Development and Validation of an Electronic Medical Record-Based Algorithm to Identify Patient Milestones in the Hepatitis C Virus Care Cascade

Hepatitis C Cascades: Data to Inform Hepatitis C Elimination in the United States

The United States has a goal to eliminate hepatitis C as a public health threat by 2030. To accomplish this goal, hepatitis C virus (HCV) care cascades (hereinafter, HCV cascades) can be used to measure progress toward HCV elimination and identify disparities in HCV testing and care. In this topical review of HCV cascades, we describe common definitions of cascade steps, review the application of HCV cascades in health care and public health settings, and discuss the strengths and limitations of data sources used. We use examples from the Massachusetts Department of Public Health as a case study to illustrate how multiple data sources can be leveraged to produce HCV cascades for public health purposes. HCV cascades in health care settings provide actionable data to improve health care quality and delivery of services in a single health system. In public health settings at jurisdictional and national levels, HCV cascades describe HCV diagnosis and treatment for populations, which can be challenging in the absence of a single data source containing complete, comprehensive, and timely data representing all steps of a cascade. Use of multiple data sources and strategies to improve interoperability of health care and public health data systems can advance the use of HCV cascades and speed progress toward HCV elimination.

Hybrid model for precise hepatitis-C classification using improved random forest and SVM method

Hepatitis C Virus (HCV) is a viral infection that causes liver inflammation. Annually, approximately 3.4 million cases of HCV are reported worldwide. A diagnosis of HCV in earlier stages helps to save lives. In the HCV review, the authors used a single ML-based prediction model in the current research, which encounters several issues, i.e., poor accuracy, data imbalance, and overfitting. This research proposed a Hybrid Predictive Model (HPM) based on an improved random forest and support vector machine to overcome existing research limitations. The proposed model improves a random forest method by adding a bootstrapping approach. The existing RF method is enhanced by adding a bootstrapping process, which helps eliminate the tree's minor features iteratively to build a strong forest. It improves the performance of the HPM model. The proposed HPM model utilizes a 'Ranker method' to rank the dataset features and applies an IRF with SVM, selecting higher-ranked feature elements to build the prediction model. This research uses the online HCV dataset from UCI to measure the proposed model's performance. The dataset is highly imbalanced; to deal with this issue, we utilized the synthetic minority over-sampling technique (SMOTE). This research performs two experiments. The first experiment is based on data splitting methods, K-fold cross-validation, and training: testing-based splitting. The proposed method achieved an accuracy of 95.89% for k = 5 and 96.29% for k = 10; for the training and testing-based split, the proposed method achieved 91.24% for 80:20 and 92.39% for 70:30, which is the best compared to the existing SVM, MARS, RF, DT, and BGLM methods. In experiment 2, the analysis is performed using feature selection (with SMOTE and without SMOTE). The proposed method achieves an accuracy of 41.541% without SMOTE and 96.82% with SMOTE-based feature selection, which is better than existing ML methods. The experimental results prove the importance of feature selection to achieve higher accuracy in HCV research.

Finding undiagnosed patients with hepatitis C virus: an application of machine learning to US ambulatory electronic medical records

AIMS

To develop and validate a machine learning (ML) algorithm to identify undiagnosed hepatitis C virus (HCV) patients, in order to facilitate prioritisation of patients for targeted HCV screening.

METHODS

This retrospective study used ambulatory electronic medical records (EMR) from January 2015 to February 2020. A Gradient Boosting Trees algorithm was trained using patient records to predict initial HCV diagnosis and was validated on a temporally independent held-out cross-section of the data. The fold improvement in precision (proportion of patients identified by the algorithm who are HCV positive) over universal screening was examined and compared with risk-based screening.

RESULTS

21 508 positive (HCV diagnosed) and 28.2M unlabelled (lacking evidence of HCV diagnosis) patients met the inclusion criteria for the study. After down-sampling unlabelled patients to aid the algorithm's learning process, 16.2M unlabelled patients entered the analysis. Performance of the algorithm was compared with universal screening on the held-out cross-section, which had an incidence of HCV diagnoses of 0.02%. The algorithm achieved a 101.0 ×, 18.0 × and 5.1 × fold improvement in precision over universal screening at 5%, 20% and 50% levels of recall. When compared with risk-based screening, the algorithm required fewer patients to be screened and improved precision.

CONCLUSIONS

This study presents strong evidence towards the use of ML on EMR data for the prioritisation of patients for targeted HCV testing with potential to improve efficiency of resource utilisation, thereby reducing the workload for clinicians and saving healthcare costs. A prospective interventional study would allow for further validation before use in a clinical setting.

Strategy for the Micro-Elimination of Hepatitis C among Patients with Diabetes Mellitus-A Hospital-Based Experience

Hepatitis C virus (HCV) infection can induce insulin resistance, and patients with diabetes mellitus (DM) have a higher prevalence of HCV infection. Patient outcomes improve after HCV eradication in DM patients. However, HCV micro-elimination targeting this population has not been approached. Little is known about using electronic alert systems for HCV screening among patients with DM in a hospital-based setting. We implemented an electronic reminder system for HCV antibody screening and RNA testing in outpatient departments among patients with DM. The screening rates and treatment rates at different departments before and after system implementation were compared. The results indicated that the total HCV screening rate increased from 49.3% (9505/19,272) to 78.2% (15,073/19,272), and the HCV-RNA testing rate increased from 73.4% to 94.2%. The anti-HCV antibody seropositive rate was 5.7%, and the HCV viremia rate was 62.7% in our patient population. The rate of positive anti-HCV antibodies and HCV viremia increased with patient age. This study demonstrates the feasibility and usefulness of an electronic alert system for HCV screening and treatment among DM patients in a hospital-based setting.

Design of an Enhanced Public Health Surveillance System for Hepatitis C Virus Elimination in King County, Washington

INTRODUCTION

With the goal of eliminating hepatitis C virus (HCV) as a public health problem in Washington State, Public Health-Seattle & King County (PHSKC) designed a Hepatitis C Virus Test and Cure (HCV-TAC) data system to integrate surveillance, clinical, and laboratory data into a comprehensive database. The intent of the system was to promote identification, treatment, and cure of HCV-infected persons (ie, HCV care cascade) using a population health approach.

MATERIALS AND METHODS

The data system automatically integrated case reports received via telephone and fax from health care providers and laboratories, hepatitis test results reported via electronic laboratory reporting, and data on laboratory and clinic visits reported by 6 regional health care systems. PHSKC examined patient-level laboratory test results and established HCV case classification using Council of State and Territorial Epidemiologists criteria, classifying patients as confirmed if they had detectable HCV RNA.

RESULTS

The data enabled PHSKC to report the number of patients at various stages along the HCV care cascade. Of 7747 HCV RNA-positive patients seen by a partner site, 5377 (69%) were assessed for severity of liver fibrosis, 3932 (51%) were treated, and 2592 (33%) were cured.

PRACTICE IMPLICATIONS

Data supported local public heath surveillance and HCV program activities. The data system could serve as a foundation for monitoring future HCV prevention and control programs.

The simplification of the diagnosis process of chronic hepatitis C is cost-effective strategy

BACKGROUND

The cascade of care of the hepatitisC are complex. The diagnosis of active infection in the same serum sample would simplify the process establishing a rapid access for patients to treatment. Our objective was to estimate the impact on healthcare and economic outcomes of the diagnosis of chronic infection in one-step diagnosis compared to standard diagnosis in Andalusia (8.39 million people).

METHODS

A decision tree was developed to estimate the referral of patients with chronic infection, loss of follow-up, access to treatment and costs of the diagnosis of the infection, for both processes. The unit costs (€, 2018) of the health resources (medical visits, antibodies, viral load and genotype), without considering the pharmacological cost, were obtained form public sources in Andalusia.

RESULTS

Of the total estimated population (269,526 patients), 1,389 patients would be referred to the specialised care in the one-step diagnosis and 1,063 in de standard diagnosis, being treated 1,320 and 1,009, respectively. In one-step diagnosis, no negative viral loud patient would be referred to specialist versus 540 with standard diagnosis. One-step diagnosis would generate a cost saving of €184,928 versus standard diagnosis (€15,671,493 vs €15,856,421). When compared one-step diagnosis to standard diagnosis, the savings per patient with positive viral load referred to specialist would be €3,634 (€11,279 vs €14,923).

CONCLUSION

The one-step diagnosis will achieve an increase in diagnosed patients, will increase the access of chronic patient to treatment and will generate cost savings, demonstrating its efficiency in the system in Andalusia.

Hepatitis C in Pregnancy: A Unique Opportunity to Improve the Hepatitis C Cascade of Care

Hepatitis C has increasingly affected women of child-bearing age over the past few years as a result of the opioid epidemic. In this review, we discuss the effect of hepatitis C on pregnancy outcomes, effect of pregnancy on hepatitis C, as well as implications on management of hepatitis C during pregnancy.