Finding undiagnosed patients with hepatitis C infection: an application of artificial intelligence to patient claims data

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. Chronic hepatitis C virus (HCV) is the leading cause of cirrhosis, liver cancer, and death from liver diseases as well as the primary indication for liver transplantation globally 1. In the United States (US), the prevalence of HCV was reported to range between 0.6% and 1.5% 2-4 with use of intravenous drugs 5 , blood transfusion (prior to 1992), high number of sexual partners and haemodialysis and body piercings or tattoos 5 reported as common risk factors. The advent of direct acting anti-virals (DAAs) has the potential to transform the HCV treatment landscape 6 with these treatments hailed as curative. However, despite these advances, HCV remains a significant public health challenge with approximately half of the infected population untreated and undiagnosed 7. Realising the potential benefits of novel treatments requires a reduction in the size of the undiagnosed population, coupled with early diagnosis so that patients can be treated before experiencing long term consequences of HCV infection 8. To improve diagnosis rates, the Centers for Disease Control and Prevention (CDC) introduced a risk-based screening programme for those who have used or are currently using intravenous drugs, have particular diagnoses (e.g. HIV infection), and were recipients of blood transfusions or organ transplants prior to 1992. In 2012, the CDC augmented the current recommendation for risk-based screening to include people who were born between 1945 and 1965 9 which was motivated by the fact that 75% of the diagnosed HCV population were born during this period....

The role of artificial intelligence in healthcare: a structured literature review

“…AI has been a disruptive innovation in healthcare [ 4 ]. With its sophisticated algorithms and several applications, AI has assisted doctors and medical professionals in the domains of health information systems, geocoding health data, epidemic and syndromic surveillance, predictive modelling and decision support, and medical imaging [ 2 , 9 , 10 , 64 ]. Furthermore, the researchers considered the bibliometric analysis to identify four macro-variables dominant in the field and used them as authors' keywords.…”

“…AI technologies can ingest, analyse, and report large volumes of data across different modalities to detect disease and guide clinical decisions [ 3 , 8 ]. AI applications can deal with the vast amount of data produced in medicine and find new information that would otherwise remain hidden in the mass of medical big data [ 9 – 11 ]. These technologies can also identify new drugs for health services management and patient care treatments [ 5 , 6 ].…”

“…However, as Meskò et al [ 7 ] find, the technology will potentially reduce care costs and repetitive operations by focusing the medical profession on critical thinking and clinical creativity. As Cho et al and Doyle et al [ 8 , 9 ] add, the AI perspective is exciting; however, new studies will be needed to establish the efficacy and applications of AI in the medical field [ 10 ].…”

“…hidden in the mass of medical big data [9][10][11]. These technologies can also identify new drugs for health services management and patient care treatments [5,6].…”

Association Between Prescription Opioid Therapy for Noncancer Pain and Hepatitis C Virus Seroconversion

“…An ecological study has implicated prescription opioid policies in increasing HCV diagnoses in the US 21 and 2 administrative case-control analyses have identified prior dispensation of prescription opioids as a risk factor for HCV diagnosis. 25 , 26 However, these studies assessed HCV diagnosis, and most analyses of HCV seroconversion have focused on the association between nonmedical prescription opioid injection and HCV acquisition among people who already inject drugs. 27 , 28 In this present analysis, we examined the association between medically dispensed prescription opioid therapy for noncancer pain and HCV seroconversion among individuals who were initially injection drug use–naive in a large population-based cohort of people who had more than 1 HCV test.…”