1 April 2020 in International Journal of Nursing Studies
11 March 2022 in BMC Medical Informatics and Decision Making
Background: Evaluation of new treatment policies is often costly and challenging in complex conditions, such as hepatitis C virus (HCV) treatment, or in limited-resource settings. We sought to identify hypothetical policies for HCV treatment that could best balance the prevention of cirrhosis while preserving resources (financial or otherwise). Methods: The cohort consisted of 3792 HCV-infected patients without a history of cirrhosis or hepatocellular carcinoma at baseline from the national Veterans Health Administration from 2015 to 2019. To estimate the efficacy of hypothetical treatment policies, we utilized historical data and reinforcement learning to allow for greater flexibility when constructing new HCV treatment strategies. We tested and compared four new treatment policies: a simple stepwise policy based on Aspartate Aminotransferase to Platelet Ratio Index (APRI), a logistic regression based on APRI, a logistic regression on multiple longitudinal and demographic indicators that were prespecified for clinical significance, and a treatment policy based on a risk model developed for HCV infection. Results: The risk-based hypothetical treatment policy achieved the lowest overall risk with a score of 0.016 (90% CI 0.016, 0.019) while treating the most high-risk (346.4 ± 1.4) and the fewest low-risk (361.0 ± 20.1) patients. Compared to hypothetical treatment policies that treated approximately the same number of patients (1843.7 vs. 1914.4 patients), the risk-based policy had more untreated time per patient (7968.4 vs. 7742.9 patient visits), signaling cost reduction for the healthcare system. Conclusions: Off-policy evaluation strategies are useful to evaluate hypothetical treatment policies without implementation. If a quality risk model is available, risk-based treatment strategies can reduce overall risk and prioritize patients while reducing healthcare system costs.
2 January 2025 in Artificial Intelligence in Health
In this study, we aim to examine the efficacy of deep learning methods in predicting the 1-year risk of developing cirrhosis in patients with chronic hepatitis C (CHC), as defined by transient elastography (TE), in comparison with conventional models, as well as to assess whether semi-supervised learning can improve performance relative to supervised learning when the labels are limited. We used the electronic health records of the 169,317 valid patients in the Veterans Health Administration system from 2000 to 2016. Predictor variables contained baseline characteristics, such as age, gender, race, hepatitis C virus genotype, and 26 liver-related longitudinal variables such as sustained virologic response and laboratory data. The response variable, developing cirrhosis, is defined as liver stiffness >12.5 kPa on TE within a 1-year window. Using baseline and longitudinal variables, we fitted four prediction models, including logistic regression (LR), random forest (RF), supervised recurrent neural network (RNN), and semi-supervised RNN (semi-RNN) and evaluated their performances. Both RNN (area under the receiver operating characteristic curve [AuROC] 0.744) and semi-RNN (AuROC 0.785) accurately predicted the risk of cirrhosis within 1 year and significantly outperformed RF (AuROC 0.731) and LR (AuROC 0.724). By enabling early identification of high-risk patients, these models hold promise for targeted interventions in clinical CHC treatment.