The Impact of Artificial Intelligence on Health Equity in Oncology: Scoping Review.

BACKGROUND: The field of oncology is at the forefront of advances in artificial intelligence (AI) in health care, providing an opportunity to examine the early integration of these technologies in clinical research and patient care. Hope that AI will revolutionize health care delivery and improve clinical outcomes has been accompanied by concerns about the impact of these technologies on health equity. OBJECTIVE: We aimed to conduct a scoping review of the literature to address the question, "What are the current and potential impacts of AI technologies on health equity in oncology?" METHODS: Following PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines for scoping reviews, we systematically searched MEDLINE and Embase electronic databases from January 2000 to August 2021 for records engaging with key concepts of AI, health equity, and oncology. We included all English-language articles that engaged with the 3 key concepts. Articles were analyzed qualitatively for themes pertaining to the influence of AI on health equity in oncology. RESULTS: Of the 14,011 records, 133 (0.95%) identified from our review were included. We identified 3 general themes in the literature: the use of AI to reduce health care disparities (58/133, 43.6%), concerns surrounding AI technologies and bias (16/133, 12.1%), and the use of AI to examine biological and social determinants of health (55/133, 41.4%). A total of 3% (4/133) of articles focused on many of these themes. CONCLUSIONS: Our scoping review revealed 3 main themes on the impact of AI on health equity in oncology, which relate to AI's ability to help address health disparities, its potential to mitigate or exacerbate bias, and its capability to help elucidate determinants of health. Gaps in the literature included a lack of discussion of ethical challenges with the application of AI technologies in low- and middle-income countries, lack of discussion of problems of bias in AI algorithms, and a lack of justification for the use of AI technologies over traditional statistical methods to address specific research questions in oncology. Our review highlights a need to address these gaps to ensure a more equitable integration of AI in cancer research and clinical practice. The limitations of our study include its exploratory nature, its focus on oncology as opposed to all health care sectors, and its analysis of solely English-language articles.

Health-Related Quality-of-Life and Cost Utility Analyses in Critical Care: A Systematic Review.

OBJECTIVES: Cost utility analyses compare the costs and health outcome of interventions, with a denominator of quality-adjusted life year, a generic health utility measure combining both quality and quantity of life. Cost utility analyses are difficult to compare when methods are not standardized. It is unclear how cost utility analyses are measured/reported in critical care and what methodologic challenges cost utility analyses pose in this setting. This may lead to differences precluding cost utility analyses comparisons. Therefore, we performed a systematic review of cost utility analyses conducted in critical care. Our objectives were to understand: 1) methodologic characteristics, 2) how health-related quality-of-life was measured/reported, and 3) what costs were reported/measured. DESIGN: Systematic review. DATA SOURCES: We systematically searched for cost utility analyses in critical care in MEDLINE, Embase, American College of Physicians Journal Club, CENTRAL, Evidence-Based Medicine Reviews' selected subset of archived versions of UK National Health Service Economic Evaluation Database, Database of Abstracts of Reviews of Effects, and American Economic Association electronic databases from inception to April 30, 2020. SETTING: Adult ICUs. PATIENTS: Adult critically ill patients. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Of 8,926 citations, 80 cost utility analyse studies were eligible. The time horizon most commonly reported was lifetime (59%). For health utility reporting, health-related quality-of-life was infrequently measured (29% reported), with only 5% of studies reporting baseline health-related quality-of-life. Indirect utility measures (generic, preference-based health utility measurement tools) were reported in 85% of studies (majority Euro-quality-of-life-5 Domains, 52%). Methods of estimating health-related quality-of-life were seldom used when the patient was incapacitated: imputation (19%), assigning fixed utilities for incapacitation (19%), and surrogates reporting on behalf of incapacitated patients (5%). For cost utility reporting transparency, separate incremental costs and quality-adjusted life years were both reported in only 76% of studies. Disaggregated quality-adjusted life years (reporting separate health utility and life years) were described in only 34% of studies. CONCLUSIONS: We identified deficiencies which warrant recommendations (standardized measurement/reporting of resource use/unit costs/health-related quality-of-life/methodological preferences) for improved design, conduct, and reporting of future cost utility analyses in critical care.

Probiotics in hospitalized adult patients: a systematic review of economic evaluations.

PURPOSE: Probiotics may prevent healthcare-associated infections, such as ventilator-associated pneumonia, Clostridioides difficile-associated diarrhea, and other adverse outcomes. Despite their potential benefits, there are no summative data examining the cost-effectiveness of probiotics in hospitalized patients. This systematic review summarized studies evaluating the economic impact of using probiotics in hospitalized adult patients. METHODS: We searched MEDLINE, EMBASE, CENTRAL, ACP Journal Club, and other EBM reviews (inception to January 31, 2019) for health economics evaluations examining the use of probiotics in hospitalized adults. Independently and in duplicate, we extracted data study characteristics, risk of bias, effectiveness and total costs (medications, diagnostics/procedures, devices, personnel, hospital) associated with healthcare-associated infections (ventilator-associated pneumonia, Clostridioides difficile-associated diarrhea and antibiotic-associated diarrhea). We used Grading of Recommendations Assessment, Development and Evaluation methods to assess certainty in the overall cost-effectiveness evidence. RESULTS: Of 721 citations identified, we included seven studies. For the clinical outcomes of interest, there was one randomized-controlled trial (RCT)-based health economic evaluation, and six model-based health economic evaluations. Probiotics showed favourable cost-effectiveness in six of seven (86%) economic evaluations. Three of the seven studies were manufacturer-supported, all which suggested cost-effectiveness. Certainty of cost-effectiveness evidence was very low because of risk of bias, imprecision, and inconsistency. CONCLUSION: Probiotics may be an economically attractive intervention for preventing ventilator-associated pneumonia, Clostridioides difficile-associated diarrhea, and antibiotic-associated diarrhea in hospitalized adult patients. Nevertheless, certainty about their cost-effectiveness evidence is very low. Future RCTs examining probiotics should incorporate cost data to inform bedside practice, clinical guidelines, and healthcare policy. TRIAL REGISTRATION: PROSPERO CRD42019129929; Registered 25 April, 2019.