Variations in breast cancer surgical treatment and timing: determinants and disparities.

PURPOSE: To describe clinical and non-clinical factors associated with receipt of breast conserving surgery (BCS) versus mastectomy and time to surgical intervention. METHODS: Cross-sectional retrospective study of January 1, 2012 through March 31, 2018 data from the IBM MarketScan Commercial Claims and Encounter and Medicare Supplemental Databases. Area Health Resource Files provided non-clinical characteristics and sociodemographic data. Eligibility: Female sex, claim(s) with ICD-9-CM or ICD-10-CM diagnosis of non-metastatic invasive breast cancer, > 6 months of continuous insurance pre- and post-diagnosis, evidence of BCS or mastectomy following initial ICD9/10 code diagnosis. Logistic and quantile multivariable regression models assessed the association between clinical and non-clinical factors and the outcome of BCS and time to surgery, respectively. RESULTS: A total of 53,060 women were included in the study. Compared to mastectomy, BCS was significantly associated with older age (ORs: 1.54 to 2.99, 95% CIs 1.45 to 3.38; ps < .0001) and higher community density of medical genetics (OR: 5.88, 95% CIs 1.38 to 25.00; p = 0.02) or obstetrics and gynecology (OR: 1.13, 95% CI 1.02 to 1.25; p = .02) physicians. Shorter time-to-BCS was associated with living in the South (-2.96, 95% CI -4.39 to -1.33; p < .0001). Longer time-to-BCS was associated with residence in more urban (4.18, 95% CI 0.08 to 8.29; p = 0. 05), educated (9.02, 95% CI 0.13 to 17.91; p = 0.05), or plastic-surgeon-dense (4.62, 95% CI 0.50 to 8.73; p = 0.03) communities. CONCLUSIONS: Clinical and non-clinical factors are associated with adoption of BCS and time to treatment, suggesting opportunities to ensure equitable and timely care.

Health Care Equity in the Use of Advanced Analytics and Artificial Intelligence Technologies in Primary Care.

The integration of advanced analytics and artificial intelligence (AI) technologies into the practice of medicine holds much promise. Yet, the opportunity to leverage these tools carries with it an equal responsibility to ensure that principles of equity are incorporated into their implementation and use. Without such efforts, tools will potentially reflect the myriad of ways in which data, algorithmic, and analytic biases can be produced, with the potential to widen inequities by race, ethnicity, gender, and other sociodemographic factors implicated in disparate health outcomes. We propose a set of strategic assertions to examine before, during, and after adoption of these technologies in order to facilitate healthcare equity across all patient population groups. The purpose is to enable generalists to promote engagement with technology companies and co-create, promote, or support innovation and insights that can potentially inform decision-making and health care equity.

Clinical Decision Support for High-Risk Stage II Colon Cancer: A Real-World Study of Treatment Concordance and Survival.

BACKGROUND: Prognostic and pathologic risk factors typically guide clinicians and patients in their choice of surveillance or adjuvant chemotherapy when managing high-risk stage II colon cancer. However, variations in treatment and outcomes in patients with stage II colon cancer remain. OBJECTIVE: This study aimed to assess the survival benefits of treatments concordant with suggested therapeutic options from Watson for Oncology, a clinical decision support system. DESIGN: This is a retrospective observational study of concordance between actual treatment and Watson for Oncology therapeutic options. SETTING: This study was conducted at a top-tier cancer center in China. PATIENTS: Postoperative treatment data were retrieved from the electronic health records of 306 patients with high-risk stage II colon adenocarcinoma. MAIN OUTCOME MEASURES: The primary outcomes measured were the treatment patterns plus 3- and 5-year overall and disease-free survival for concordant and nonconcordant cases. RESULTS: Overall concordance was 90%. Most nonconcordant care resulted from adjuvant chemotherapy use (rather than surveillance) in patients with high-level microsatellite instability and ≥70 years old. No difference in overall survival (p = 0.56) or disease-free survival (p = 0.19) was observed between concordance groups. Patients receiving adjuvant chemotherapy had significantly higher 5-year overall survival than those undergoing surveillance (94% vs 84%, p = 0.01). LIMITATIONS: This study was limited by the use of retrospective cases drawn from patients presenting for surgery, the lack of complete follow-up data for 58% of patients who could not be included in the analysis, and a survival analysis that assumes no unmeasured correlation between survival and censoring. CONCLUSIONS: Watson for Oncology produced therapeutic options highly concordant with human decisions at a top-tier cancer center in China. Treatment patterns suggest that Watson for Oncology may be able to guide clinicians to minimize overtreatment of patients with high-risk stage II colon cancer with chemotherapy. Survival analyses suggest the need for further investigation to specifically assess the association between surveillance, single-agent and multiagent chemotherapy, and survival outcomes in this population. See Video Abstract at http://links.lww.com/DCR/B291. APOYO A LA DECISIÓN CLÍNICA DEL CÁNCER DE COLON EN ESTADIO II DE ALTO RIESGO: UN ESTUDIO DEL MUNDO REAL SOBRE LA CONCORDANCIA DEL TRATAMIENTO Y LA SUPERVIVENCIA: Los factores de riesgo pronósticos y patológicos generalmente guían a los médicos y pacientes en su elección de vigilancia o quimioterapia adyuvante cuando se trata el cáncer de colon en estadio II de alto riesgo. Sin embargo, las variaciones en el tratamiento y los resultados en pacientes con cáncer de colon en estadio II permanecen.Evaluar los beneficios de supervivencia de los tratamientos concordantes con las opciones terapéuticas sugeridas por "Watson for Oncology" (Watson para la oncología), un sistema de apoyo a la decisión clínica.Estudio observacional retrospectivo de concordancia entre el tratamiento real y las opciones terapéuticas de Watson para oncología.Un centro oncológico de primer nivel en China.Datos de tratamiento postoperatorio de registros de salud electrónicos de 306 pacientes con adenocarcinoma de colon en estadio II de alto riesgo.Patrones de tratamiento más supervivencia global y libre de enfermedad a 3 y 5 años para casos concordantes y no concordantes.La concordancia general fue del 90%. La mayoría de la atención no concordante resultó del uso de quimioterapia adyuvante (en lugar de vigilancia) en pacientes de alto nivel con inestabilidad de microsatélites y pacientes ≥70 años. No se observaron diferencias en la supervivencia global (p = 0,56) o la supervivencia libre de enfermedad (p = 0,19) entre los grupos de concordancia. Los pacientes que recibieron quimioterapia adyuvante tuvieron una supervivencia global a los 5 años significativamente más alta que los que fueron sometidos a vigilancia (94% frente a 84%, p = 0,01).Uso de casos retrospectivos extraídos de pacientes que se presentan para cirugía, falta de datos de seguimiento completos para el 58% de los pacientes que no pudieron ser incluidos en el análisis, y análisis de supervivencia que asume que no exite una correlación no medida entre supervivencia y censura.Watson para Oncología produjo opciones terapéuticas altamente concordantes con las decisiones humanas en un centro oncológico de primer nivel en China. Los patrones de tratamiento sugieren que Watson para Oncología puede guiar a los médicos para minimizar el sobretratamiento de pacientes con cáncer de colon en estadio II de alto riesgo con quimioterapia. Los análisis de supervivencia sugieren la necesidad de realizar mas investigaciónes para evaluar específicamente la asociación entre la vigilancia, la quimioterapia con uno solo o múltiples agentes y los resultados de supervivencia en esta población. Consulte Video Resumen en http://links.lww.com/DCR/B291. (Traducción-Dr. Gonzalo Hagerman).

Screening Health-Related Social Needs in Hospitals: A Systematic Review of Health Care Professional and Patient Perspectives.

Health outcomes are markedly influenced by health-related social needs (HRSN) such as food insecurity and housing instability. Under new Joint Commission requirements, hospitals have recently increased attention to HRSN to reduce health disparities. To evaluate prevailing attitudes and guide hospital efforts, the authors conducted a systematic review to describe patients' and health care providers' perceptions related to screening for and addressing patients' HRSN in US hospitals. Articles were identified through PubMed and by expert recommendations, and synthesized by relevance of findings and basic study characteristics. The review included 22 articles, which showed that most health care providers believed that unmet social needs impact health and that screening for HRSN should be a standard part of hospital care. Notable differences existed between perceived importance of HRSN and actual screening rates, however. Patients reported high receptiveness to screening in hospital encounters, but cautioned to avoid stigmatization and protect privacy when screening. Limited knowledge of resources available, lack of time, and lack of actual resources were the most frequently reported barriers to screening for HRSN. Hospital efforts to screen and address HRSN will likely be facilitated by stakeholders' positive perceptions, but common barriers to screening and referral will need to be addressed to effectively scale up efforts and impact health disparities.

Disparity dashboards: an evaluation of the literature and framework for health equity improvement.

The growing recognition of differences in health outcomes across populations has led to a slow but increasing shift towards transparent reporting of patient outcomes. In addition, pay-for-equity initiatives, such as those proposed by the Centers for Medicare and Medicaid, will require the reporting of health outcomes across subgroups over time. Dashboards offer one means of visualising data in the health-care context that can highlight essential disparities in clinical outcomes, guide targeted quality-improvement efforts, and ultimately improve health equity. In this Viewpoint, we evaluate all studies that have reported the successful development of a disparity dashboard and share the data collected and unintended consequences reported. We propose a framework for systematic equality improvement through incentivisation of the collecting and reporting of health data and through implementation of reward systems to reduce health disparities.

Evaluating Social Determinants of Health Variables in Advanced Analytic and Artificial Intelligence Models for Cardiovascular Disease Risk and Outcomes: A Targeted Review.

Introduction/Purpose: Predictive models incorporating relevant clinical and social features can provide meaningful insights into complex interrelated mechanisms of cardiovascular disease (CVD) risk and progression and the influence of environmental exposures on adverse outcomes. The purpose of this targeted review (2018-2019) was to examine the extent to which present-day advanced analytics, artificial intelligence, and machine learning models include relevant variables to address potential biases that inform care, treatment, resource allocation, and management of patients with CVD. Methods: PubMed literature was searched using the prespecified inclusion and exclusion criteria to identify and critically evaluate primary studies published in English that reported on predictive models for CVD, associated risks, progression, and outcomes in the general adult population in North America. Studies were then assessed for inclusion of relevant social variables in the model construction. Two independent reviewers screened articles for eligibility. Primary and secondary independent reviewers extracted information from each full-text article for analysis. Disagreements were resolved with a third reviewer and iterative screening rounds to establish consensus. Cohen's kappa was used to determine interrater reliability. Results: The review yielded 533 unique records where 35 met the inclusion criteria. Studies used advanced statistical and machine learning methods to predict CVD risk (10, 29%), mortality (19, 54%), survival (7, 20%), complication (10, 29%), disease progression (6, 17%), functional outcomes (4, 11%), and disposition (2, 6%). Most studies incorporated age (34, 97%), sex (34, 97%), comorbid conditions (32, 91%), and behavioral risk factor (28, 80%) variables. Race or ethnicity (23, 66%) and social variables, such as education (3, 9%) were less frequently observed. Conclusions: Predictive models should adjust for race and social predictor variables, where relevant, to improve model accuracy and to inform more equitable interventions and decision making.

Evaluating equitable care in the ICU: Creating a causal inference framework to assess the impact of life-sustaining interventions across racial and ethnic groups.

Background: Variability in the provision of intensive care unit (ICU)-interventions may lead to disparities between socially defined racial-ethnic groups. Research Question: We used causal inference to examine the use of invasive mechanical ventilation (IMV), renal replacement therapy (RRT), and vasopressor agents (VP) to identify disparities in outcomes across race-ethnicity in patients with sepsis. Study Design and Methods: Single-center, academic referral hospital in Boston, Massachusetts, USA. Retrospective analysis of treatment effect with a targeted trial design categorized by treatment assignment within the first 24 hours in the MIMIC-IV dataset (2008- 2019) using targeted maximum likelihood estimation. Of 76,943 ICU stays in MIMIC-IV, 32,971 adult stays fulfilling sepsis-3 criteria were included. The primary outcome was in-hospital mortality. Secondary outcomes were hospital-free days, and occurrence of nosocomial infection stratified by predicted mortality probability ranges and self-reported race-ethnicity. Average treatment effects by treatment type and race-ethnicity, Racial-ethnic group (REG) or White group (WG), were estimated. Results: Of 19,419 admissions that met inclusion criteria, median age was 68 years, 57.4% were women, 82% were White, and mortality was 18.2%. There was no difference in mortality benefit associated with the administration of IMV, RRT, or VP between the REG and the WG. There was also no difference in hospital-free days or nosocomial infections. These findings are unchanged with different eligibility periods. Interpretation: There were no differences in the treatment outcomes from three life-sustaining interventions in the ICU according to race-ethnicity. While there was no discernable harm from the treatments across mortality risk, there was also no measurable benefit. These findings highlight the need for research to understand better the risk-benefit of life-sustaining interventions in the ICU.

Strategies and solutions to address Digital Determinants of Health (DDOH) across underinvested communities.

Healthcare has long struggled to improve services through technology without further widening health disparities. With the significant expansion of digital health, a group of healthcare professionals and scholars from across the globe are proposing the official usage of the term "Digital Determinants of Health" (DDOH) to explicitly call out the relationship between technology, healthcare, and equity. This is the final paper in a series published in PLOS Digital Health that seeks to understand and summarize current knowledge of the strategies and solutions that help to mitigate the negative effects of DDOH for underinvested communities. Through a search of English-language Medline, Scopus, and Google Scholar articles published since 2010, 345 articles were identified that discussed the application of digital health technology among underinvested communities. A group of 8 reviewers assessed 132 articles selected at random for the mention of solutions that minimize differences in DDOH. Solutions were then organized by categories of policy; design and development; implementation and adoption; and evaluation and ongoing monitoring. The data were then assessed by category and the findings summarized. The reviewers also looked for common themes across the solutions and evidence of effectiveness. From this limited scoping review, the authors found numerous solutions mentioned across the papers for addressing DDOH and many common themes emerged regardless of the specific community or digital health technology under review. There was notably less information on solutions regarding ongoing evaluation and monitoring which corresponded with a lack of research evidence regarding effectiveness. The findings directionally suggest that universal strategies and solutions can be developed to address DDOH independent of the specific community under focus. With the need for the further development of DDOH measures, we also provide a framework for DDOH assessment.

A new tool for evaluating health equity in academic journals; the Diversity Factor.

Current methods to evaluate a journal's impact rely on the downstream citation mapping used to generate the Impact Factor. This approach is a fragile metric prone to being skewed by outlier values and does not speak to a researcher's contribution to furthering health outcomes for all populations. Therefore, we propose the implementation of a Diversity Factor to fulfill this need and supplement the current metrics. It is composed of four key elements: dataset properties, author country, author gender and departmental affiliation. Due to the significance of each individual element, they should be assessed independently of each other as opposed to being combined into a simplified score to be optimized. Herein, we discuss the necessity of such metrics, provide a framework to build upon, evaluate the current landscape through the lens of each key element and publish the findings on a freely available website that enables further evaluation. The OpenAlex database was used to extract the metadata of all papers published from 2000 until August 2022, and Natural language processing was used to identify individual elements. Features were then displayed individually on a static dashboard developed using TableauPublic, which is available at www.equitablescience.com. In total, 130,721 papers were identified from 7,462 journals where significant underrepresentation of LMIC and Female authors was demonstrated. These findings are pervasive and show no positive correlation with the Journal's Impact Factor. The systematic collection of the Diversity Factor concept would allow for more detailed analysis, highlight gaps in knowledge, and reflect confidence in the translation of related research. Conversion of this metric to an active pipeline would account for the fact that how we define those most at risk will change over time and quantify responses to particular initiatives. Therefore, continuous measurement of outcomes across groups and those investigating those outcomes will never lose importance. Moving forward, we encourage further revision and improvement by diverse author groups in order to better refine this concept.

Artificial Intelligence and Machine Learning Technologies in Cancer Care: Addressing Disparities, Bias, and Data Diversity.

SUMMARY: Artificial intelligence (AI) and machine learning (ML) technologies have not only tremendous potential to augment clinical decision-making and enhance quality care and precision medicine efforts, but also the potential to worsen existing health disparities without a thoughtful, transparent, and inclusive approach that includes addressing bias in their design and implementation along the cancer discovery and care continuum. We discuss applications of AI/ML tools in cancer and provide recommendations for addressing and mitigating potential bias with AI and ML technologies while promoting cancer health equity.

For the Commercially Insured, Equitable Health Benefits Begin With Equitable Health Insurance Design.

Equitable health benefit design is central to addressing the health inequities of individuals with commercial health insurance in the United States. To do so, employers and other plan sponsors must take action to identify and address unmet health and well-being priorities among racialized groups and low-income workers. These historically underrepresented subpopulations will also benefit from more equitable approaches to healthcare benefits design that recognize and meaningfully address access and affordability concerns. Targeted appropriately, these actions have the potential to foster greater employee engagement and productivity, leading to enhanced business performance.

The development and implementation of a new hospital performance measure to assess hospital contributions to community health and equity.

OBJECTIVE: To develop and implement a measure of how US hospitals contribute to community health with a focus on equity. DATA SOURCES: Primary data from public comments and hospital surveys and secondary data from the IBM Watson Top 100 Hospitals program collected in the United States in 2020 and 2021. STUDY DESIGN: A thematic analysis of public comments on the proposed measure was conducted using an iterative grounded approach for theme identification. A cross-sectional survey of 207 hospitals was conducted to assess self-attestation to 28 community health best practice standards in the revised measure. An analysis of hospital rankings before and after inclusion of the new measure was performed. DATA COLLECTION/EXTRACTION METHODS: Public comment on the proposed measure was collected via an online survey, email, and virtual meetings in 2020. The survey of hospitals was conducted online by IBM in 2021. The analysis of hospital ranking compared the 2020 and 2021 IBM Watson Top 100 Hospitals program results. PRINCIPAL FINDINGS: More than 650 discrete comments from 83 stakeholders were received and analyzed during measure development. Key themes identified in thematic analysis included equity, fairness, and community priorities. Hospitals that responded to a cross-sectional survey reported meeting on average 76% of applicable best practice standards. Least met standards included providing emergent buprenorphine treatment for opioid use disorder (53%), supporting an evidence-based home visiting program (53%), and establishing a returning citizens employment program (27%). Thirty-seven hospitals shifted position in the 100 Top Hospital rankings after the inclusion of the new measure. CONCLUSIONS: There is broad interest in measuring hospital contributions to community health with a focus on equity. Many highly ranked hospitals report meeting best practice standards, but significant gaps remain. Improving measurement to incentivize greater hospital contributions to community health and equity is an important priority.

Symposium on integrating the science of environmental justice into decision-making at the Environmental Protection Agency: an overview.

In March 2010, the Environmental Protection Agency (EPA) collaborated with government and nongovernmental organizations to host a groundbreaking symposium, "Strengthening Environmental Justice Research and Decision Making: A Symposium on the Science of Disproportionate Environmental Health Impacts." The symposium provided a forum for discourse on the state of scientific knowledge about factors identified by EPA that may contribute to higher burdens of environmental exposure or risk in racial/ethnic minorities and low-income populations. Also featured were discussions on how environmental justice considerations may be integrated into EPA's analytical and decision-making frameworks and on research needs for advancing the integration of environmental justice into environmental policymaking. We summarize key discussions and conclusions from the symposium and briefly introduce the articles in this issue.

Chronic disease surveillance systems within the US Associated Pacific Island jurisdictions.

In recent years, illness and death due to chronic disease in the US Associated Pacific Islands (USAPI) jurisdictions have dramatically increased. Effective chronic disease surveillance can help monitor disease trends, evaluate public policy, prioritize resource allocation, and guide program planning, evaluation, and research. Although chronic disease surveillance is being conducted in the USAPI, no recently published capacity assessments for chronic disease surveillance are available. The objective of this study was to assess the quality of existing USAPI chronic disease data sources and identify jurisdictional capacity for chronic disease surveillance. The assessment included a chronic disease data source inventory, literature review, and review of surveillance documentation available from the web or through individual jurisdictions. We used the World Health Organization's Health Metric Network Framework to assess data source quality and to identify jurisdictional capacity. Results showed that USAPI data sources are generally aligned with widely accepted chronic disease surveillance indicators and use standardized data collection methodology to measure chronic disease behavioral risks, preventive practices, illness, and death. However, all jurisdictions need to strengthen chronic disease surveillance through continued assessment and expanded support for valid and reliable data collection, analysis and reporting, dissemination, and integration among population-based and institution-based data sources. For sustained improvement, we recommend investment and technical assistance in support of a chronic disease surveillance system that integrates population-based and institution-based data sources. An integrated strategy that bridges and links USAPI data sources can support evidence-based policy and population health interventions.

Artificial intelligence applications in social media for depression screening: A systematic review protocol for content validity processes.

BACKGROUND: The popularization of social media has led to the coalescing of user groups around mental health conditions; in particular, depression. Social media offers a rich environment for contextualizing and predicting users' self-reported burden of depression. Modern artificial intelligence (AI) methods are commonly employed in analyzing user-generated sentiment on social media. In the forthcoming systematic review, we will examine the content validity of these computer-based health surveillance models with respect to standard diagnostic frameworks. Drawing from a clinical perspective, we will attempt to establish a normative judgment about the strengths of these modern AI applications in the detection of depression. METHODS: We will perform a systematic review of English and German language publications from 2010 to 2020 in PubMed, APA PsychInfo, Science Direct, EMBASE Psych, Google Scholar, and Web of Science. The inclusion criteria span cohort, case-control, cross-sectional studies, randomized controlled studies, in addition to reports on conference proceedings. The systematic review will exclude some gray source materials, specifically editorials, newspaper articles, and blog posts. Our primary outcome is self-reported depression, as expressed on social media. Secondary outcomes will be the types of AI methods used for social media depression screen, and the clinical validation procedures accompanying these methods. In a second step, we will utilize the evidence-strengthening Population, Intervention, Comparison, Outcomes, Study type (PICOS) tool to refine our inclusion and exclusion criteria. Following the independent assessment of the evidence sources by two authors for the risk of bias, the data extraction process will culminate in a thematic synthesis of reviewed studies. DISCUSSION: We present the protocol for a systematic review which will consider all existing literature from peer reviewed publication sources relevant to the primary and secondary outcomes. The completed review will discuss depression as a self-reported health outcome in social media material. We will examine the computational methods, including AI and machine learning techniques which are commonly used for online depression surveillance. Furthermore, we will focus on standard clinical assessments, as indicating content validity, in the design of the algorithms. The methodological quality of the clinical construct of the algorithms will be evaluated with the COnsensus-based Standards for the selection of health status Measurement Instruments (COSMIN) framework. We conclude the study with a normative judgment about the current application of AI to screen for depression on social media. SYSTEMATIC REVIEW REGISTRATION: International Prospective Register of Systematic Reviews PROSPERO (registration number CRD42020187874).

TechQuity is an imperative for health and technology business: Let's work together to achieve it.

Open discussions of social justice and health inequities may be an uncommon focus within information technology science, business, and health care delivery partnerships. However, the COVID-19 pandemic-which disproportionately affected Black, indigenous, and people of color-has reinforced the need to examine and define roles that technology partners should play to lead anti-racism efforts through our work. In our perspective piece, we describe the imperative to prioritize TechQuity-equity and social justice as a technology business strategy-through collaborating in partnerships that focus on eliminating racial and social inequities.

Comparison of Methods to Reduce Bias From Clinical Prediction Models of Postpartum Depression.

Importance: The lack of standards in methods to reduce bias for clinical algorithms presents various challenges in providing reliable predictions and in addressing health disparities. Objective: To evaluate approaches for reducing bias in machine learning models using a real-world clinical scenario. Design, Setting, and Participants: Health data for this cohort study were obtained from the IBM MarketScan Medicaid Database. Eligibility criteria were as follows: (1) Female individuals aged 12 to 55 years with a live birth record identified by delivery-related codes from January 1, 2014, through December 31, 2018; (2) greater than 80% enrollment through pregnancy to 60 days post partum; and (3) evidence of coverage for depression screening and mental health services. Statistical analysis was performed in 2020. Exposures: Binarized race (Black individuals and White individuals). Main Outcomes and Measures: Machine learning models (logistic regression [LR], random forest, and extreme gradient boosting) were trained for 2 binary outcomes: postpartum depression (PPD) and postpartum mental health service utilization. Risk-adjusted generalized linear models were used for each outcome to assess potential disparity in the cohort associated with binarized race (Black or White). Methods for reducing bias, including reweighing, Prejudice Remover, and removing race from the models, were examined by analyzing changes in fairness metrics compared with the base models. Baseline characteristics of female individuals at the top-predicted risk decile were compared for systematic differences. Fairness metrics of disparate impact (DI, 1 indicates fairness) and equal opportunity difference (EOD, 0 indicates fairness). Results: Among 573 634 female individuals initially examined for this study, 314 903 were White (54.9%), 217 899 were Black (38.0%), and the mean (SD) age was 26.1 (5.5) years. The risk-adjusted odds ratio comparing White participants with Black participants was 2.06 (95% CI, 2.02-2.10) for clinically recognized PPD and 1.37 (95% CI, 1.33-1.40) for postpartum mental health service utilization. Taking the LR model for PPD prediction as an example, reweighing reduced bias as measured by improved DI and EOD metrics from 0.31 and -0.19 to 0.79 and 0.02, respectively. Removing race from the models had inferior performance for reducing bias compared with the other methods (PPD: DI = 0.61; EOD = -0.05; mental health service utilization: DI = 0.63; EOD = -0.04). Conclusions and Relevance: Clinical prediction models trained on potentially biased data may produce unfair outcomes on the basis of the chosen metrics. This study's results suggest that the performance varied depending on the model, outcome label, and method for reducing bias. This approach toward evaluating algorithmic bias can be used as an example for the growing number of researchers who wish to examine and address bias in their data and models.

Accuracy of an Artificial Intelligence System for Cancer Clinical Trial Eligibility Screening: Retrospective Pilot Study.

BACKGROUND: Screening patients for eligibility for clinical trials is labor intensive. It requires abstraction of data elements from multiple components of the longitudinal health record and matching them to inclusion and exclusion criteria for each trial. Artificial intelligence (AI) systems have been developed to improve the efficiency and accuracy of this process. OBJECTIVE: This study aims to evaluate the ability of an AI clinical decision support system (CDSS) to identify eligible patients for a set of clinical trials. METHODS: This study included the deidentified data from a cohort of patients with breast cancer seen at the medical oncology clinic of an academic medical center between May and July 2017 and assessed patient eligibility for 4 breast cancer clinical trials. CDSS eligibility screening performance was validated against manual screening. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value for eligibility determinations were calculated. Disagreements between manual screeners and the CDSS were examined to identify sources of discrepancies. Interrater reliability between manual reviewers was analyzed using Cohen (pairwise) and Fleiss (three-way) κ, and the significance of differences was determined by Wilcoxon signed-rank test. RESULTS: In total, 318 patients with breast cancer were included. Interrater reliability for manual screening ranged from 0.60-0.77, indicating substantial agreement. The overall accuracy of breast cancer trial eligibility determinations by the CDSS was 87.6%. CDSS sensitivity was 81.1% and specificity was 89%. CONCLUSIONS: The AI CDSS in this study demonstrated accuracy, sensitivity, and specificity of greater than 80% in determining the eligibility of patients for breast cancer clinical trials. CDSSs can accurately exclude ineligible patients for clinical trials and offer the potential to increase screening efficiency and accuracy. Additional research is needed to explore whether increased efficiency in screening and trial matching translates to improvements in trial enrollment, accruals, feasibility assessments, and cost.

Comparison of an oncology clinical decision-support system's recommendations with actual treatment decisions.

OBJECTIVE: IBM(R) Watson for Oncology (WfO) is a clinical decision-support system (CDSS) that provides evidence-informed therapeutic options to cancer-treating clinicians. A panel of experienced oncologists compared CDSS treatment options to treatment decisions made by clinicians to characterize the quality of CDSS therapeutic options and decisions made in practice. METHODS: This study included patients treated between 1/2017 and 7/2018 for breast, colon, lung, and rectal cancers at Bumrungrad International Hospital (BIH), Thailand. Treatments selected by clinicians were paired with therapeutic options presented by the CDSS and coded to mask the origin of options presented. The panel rated the acceptability of each treatment in the pair by consensus, with acceptability defined as compliant with BIH's institutional practices. Descriptive statistics characterized the study population and treatment-decision evaluations by cancer type and stage. RESULTS: Nearly 60% (187) of 313 treatment pairs for breast, lung, colon, and rectal cancers were identical or equally acceptable, with 70% (219) of WfO therapeutic options identical to, or acceptable alternatives to, BIH therapy. In 30% of cases (94), 1 or both treatment options were rated as unacceptable. Of 32 cases where both WfO and BIH options were acceptable, WfO was preferred in 18 cases and BIH in 14 cases. Colorectal cancers exhibited the highest proportion of identical or equally acceptable treatments; stage IV cancers demonstrated the lowest. CONCLUSION: This study demonstrates that a system designed in the US to support, rather than replace, cancer-treating clinicians provides therapeutic options which are generally consistent with recommendations from oncologists outside the US.