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

Ensemble for evaluating diagnostic efficacy of non-invasive indices in predicting liver fibrosis in untreated hepatitis C virus population

BACKGROUND

Hepatitis C virus (HCV) infection progresses through various phases, starting with inflammation and ending with hepatocellular carcinoma. There are several invasive and non-invasive methods to diagnose chronic HCV infection. The invasive methods have their benefits but are linked to morbidity and complications. Thus, it is important to analyze the potential of non-invasive methods as an alternative. Shear wave elastography (SWE) is a non-invasive imaging tool widely validated in clinical and research studies as a surrogate marker of liver fibrosis. Liver fibrosis determination by invasive liver biopsy and non-invasive SWE agree closely in clinical studies and therefore both are gold standards.

AIM

To analyzed the diagnostic efficacy of non-invasive indices [serum fibronectin, aspartate aminotransferase to platelet ratio index (APRI), alanine aminotransferase ratio (AAR), and fibrosis-4 (FIB-4)] in relation to SWE. We have used an Artificial Intelligence method to predict the severity of liver fibrosis and uncover the complex relationship between non-invasive indices and fibrosis severity.

METHODS

We have conducted a hospital-based study considering 100 untreated patients detected as HCV positive using a quantitative Real-Time Polymerase Chain Reaction assay. We performed statistical and probabilistic analyses to determine the relationship between non-invasive indices and the severity of fibrosis. We also used standard diagnostic methods to measure the diagnostic accuracy for all the subjects.

RESULTS

The results of our study showed that fibronectin is a highly accurate diagnostic tool for predicting fibrosis stages (mild, moderate, and severe). This was based on its sensitivity (100%, 92.2%, 96.2%), specificity (96%, 100%, 98.6%), Youden’s index (0.960, 0.922, 0.948), area under receiver operating characteristic curve (0.999, 0.993, 0.922), and Likelihood test (LR+ > 10 and LR- < 0.1). Additionally, our Bayesian Network analysis revealed that fibronectin (> 200), AAR (> 1), APRI (> 3), and FIB-4 (> 4) were all strongly associated with patients who had severe fibrosis, with a 100% probability.

CONCLUSION

We have found a strong correlation between fibronectin and liver fibrosis progression in HCV patients. Additionally, we observed that the severity of liver fibrosis increases with an increase in the non-invasive indices that we investigated.

Uncovering the burden of hidradenitis suppurativa misdiagnosis and underdiagnosis: a machine learning approach

Hidradenitis suppurativa (HS) is a chronic inflammatory follicular skin condition that is associated with significant psychosocial and economic burden and a diminished quality of life and work productivity. Accurate diagnosis of HS is challenging due to its unknown etiology, which can lead to underdiagnosis or misdiagnosis that results in increased patient and healthcare system burden. We applied machine learning (ML) to a medical and pharmacy claims database using data from 2000 through 2018 to develop a novel model to better understand HS underdiagnosis on a healthcare system level. The primary results demonstrated that high-performing models for predicting HS diagnosis can be constructed using claims data, with an area under the curve (AUC) of 81%-82% observed among the top-performing models. The results of the models developed in this study could be input into the development of an impact of inaction model that determines the cost implications of HS diagnosis and treatment delay to the healthcare system.

Machine learning for prediction of viral hepatitis: A systematic review and meta-analysis

BACKGROUND

Lack of accurate and timely diagnosis of hepatitis poses obstacles to effective treatment, disease progression prevention, complication reduction, and life-saving interventions of patients. Utilizing machine learning can greatly enhance the achievement of timely and precise disease diagnosis. Therefore, we carried out this systematic review and meta-analysis to explore the performance of machine learning algorithms in predicting viral hepatitis.

METHODS

Using an extensive literature search in PubMed, Scopus, and Web of Science databases until June 15, 2023, English publications on hepatitis prediction using machine learning algorithms were included. Two authors independently extracted pertinent information from the selected studies. The PRISMA 2020 checklist was followed for study selection and result reporting. The risk of bias was checked using the International Journal of Medical Informatics (IJMEDI) checklist. Data were analyzed using the 'metandi' command in Stata 17.

RESULTS

Twenty-one original studies were included, covering 82 algorithms. Sixteen studies utilized five algorithms to predict hepatitis B. Ten studies used five algorithms for hepatitis C prediction. For hepatitis B prediction, the SVM algorithms demonstrated the highest sensitivity (90.0%; 95% confidence interval (CI): 77.0%-96.0%), specificity (94%; 95% CI: 90.0%-97.0%), and a diagnostic odds ratio (DOR) of 145 (95% CI: 37.0-559.0). In the case of hepatitis C, the KNN algorithms exhibited the highest sensitivity (80%; 95% CI:30.0%-97.0%), specificity (95%; 95% CI: 58.0%-99.0%), and DOR (72; 95% CI: 3.0-1644.0) for prediction.

CONCLUSION

SVM and KNN demonstrated superior performance in predicting hepatitis. The proper algorithm along with clinical practice could improve hepatitis prediction and management.

Machine learning prediction models for clinical management of blood-borne viral infections: a systematic review of current applications and future impact

BACKGROUND

Machine learning (ML) prediction models to support clinical management of blood-borne viral infections are becoming increasingly abundant in medical literature, with a number of competing models being developed for the same outcome or target population. However, evidence on the quality of these ML prediction models are limited.

OBJECTIVE

This study aimed to evaluate the development and quality of reporting of ML prediction models that could facilitate timely clinical management of blood-borne viral infections.

METHODS

We conducted narrative evidence synthesis following the synthesis without meta-analysis guidelines. We searched PubMed and Cochrane Central Register of Controlled Trials for all studies applying ML models for predicting clinical outcomes associated with hepatitis B virus (HBV), human immunodeficiency virus (HIV), or hepatitis C virus (HCV).

RESULTS

We found 33 unique ML prediction models aiming to support clinical decision making. Overall, 12 (36.4%) focused on HBV, 10 (30.3%) on HCV, 10 on HIV (30.3%) and two (6.1%) on co-infection. Among these, six (18.2%) addressed the diagnosis of infection, 16 (48.5%) the prognosis of infection, eight (24.2%) the prediction of treatment response, two (6.1%) progression through a cascade of care, and one (3.03%) focused on the choice of antiretroviral therapy (ART). Nineteen prediction models (57.6%) were developed using data from high-income countries. Evaluation of prediction models was limited to measures of performance. Detailed information on software code accessibility was often missing. Independent validation on new datasets and/or in other institutions was rarely done.

CONCLUSION

Promising approaches for ML prediction models in blood-borne viral infections were identified, but the lack of robust validation, interpretability/explainability, and poor quality of reporting hampered their clinical relevance. Our findings highlight important considerations that can inform standard reporting guidelines for ML prediction models in the future (e.g., TRIPOD-AI), and provides critical data to inform robust evaluation of the models.

Revolutionizing Cancer Research: The Impact of Artificial Intelligence in Digital Biobanking

BACKGROUND

Biobanks are vital research infrastructures aiming to collect, process, store, and distribute biological specimens along with associated data in an organized and governed manner. Exploiting diverse datasets produced by the biobanks and the downstream research from various sources and integrating bioinformatics and "omics" data has proven instrumental in advancing research such as cancer research. Biobanks offer different types of biological samples matched with rich datasets comprising clinicopathologic information. As digital pathology and artificial intelligence (AI) have entered the precision medicine arena, biobanks are progressively transitioning from mere biorepositories to integrated computational databanks. Consequently, the application of AI and machine learning on these biobank datasets holds huge potential to profoundly impact cancer research.

METHODS

In this paper, we explore how AI and machine learning can respond to the digital evolution of biobanks with flexibility, solutions, and effective services. We look at the different data that ranges from specimen-related data, including digital images, patient health records and downstream genetic/genomic data and resulting "Big Data" and the analytic approaches used for analysis.

RESULTS

These cutting-edge technologies can address the challenges faced by translational and clinical research, enhancing their capabilities in data management, analysis, and interpretation. By leveraging AI, biobanks can unlock valuable insights from their vast repositories, enabling the identification of novel biomarkers, prediction of treatment responses, and ultimately facilitating the development of personalized cancer therapies.

CONCLUSIONS

The integration of biobanking with AI has the potential not only to expand the current understanding of cancer biology but also to pave the way for more precise, patient-centric healthcare strategies.

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.

Identifying individuals with undiagnosed post-traumatic stress disorder in a large United States civilian population - a machine learning approach

BACKGROUND

The proportion of patients with post-traumatic stress disorder (PTSD) that remain undiagnosed may be substantial. Without an accurate diagnosis, these patients may lack PTSD-targeted treatments and experience adverse health outcomes. This study used a machine learning approach to identify and describe civilian patients likely to have undiagnosed PTSD in the US commercial population.

METHODS

The IBM® MarketScan® Commercial Subset (10/01/2015-12/31/2018) was used. A random forest machine learning model was developed and trained to differentiate between patients with and without PTSD using non-trauma-based features. The model was applied to patients for whom PTSD status could not be confirmed to identify individuals likely and unlikely to have undiagnosed PTSD. Patient characteristics, symptoms and complications potentially related to PTSD, treatments received, healthcare costs, and healthcare resource utilization were described separately for patients with PTSD (Actual Positive PTSD cohort), patients likely to have PTSD (Likely PTSD cohort), and patients without PTSD (Without PTSD cohort).

RESULTS

A total of 44,342 patients were classified in the Actual Positive PTSD cohort, 5683 in the Likely PTSD cohort, and 2,074,471 in the Without PTSD cohort. While several symptoms/comorbidities were similar between the Actual Positive and Likely PTSD cohorts, others, including depression and anxiety disorders, suicidal thoughts/actions, and substance use, were more common in the Likely PTSD cohort, suggesting that certain symptoms may be exacerbated among those without a formal diagnosis. Mean per-patient-per-6-month healthcare costs were similar between the Actual Positive and Likely PTSD cohorts ($11,156 and $11,723) and were higher than those of the Without PTSD cohort ($3616); however, cost drivers differed between cohorts, with the Likely PTSD cohort experiencing more inpatient admissions and less outpatient visits than the Actual Positive PTSD cohort.

CONCLUSIONS

These findings suggest that the lack of a PTSD diagnosis and targeted management of PTSD may result in a greater burden among undiagnosed patients and highlights the need for increased awareness of PTSD in clinical practice and among the civilian population.

Predicting misdiagnosed adult-onset type 1 diabetes using machine learning

AIMS

It is now understood that almost half of newly diagnosed cases of type 1 diabetes are adult-onset. However, type 1 and type 2 diabetes are difficult to initially distinguish clinically in adults, potentially leading to ineffective care. In this study a machine learning model was developed to identify type 1 diabetes patients misdiagnosed as type 2 diabetes.

METHODS

In this retrospective study, a machine learning model was developed to identify misdiagnosed type 1 diabetes patients from a population of patients with a prior type 2 diabetes diagnosis. Using Ambulatory Electronic Medical Records (AEMR), features capturing relevant information on age, demographics, risk factors, symptoms, treatments, procedures, vitals, or lab results were extracted from patients' medical history.

RESULTS

The model identified age, BMI/weight, therapy history, and HbA1c/blood glucose values among top predictors of misdiagnosis. Model precision at low levels of recall (10 %) was 17 %, compared to <1 % incidence rate of misdiagnosis at the time of the first type 2 diabetes encounter in AEMR.

CONCLUSIONS

This algorithm shows potential for being translated into screening guidelines or a clinical decision support tool embedded directly in an EMR system to reduce misdiagnosis of adult-onset type 1 diabetes and implement effective care at the outset.

Application of artificial intelligence in non-alcoholic fatty liver disease and viral hepatitis

Non-alcoholic fatty liver disease (NAFLD) and chronic viral hepatitis are among the most significant causes of liver-related mortality worldwide. It is critical to develop reliable methods of predicting progression to fibrosis, cirrhosis, and decompensated liver disease. Current screening methods such as biopsy and transient elastography are limited by invasiveness and observer variation in analysis of data. Artificial intelligence (AI) provides a unique opportunity to more accurately diagnose NAFLD and viral hepatitis, and to identify patients at high risk for disease progression. We conducted a literature review of existing evidence for AI in NAFLD and viral hepatitis. Thirteen articles on AI in NAFLD and 14 on viral hepatitis were included in our analysis. We found that machine learning algorithms were comparable in accuracy to current methods for diagnosis and fibrosis prediction (MELD-Na score, liver biopsy, FIB-4 score, and biomarkers). They also reliably predicted hepatitis C treatment failure and hepatic encephalopathy, for which there are currently no established prediction tools. These studies show that AI could be a helpful adjunct to existing techniques for diagnosing, monitoring, and treating both NAFLD and viral hepatitis.

Burden of chronic hepatitis B and C infections in 2015 and future trends in Japan: A simulation study

Background

Determining the number of chronic hepatitis B (HBV) and C virus (HCV) infections is essential to assess the progress towards the World Health Organization 2030 viral hepatitis elimination goals. Using data from the Japanese National Database (NDB), we calculated the number of chronic HBV and HCV infections in 2015 and predicted the trend until 2035.

Methods

NDB and first-time blood donors data were used to calculate the number of chronic HBV and HCV infections in 2015. A Markov simulation was applied to predict chronic infections until 2035 using transition probabilities calculated from NDB data.

Findings

The total number of chronic HBV and HCV infections in 2015 in Japan was 1,905,187–2,490,873 (HCV:877,841–1,302,179, HBV:1,027,346–1,188,694), of which 923,661–1,509,347 were undiagnosed or diagnosed but not linked to care (“not engaged in care”), and 981,526 were engaged in care. Chronic HBV and HCV infections are expected to be 923,313–1,304,598 in 2030, and 739,118–1,045,884 in 2035. Compared to 2015, by 2035, the number of persons with HCV not engaged in care will decline by 59·8 – 76·1% and 86·5% for patients in care. For HBV, a 47·3 – 49·3% decrease is expected for persons not engaged in care and a decline of 26·0% for patients engaged in care.

Interpretation

Although the burden of HBV and HCV is expected to decrease by 2035, challenges in controlling hepatitis remain. Improved and innovative screening strategies with linkage to care for HCV cases, and a functional cure for HBV are needed.

Funding

Japan Ministry of Health, Labour and Welfare.

Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH)

Objectives

To develop and evaluate machine learning models to detect patients with suspected undiagnosed non-alcoholic steatohepatitis (NASH) for diagnostic screening and clinical management.

Methods

In this retrospective observational non-interventional study using administrative medical claims data from 1 463 089 patients, gradient-boosted decision trees were trained to detect patients with likely NASH from an at-risk patient population with a history of obesity, type 2 diabetes mellitus, metabolic disorder or non-alcoholic fatty liver (NAFL). Models were trained to detect likely NASH in all at-risk patients or in the subset without a prior NAFL diagnosis (at-risk non-NAFL patients). Models were trained and validated using retrospective medical claims data and assessed using area under precision recall curves and receiver operating characteristic curves (AUPRCs and AUROCs).

Results

The 6-month incidences of NASH in claims data were 1 per 1437 at-risk patients and 1 per 2127 at-risk non-NAFL patients. The model trained to detect NASH in all at-risk patients had an AUPRC of 0.0107 (95% CI 0.0104 to 0.0110) and an AUROC of 0.84. At 10% recall, model precision was 4.3%, which is 60× above NASH incidence. The model trained to detect NASH in the non-NAFL cohort had an AUPRC of 0.0030 (95% CI 0.0029 to 0.0031) and an AUROC of 0.78. At 10% recall, model precision was 1%, which is 20× above NASH incidence.

Conclusion

The low incidence of NASH in medical claims data corroborates the pattern of NASH underdiagnosis in clinical practice. Claims-based machine learning could facilitate the detection of patients with probable NASH for diagnostic testing and disease management.

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

IMPORTANCE

Initiation of injection drug use may be more frequent among people dispensed prescription opioid therapy for noncancer pain, potentially increasing the risk of hepatitis C virus (HCV) acquisition.

OBJECTIVE

To assess the association between medically dispensed long-term prescription opioid therapy for noncancer pain and HCV seroconversion among individuals who were initially injection drug use-naive.

DESIGN, SETTING, AND PARTICIPANTS

A population-based, retrospective cohort study of individuals tested for HCV in British Columbia, Canada, with linkage to outpatient pharmacy dispensations, was conducted. Individuals with an initial HCV-negative test result followed by 1 additional test between January 1, 2000, and December 31, 2017, and who had no history of substance use at baseline (first HCV-negative test), were included. Participants were followed up from baseline to the last HCV-negative test or estimated date of seroconversion (midpoint between HCV-positive and the preceding HCV-negative test).

EXPOSURES

Episodes of prescription opioid use for noncancer pain were defined as acute (<90 days) or long-term (≥90 days). Prescription opioid exposure status (long-term vs prescription opioid-naive/acute) was treated as time-varying in survival analyses. In secondary analyses, long-term exposure was stratified by intensity of use (chronic vs. episodic) and by average daily dose in morphine equivalents (MEQ).

MAIN OUTCOMES AND MEASURES

Multivariable Cox regression models were used to assess the association between time-varying prescription opioid status and HCV seroconversion.

RESULTS

A total of 382 478 individuals who had more than 1 HCV test were included, of whom more than half were female (224 373 [58.7%]), born before 1974 (201 944 [52.8%]), and younger than 35 years at baseline (196 298 [53.9%]). Participants were followed up for 2 057 668 person-years and 1947 HCV seroconversions occurred. Of the participants, 41 755 people (10.9%) were exposed to long-term prescription opioid therapy at baseline or during follow-up. The HCV seroconversion rate per 1000 person-years was 0.8 among the individuals who were prescription opioid-naive/acute (1489 of 1947 [76.5%] seroconversions; 0.4% seroconverted within 5 years) and 2.1 with long-term prescription opioid therapy (458 of 1947 [23.5%] seroconversions; 1.1% seroconverted within 5 years). In multivariable analysis, exposure to long-term prescription opioid therapy was associated with a 3.2-fold (95% CI, 2.9-3.6) higher risk of HCV seroconversion (vs prescription opioid-naive/acute). In separate Cox models, long-term chronic use was associated with a 4.7-fold higher risk of HCV seroconversion (vs naive/acute use 95% CI, 3.9-5.8), and long-term higher-dose use (≥90 MEQ) was associated with a 5.1-fold higher risk (vs naive/acute use 95% CI, 3.7-7.1).

CONCLUSIONS AND RELEVANCE

In this cohort study of people with more than 1 HCV test, long-term prescription opioid therapy for noncancer pain was associated with a higher risk of HCV seroconversion among individuals who were injection drug use-naive at baseline or at prescription opioid initiation. These results suggest injection drug use initiation risk is higher among people dispensed long-term therapy and may be useful for informing approaches to identify and prevent HCV infection. These findings should not be used to justify abrupt discontinuation of long-term therapy, which could increase risk of harms.

Artificial intelligence for hepatitis evaluation

Recently, increasing attention has been paid to the application of artificial intelligence (AI) to the diagnosis of diverse hepatic diseases, which comprises traditional machine learning and deep learning. Recent studies have shown the possible value of AI based data mining in predicting the incidence of hepatitis, classifying the different stages of hepatitis, diagnosing or screening for hepatitis, forecasting the progression of hepatitis, and predicting response to antiviral drugs in chronic hepatitis C patients. More importantly, AI based on radiology has been proven to be useful in predicting hepatitis and liver fibrosis as well as grading hepatocellular carcinoma (HCC) and differentiating it from benign liver tumors. It can predict the risk of vascular invasion of HCC, the risk of hepatic encephalopathy secondary to hepatitis B related cirrhosis, and the risk of liver failure after hepatectomy in HCC patients. In this review, we summarize the application of AI in hepatitis, and identify the challenges and future perspectives.

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

BACKGROUND/INTRODUCTION

Artificial intelligence (AI) in the healthcare sector is receiving attention from researchers and health professionals. Few previous studies have investigated this topic from a multi-disciplinary perspective, including accounting, business and management, decision sciences and health professions.

METHODS

The structured literature review with its reliable and replicable research protocol allowed the researchers to extract 288 peer-reviewed papers from Scopus. The authors used qualitative and quantitative variables to analyse authors, journals, keywords, and collaboration networks among researchers. Additionally, the paper benefited from the Bibliometrix R software package.

RESULTS

The investigation showed that the literature in this field is emerging. It focuses on health services management, predictive medicine, patient data and diagnostics, and clinical decision-making. The United States, China, and the United Kingdom contributed the highest number of studies. Keyword analysis revealed that AI can support physicians in making a diagnosis, predicting the spread of diseases and customising treatment paths.

CONCLUSIONS

The literature reveals several AI applications for health services and a stream of research that has not fully been covered. For instance, AI projects require skills and data quality awareness for data-intensive analysis and knowledge-based management. Insights can help researchers and health professionals understand and address future research on AI in the healthcare field.