Finding undiagnosed patients with hepatitis C infection: an application of artificial intelligence to patient claims
Orla M Doyle1, Nadejda Leavitt2, John A Rigg3
1Predictive Analytics, Real World Solutions, IQVIA, London, N1 9JY, UK. orla.doyle@iqvia.com.
Insights
Identifying undiagnosed Hepatitis C virus (HCV) cases is crucial. This study developed artificial intelligence (AI) models using medical claims to accurately pinpoint individuals with undiagnosed HCV, improving public health outcomes.
Area of Science:
- Hepatology
- Medical Informatics
- Public Health
Background:
- Hepatitis C virus (HCV) infection is a major global health concern, with a significant portion of cases remaining undiagnosed and untreated.
- Early detection and treatment of HCV are vital to prevent disease progression and transmission.
Purpose of the Study:
- To develop and evaluate predictive models for identifying patients with undiagnosed Hepatitis C virus (HCV) using electronic health records.
- To assess the performance of various machine learning algorithms in detecting undiagnosed HCV cases.
Main Methods:
- A retrospective analysis of longitudinal medical claims and prescription data from approximately ten million US patients (2010-2016).
- Extraction of demographic, risk factor, symptom, treatment, and procedure features relevant to HCV.
- Development and comparison of predictive algorithms including logistic regression, random forests, gradient boosted trees, and a stacked ensemble.
Main Results:
- Patients often exhibited HCV symptoms 2-3 years before diagnosis.
- All developed algorithms achieved at least 95% precision at 10% recall.
- The stacked ensemble model demonstrated superior performance with 97% precision at >50% recall, outperforming other models.
Conclusions:
- Artificial intelligence (AI) algorithms can significantly enhance the identification of undiagnosed HCV cases.
- The AI model's high precision surpasses current screening recommendations, offering a potential step-change in HCV screening effectiveness.
- This approach holds promise for improving public health strategies in managing HCV infection.
Abstract:
Hepatitis C virus (HCV) remains a significant public health challenge with approximately half of the infected population untreated and undiagnosed. In this retrospective study, predictive models were developed to identify undiagnosed HCV patients using longitudinal medical claims linked to prescription data from approximately ten million patients in the United States (US) between 2010 and 2016. Features capturing information on demographics, risk factors, symptoms, treatments and procedures relevant to HCV were extracted from patients' medical history. Predictive algorithms were developed based on logistic regression, random forests, gradient boosted trees and a stacked ensemble. Descriptive analysis indicated that patients exhibited known symptoms of HCV on average 2-3 years prior to their diagnosis. The precision was at least 95% for all algorithms at low levels of recall (10%). For recall levels >50%, the stacked ensemble performed best with a precision of 97% compared with 87% for the gradient boosted trees and just 31% for the logistic regression. For context, the Center for Disease Control recommends screening in an at-risk sub-population with an estimated HCV prevalence of 2.23%. The artificial intelligence (AI) algorithm presented here has a precision which is substantially higher than the screening rates associated with recommended clinical guidelines, suggesting that AI algorithms have the potential to provide a step change in the effectiveness of HCV screening.
