402, p = 0.92), but cases had significantly higher total healthcare costs during the 12 months after initial mistreatment identification ($15,927 vs. $10,805, p = 0.04). Adjusting for CMS-HCC scores, cases had, in the 12 months after initial EM identification, $5084 of additional total healthcare costs (95% confidence interval [$92, $10,077], p = 0.046) and $5817 of additional acute/subacute/post-acute costs (95% confidence interval [$1271, $10,362], p = 0.012) compared with controls. The significantly higher total costs and acute/sub-acute/post-acute costs among EM victims in the post-year were concentrated in the 120 days after EM detection. CONCLUSIONS: Older adults experiencing EM had substantially higher total costs during the 12 months after mistreatment identification, driven by an increase in acute/sub-acute/post-acute costs and focused on the period immediately after initial EM detection.
Asunto(s)
Abuso de Ancianos , Anciano , Humanos , Recolección de Datos , Abuso de Ancianos/diagnóstico , Costos de la Atención en Salud , Medicare , Factores de Riesgo , Estados UnidosRESUMEN
BACKGROUND: SARS-CoV-2-infected patients may develop new conditions in the period after the acute infection. These conditions, the post-acute sequelae of SARS-CoV-2 infection (PASC, or Long COVID), involve a diverse set of organ systems. Limited studies have investigated the predictability of Long COVID development and its associated risk factors. METHODS: In this retrospective cohort study, we used electronic healthcare records from two large-scale PCORnet clinical research networks, INSIGHT (~1.4 million patients from New York) and OneFlorida+ (~0.7 million patients from Florida), to identify factors associated with having Long COVID, and to develop machine learning-based models for predicting Long COVID development. Both SARS-CoV-2-infected and non-infected adults were analysed during the period of March 2020 to November 2021. Factors associated with Long COVID risk were identified by removing background associations and correcting for multiple tests. RESULTS: We observed complex association patterns between baseline factors and a variety of Long COVID conditions, and we highlight that severe acute SARS-CoV-2 infection, being underweight, and having baseline comorbidities (e.g., cancer and cirrhosis) are likely associated with increased risk of developing Long COVID. Several Long COVID conditions, e.g., dementia, malnutrition, chronic obstructive pulmonary disease, heart failure, PASC diagnosis U099, and acute kidney failure are well predicted (C-index > 0.8). Moderately predictable conditions include atelectasis, pulmonary embolism, diabetes, pulmonary fibrosis, and thromboembolic disease (C-index 0.7-0.8). Less predictable conditions include fatigue, anxiety, sleep disorders, and depression (C-index around 0.6). CONCLUSIONS: This observational study suggests that association patterns between investigated factors and Long COVID are complex, and the predictability of different Long COVID conditions varies. However, machine learning-based predictive models can help in identifying patients who are at risk of developing a variety of Long COVID conditions.
Most people who develop COVID-19 make a full recovery, but some go on to develop post-acute sequelae of SARS-CoV-2 infection, commonly known as Long COVID. Up to now, we did not know why some people are affected by Long COVID whilst others are not. We conducted a study to identify risk factors for Long COVID and developed a mathematical modeling approach to predict those at risk. We find that Long COVID is associated with some factors such as experiencing severe acute COVID-19, being underweight, and having conditions including cancer or cirrhosis. Due to the wide variety of symptoms defined as Long COVID, it may be challenging to come up with a set of risk factors that can predict the whole spectrum of Long COVID. However, our approach could be used to predict a variety of Long COVID conditions.