Uses and limitations of artificial intelligence for oncology.

Modern artificial intelligence (AI) tools built on high-dimensional patient data are reshaping oncology care, helping to improve goal-concordant care, decrease cancer mortality rates, and increase workflow efficiency and scope of care. However, data-related concerns and human biases that seep into algorithms during development and post-deployment phases affect performance in real-world settings, limiting the utility and safety of AI technology in oncology clinics. To this end, the authors review the current potential and limitations of predictive AI for cancer diagnosis and prognostication as well as of generative AI, specifically modern chatbots, which interfaces with patients and clinicians. They conclude the review with a discussion on ongoing challenges and regulatory opportunities in the field.

Racial Differences in Germline Genetic Testing Completion Among Males With Pancreatic, Breast, or Metastatic Prostate Cancers.

BACKGROUND: Germline genetic testing is a vital component of guideline-recommended cancer care for males with pancreatic, breast, or metastatic prostate cancers. We sought to determine whether there were racial disparities in germline genetic testing completion in this population. PATIENTS AND METHODS: This retrospective cohort study included non-Hispanic White and Black males with incident pancreatic, breast, or metastatic prostate cancers between January 1, 2019, and September 30, 2021. Two nationwide cohorts were examined: (1) commercially insured individuals in an administrative claims database, and (2) Veterans receiving care in the Veterans Health Administration. One-year germline genetic testing rates were estimated by using Kaplan-Meier methods. Cox proportional hazards regression was used to test the association between race and genetic testing completion. Causal mediation analyses were performed to investigate whether socioeconomic variables contributed to associations between race and germline testing. RESULTS: Our cohort consisted of 7,894 males (5,142 commercially insured; 2,752 Veterans). One-year testing rates were 18.0% (95% CI, 16.8%-19.2%) in commercially insured individuals and 14.2% (95% CI, 11.5%-15.0%) in Veterans. Black race was associated with a lower hazard of testing among commercially insured individuals (adjusted hazard ratio [aHR], 0.73; 95% CI, 0.58-0.91; P=.005) but not among Veterans (aHR, 0.99; 95% CI, 0.75-1.32; P=.960). In commercially insured individuals, income (aHR, 0.90; 95% CI, 0.86-0.96) and net worth (aHR, 0.92; 95% CI, 0.86-0.98) mediated racial disparities, whereas education (aHR, 0.98; 95% CI, 0.94-1.01) did not. CONCLUSIONS: Overall rates of guideline-recommended genetic testing are low in males with pancreatic, breast, or metastatic prostate cancers. Racial disparities in genetic testing among males exist in a commercially insured population, mediated by net worth and household income; these disparities are not seen in the equal-access Veterans Health Administration. Alleviating financial and access barriers may mitigate racial disparities in genetic testing.

Patient perspectives on treatment and prevention of recurrent urinary tract infections: a focus group study.

INTRODUCTION AND HYPOTHESIS: We sought to understand factors that are important to patients for the management of recurrent urinary tract infections (UTI) during both an acute episode and for the prevention of future episodes. METHODS: This was a qualitative study with focus groups in women with recurrent UTIs. Participants filled out information about prior recurrent UTI treatment and the Belief about Medicines Questionnaire (BMQ). Each 90-minute focus group was moderated by a nonphysician psychologist. Line-by-line coding of each transcript by three independent physicians was used to develop emergent concepts and themes using Grounded Theory methodology. RESULTS: Twenty-six women participated in six focus groups. The average age of participants was 62 years and 77% were post-menopausal. All women had already tried multiple prevention strategies for their recurrent UTIs. The average BMQ-specific scores indicated a net positive attitude toward medicines specifically prescribed for recurrent UTI prevention. Several themes emerged from the focus groups. First, patients wanted providers to acknowledge the high burden imposed by frequent interactions with the health care system for the management of recurrent UTI. Second, patients wanted earlier access to providers knowledgeable in the management of this condition. Third, patients wanted to self-manage their condition through a structured treatment plan with support from their providers. Finally, patients wanted greater emphasis on education and prevention strategies to reduce their antibiotic intake. CONCLUSIONS: Patients with recurrent UTI want more efficient workflows, a framework that promotes self-management in partnership with their providers, and a greater emphasis on prevention.

Association of Remote Patient-Reported Outcomes and Step Counts With Hospitalization or Death Among Patients With Advanced Cancer Undergoing Chemotherapy: Secondary Analysis of the PROStep Randomized Trial.

BACKGROUND: Patients with advanced cancer undergoing chemotherapy experience significant symptoms and declines in functional status, which are associated with poor outcomes. Remote monitoring of patient-reported outcomes (PROs; symptoms) and step counts (functional status) may proactively identify patients at risk of hospitalization or death. OBJECTIVE: The aim of this study is to evaluate the association of (1) longitudinal PROs with step counts and (2) PROs and step counts with hospitalization or death. METHODS: The PROStep randomized trial enrolled 108 patients with advanced gastrointestinal or lung cancers undergoing cytotoxic chemotherapy at a large academic cancer center. Patients were randomized to weekly text-based monitoring of 8 PROs plus continuous step count monitoring via Fitbit (Google) versus usual care. This preplanned secondary analysis included 57 of 75 patients randomized to the intervention who had PRO and step count data. We analyzed the associations between PROs and mean daily step counts and the associations of PROs and step counts with the composite outcome of hospitalization or death using bootstrapped generalized linear models to account for longitudinal data. RESULTS: Among 57 patients, the mean age was 57 (SD 10.9) years, 24 (42%) were female, 43 (75%) had advanced gastrointestinal cancer, 14 (25%) had advanced lung cancer, and 25 (44%) were hospitalized or died during follow-up. A 1-point weekly increase (on a 32-point scale) in aggregate PRO score was associated with 247 fewer mean daily steps (95% CI -277 to -213; P<.001). PROs most strongly associated with step count decline were patient-reported activity (daily step change -892), nausea score (-677), and constipation score (524). A 1-point weekly increase in aggregate PRO score was associated with 20% greater odds of hospitalization or death (adjusted odds ratio [aOR] 1.2, 95% CI 1.1-1.4; P=.01). PROs most strongly associated with hospitalization or death were pain (aOR 3.2, 95% CI 1.6-6.5; P<.001), decreased activity (aOR 3.2, 95% CI 1.4-7.1; P=.01), dyspnea (aOR 2.6, 95% CI 1.2-5.5; P=.02), and sadness (aOR 2.1, 95% CI 1.1-4.3; P=.03). A decrease in 1000 steps was associated with 16% greater odds of hospitalization or death (aOR 1.2, 95% CI 1.0-1.3; P=.03). Compared with baseline, mean daily step count decreased 7% (n=274 steps), 9% (n=351 steps), and 16% (n=667 steps) in the 3, 2, and 1 weeks before hospitalization or death, respectively. CONCLUSIONS: In this secondary analysis of a randomized trial among patients with advanced cancer, higher symptom burden and decreased step count were independently associated with and predictably worsened close to hospitalization or death. Future interventions should leverage longitudinal PRO and step count data to target interventions toward patients at risk for poor outcomes. TRIAL REGISTRATION: ClinicalTrials.gov NCT04616768; https://clinicaltrials.gov/study/NCT04616768. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1136/bmjopen-2021-054675.

Oncologist Participation and Performance in the Merit-Based Incentive Payment System.

The merit-based incentive payment system (MIPS) is a value-based payment model created by the Centers for Medicare & Medicaid Services (CMS) to promote high-value care through performance-based adjustments of Medicare reimbursements. In this cross-sectional study, we examined the participation and performance of oncologists in the 2019 MIPS. Oncologist participation was low (86%) compared to all-specialty participation (97%). After adjusting for practice characteristics, higher MIPS scores were observed among oncologists with alternative payment models (APMs) as their filing source (mean score, 91 for APMs vs. 77.6 for individuals; difference, 13.41 [95% CI, 12.21, 14.6]), indicating the importance of greater organizational resources for participants. Lower scores were associated with greater patient complexity (mean score, 83.4 for highest quintile vs. 84.9 for lowest quintile, difference, -1.43 [95% CI, -2.48, -0.37]), suggesting the need for better risk-adjustment by CMS. Our findings may guide future efforts to improve oncologist engagement in MIPS.

Time of Clinic Appointment and Serious Illness Communication in Oncology.

INTRODUCTION: Serious illness communication in oncology increases goal concordant care. Factors associated with the frequency of serious illness conversations are not well understood. Given prior evidence of the association between suboptimal decision-making and clinic time, we aimed to investigate the relationship between appointment time and the likelihood of serious illness conversations in oncology. METHODS: We conducted a retrospective study of electronic health record data from 55 367 patient encounters between June 2019 to April 2020, using generalized estimating equations to model the likelihood of a serious illness conversation across clinic time. RESULTS: Documentation rate decreased from 2.1 to 1.5% in the morning clinic session (8am-12pm) and from 1.2% to .9% in the afternoon clinic session (1pm-4pm). Adjusted odds ratios for Serious illness conversations documentation rates were significantly lower for all hours of each session after the earliest hour (adjusted odds ratios .91 [95% CI, .84-.97], P = .006 for overall linear trend). CONCLUSIONS: Serious illness conversations between oncologists and patients decrease considerably through the clinic day, and proactive strategies to avoid missed conversations should be investigated.

Clinician perspectives on machine learning prognostic algorithms in the routine care of patients with cancer: a qualitative study.

PURPOSE: Oncologists may overestimate prognosis for patients with cancer, leading to delayed or missed conversations about patients' goals and subsequent low-quality end-of-life care. Machine learning algorithms may accurately predict mortality risk in cancer, but it is unclear how oncology clinicians would use such algorithms in practice. METHODS: The purpose of this qualitative study was to assess oncology clinicians' perceptions on the utility and barriers of machine learning prognostic algorithms to prompt advance care planning. Participants included medical oncology physicians and advanced practice providers (APPs) practicing in tertiary and community practices within a large academic healthcare system. Transcripts were coded and analyzed inductively using NVivo software. RESULTS: The study included 29 oncology clinicians (19 physicians, 10 APPs) across 6 practice sites (1 tertiary, 5 community) in the USA. Fourteen participants had previously had exposure to an automated machine learning-based prognostic algorithm as part of a pragmatic randomized trial. Clinicians believed that there was utility for algorithms in validating their own intuition about prognosis and prompting conversations about patient goals and preferences. However, this enthusiasm was tempered by concerns about algorithm accuracy, over-reliance on algorithm predictions, and the ethical implications around disclosure of an algorithm prediction. There was significant variation in tolerance for false positive vs. false negative predictions. CONCLUSION: While oncologists believe there are applications for advanced prognostic algorithms in routine care of patients with cancer, they are concerned about algorithm accuracy, confirmation and automation biases, and ethical issues of prognostic disclosure.

Long-term depression incidence and associated mortality among African American and White prostate cancer survivors.

BACKGROUND: Depression is common after a diagnosis of prostate cancer and may contribute to poor outcomes, particularly among African Americans. The authors assessed the incidence and management of depression and its impact on overall mortality among African American and White veterans with localized prostate cancer. METHODS: The authors used the Veterans Health Administration Corporate Data Warehouse to identify 40,412 African American and non-Hispanic White men diagnosed with localized prostate cancer from 2001 to 2013. Patients were followed through 2019. Multivariable logistic regression was used to measure associations between race and incident depression, which were ascertained from administrative and depression screening data. Cox proportional hazards models were used to measure associations between incident depression and all-cause mortality, with race-by-depression interactions used to assess disparities. RESULTS: Overall, 10,013 veterans (24.5%) were diagnosed with depression after a diagnosis of prostate cancer. Incident depression was associated with higher all-cause mortality (adjusted hazard ratio [aHR], 1.27; 95% confidence interval [CI], 1.23-1.32). African American veterans were more likely than White veterans to be diagnosed with depression (29.3% vs 23.2%; adjusted odds ratio [aOR], 1.15; 95% CI, 1.09-1.21). Among those with depression, African Americans were less likely to be prescribed an antidepressant (30.4% vs 31.7%; aOR, 0.85; 95% CI, 0.77-0.93). The hazard of all-cause mortality associated with depression was greater for African American veterans than White veterans (aHR, 1.32 [95% CI, 1.26-1.38] vs 1.15 [95% CI, 1.07-1.24]; race-by-depression interaction P < .001). CONCLUSIONS: Incident depression is common among prostate cancer survivors and is associated with higher mortality, particularly among African American men. Patient-centered strategies to manage incident depression may be critical to reducing disparities in prostate cancer outcomes.

Artificial Intelligence and Liability in Medicine: Balancing Safety and Innovation.

Policy Points With increasing integration of artificial intelligence and machine learning in medicine, there are concerns that algorithm inaccuracy could lead to patient injury and medical liability. While prior work has focused on medical malpractice, the artificial intelligence ecosystem consists of multiple stakeholders beyond clinicians. Current liability frameworks are inadequate to encourage both safe clinical implementation and disruptive innovation of artificial intelligence. Several policy options could ensure a more balanced liability system, including altering the standard of care, insurance, indemnification, special/no-fault adjudication systems, and regulation. Such liability frameworks could facilitate safe and expedient implementation of artificial intelligence and machine learning in clinical care.

First-line immune checkpoint inhibitor use in cisplatin-eligible patients with advanced urothelial carcinoma: a secular trend analysis.

Aim: Standard first-line treatment of advanced urothelial cell carcinoma involves cisplatin-based chemotherapy, with carboplatin or immune checkpoint inhibitor therapy (ICI) reserved for cisplatin-ineligible individuals. Methods: Using a large de-identified electronic health record-derived database of patients with advanced urothelial cell carcinoma in the USA, we examined trends in utilization of first-line systemic therapies in cisplatin-eligible patients from 1 January 2015 to 31 March 2018. Results: Among 1181 cisplatin-eligible patients, the quarterly proportion who received first-line ICI increased from 1 to 42% (ptrend <0.001), while the proportion who received cisplatin-based chemotherapy decreased from 53 to 33% (ptrend = 0.018). Patients receiving ICI were older than those receiving cisplatin (median age: 75 vs 68). Conclusion: Our analysis suggests rising off-label ICI use in cisplatin-eligible individuals, potentially because of ICI's favorable toxicity profile.

Trends in Checkpoint Inhibitor Therapy for Advanced Urothelial Cell Carcinoma at the End of Life: Insights from Real-World Practice.

Several immune checkpoint inhibitor therapies (CPIs) have been approved to treat metastatic urothelial cell carcinoma (mUC). Because of the favorable toxicity profile of CPI compared with chemotherapy, oncologists may have a low threshold to prescribe CPI to patients near the end of life. We evaluated trends in initiation of end-of-life systemic therapy in 1,637 individuals in the Flatiron Health Database who were diagnosed with mUC between 2015 and 2017 and who died. Rates of systemic therapy initiation in the last 30 and 60 days of life were 17.0% and 29.8%, respectively. The quarterly proportion of patients who initiated CPI within 60 days of death increased from 1.0% to 23% during the study period (p trend < .001). After CPI approval, end-of-life CPI initiation significantly increased among patients with poor performance status (p trend = .020) and did not significantly change among individuals with good performance status. The quarterly proportion of patients who initiated any systemic therapy at the end of life doubled (17.4% to 34.8%) during the study period, largely explained by increased CPI use. These findings suggest a dramatic rise in CPI use at the end of life in patients with mUC, a finding that may have important guideline and policy implications.

Real-world evaluation of deep learning algorithms to classify functional pathogenic germline variants.

Deep learning models for variant pathogenicity prediction can recapitulate expert-curated annotations, but their performance remains unexplored on actual disease phenotypes in a real-world setting. Here, we apply three state-of-the-art pathogenicity prediction models to classify hereditary breast cancer gene variants in the UK Biobank. Predicted pathogenic variants in BRCA1, BRCA2 and PALB2, but not ATM and CHEK2, were associated with increased breast cancer risk. We explored gene-specific score thresholds for variant pathogenicity, finding that they could improve model performance. However, when specifically tasked with classifying variants of uncertain significance, the deep learning models were generally of limited clinical utility.

Real-world use, dose intensity, and adherence to enfortumab vedotin in locally advanced or metastatic urothelial cancer.

BACKGROUND: Enfortumab vedotin (EV) monotherapy is approved for the treatment of advanced urothelial cancer as later-line therapy (post-immunotherapy and -platinum-chemotherapy) and as earlier-line therapy (cisplatin-ineligible, at least 1 prior therapy). We examined real-world EV monotherapy use, dose intensity and adherence across 280 US cancer clinics. METHODS: This postmarketing study used data from a nationwide (United States) deidentified patient-level electronic health record-derived database. Included were patients with advanced urothelial cancer initiating EV on or after December 19, 2019 (date of accelerated approval). We summarized characteristics of EV users using descriptive statistics and computed metrics of EV use, EV dose intensity, and EV treatment adherence. RESULTS: We identified 416 advanced urothelial cancer patients initiating EV monotherapy. More than half of patients (55.3%) received EV as later-line therapy (3L+), and nearly half (44.7%) received EV as earlier line therapy (1 or 2L). Dosing frequency (mean [SD] 2.4 [0.5] treatments per 28 day cycle) and dose (1.1 [0.2] mg/kg) were lower than label indication guidelines (1.25 mg/kg, Day 1, 8, 15 of a 28 day cycle). Only 58.8% of patients received an average of >2 treatments per 28-day cycle. CONCLUSIONS: Among patients with advanced urothelial cancer treated with EV monotherapy in contemporary practice, EV dosing frequency, and dosage was lower in clinical practice than recommended in the product labeling. Further research is required to understand clinical factors and outcomes associated with the differences observed.

The COVID-19 Pandemic Led To A Large Decline In Physician Gross Revenue Across All Specialties In 2020.

US health care use declined during the initial phase of the COVID-19 pandemic in 2020. Although utilization is known to have recovered in 2021 and 2022, it is unknown how revenue in 2020-22 varied by physician specialty and practice setting. This study linked medical claims from a large national federation of commercial health plans to physician and practice data to estimate pandemic-associated impacts on physician revenue (defined as payments to eligible physicians) by specialty and practice characteristics. Surgical specialties, emergency medicine, and medical subspecialties each experienced a greater than 9 percent adjusted gross revenue decline in 2020 relative to prepandemic baselines. By 2022, pathology and psychiatry revenue experienced robust recovery, whereas surgical and oncology revenue remained at or below baseline. Revenue recovery in 2022 was greater for physicians practicing in hospital-owned practices and in practices participating in accountable care organizations. Pandemic-associated revenue recovery in 2021 and 2022 varied by specialty and practice type. Given that physician financial instability is associated with health care consolidation and leaving practice, policy makers should closely monitor revenue trends among physicians in specialties or practice settings with sustained gross revenue reductions during the pandemic.

Clinician Perspectives on Virtual Specialty Palliative Care for Patients With Advanced Illnesses.

Background: Patients with serious illnesses have unmet symptom and psychosocial needs. Specialty palliative care could address many of these needs; however, access varies by geography and health system. Virtual visits and automated referrals could increase access and lead to improved quality of life, health outcomes, and patient-centered care for patients with serious illness. Objectives: We sought to understand referring clinician perspectives on barriers and facilitators to utilizing virtual tools to increase upstream access to palliative care. Design: Participants in this multisite qualitative study included practicing clinicians who commonly place palliative care referrals across multiple specialties, including hematology/oncology, family medicine, cardiology, and geriatrics. All interviews were transcribed and subsequently coded and analyzed by trained research coordinators using Atlas.ti software. Settings/Subjects: This study included 23 clinicians (21 physicians, 2 nonphysicians) across 5 specialties, 4 practice settings, and 7 states in the United States. Results: Respondents felt that community-based specialty palliative services including symptom management, advance care planning, physical therapy, and mental health counseling would benefit their patients. However, they had mixed feelings about automated referrals, with some clinicians feeling hesitant about not being alerted to such referrals. Many respondents were supportive of virtual palliative care, particularly for those who may have difficulty accessing physician offices, but most respondents felt that such care should only be provided after an initial in-person consultation where clinicians can meet face-to-face with patients. Conclusion: Clinicians believe that automated referrals and virtual palliative care could increase access to the benefits of specialty palliative care. However, virtual palliative care models should give attention to iterative communication with primary clinicians and the perceived need for an initial in-person visit.

Trends in low-value cancer care during the COVID-19 pandemic.

OBJECTIVE: To assess the association between the onset of the COVID-19 pandemic and change in low-value cancer services. STUDY DESIGN: In this retrospective cohort study, we used administrative claims from the HealthCore Integrated Research Environment, a repository of medical and pharmacy data from US health plans representing more than 80 million members, between January 1, 2016, and March 31, 2021. METHODS: We used linear probability models to investigate the relation between the onset of the COVID-19 pandemic and 4 guideline-based metrics of low-value cancer care: (1) conventional fractionation radiotherapy instead of hypofractionated radiotherapy for early-stage breast cancer; (2) non-guideline-based antiemetic use for minimal-, low-, or moderate- to high-risk chemotherapies; (3) off-pathway systemic therapy; and (4) aggressive end-of-life care. We identified patients with new diagnoses of breast, colorectal, and/or lung cancer. We excluded members who did not have at least 6 months of continuous insurance coverage and members with prevalent cancers. RESULTS: Among 117,116 members (median [IQR] age, 60 [53-69] years; 72.4% women), 59,729 (51.0%) had breast cancer, 25,751 (22.0%) had colorectal cancer, and 31,862 (27.2%) had lung cancer. The payer mix was 18.7% Medicare Advantage or Medicare supplemental and 81.2% commercial non-Medicare. Rates of low-value cancer services exhibited minimal changes during the pandemic, as adjusted percentage-point differences were 3.93 (95% CI, 1.50-6.36) for conventional radiotherapy, 0.82 (95% CI, -0.62 to 2.25) for off-pathway systemic therapy, -3.62 (95% CI, -4.97 to -2.27) for non-guideline-based antiemetics, and 2.71 (95% CI, -0.59 to 6.02) for aggressive end-of-life care. CONCLUSIONS: Low-value cancer care remained prevalent throughout the pandemic. Policy makers should consider changes to payment and incentive design to turn the tide against low-value cancer care.