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.

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.

Let Us Have the Conversation: Serious Illness Communication in Oncology: Definitions, Barriers, and Successful Approaches.

Serious illness communications are crucial elements of care delivery for patients with cancer. High-quality serious illness communications are composed of open, honest discussions between patients, caregivers, and clinicians regarding patient's communication preferences, expected illness trajectory, prognosis, and risks and benefits of any recommended care. High-quality communication ideally starts at the time of a patients' cancer diagnosis, allows space for and response to patient emotions, elicits patients' values and care preferences, and is iterative and longitudinal. When integrated into cancer care, such communication can result in improved patient experiences with their care, care that matches patients' goals, and reduced care intensity at the end of life. Despite national recommendations for routine integration of these communication into cancer care, a minority of patients with cancer receive such communication. In this chapter, we describe elements of high-quality serious illness communication, patient-, clinician-, institution-, and payer-level barriers, and successful strategies that can routinely integrate such communication into cancer care delivery.

Cancer Screening Rates and Outcomes for Justice-Involved Individuals: A Scoping Review.

Individuals who have been incarcerated or under community supervision have elevated cancer mortality. This review summarizes existing knowledge on implementation and outcomes of cancer screening for justice-involved individuals to identify opportunities for reducing cancer disparities. This scoping review identified 16 studies published between January 1990 and June 2021 that reported cancer screening rates and outcomes in U.S. jails or prisons or for individuals under community supervision. Most studies evaluated cervical cancer screening, while fewer studies evaluated screening for breast, colon, prostate, lung, and hepatocellular cancers. Although incarcerated women are often up to date with cervical cancer screening, only about half had recent mammograms and only 20% of male patients were up to date with colorectal cancer screening. Justice-involved patients are at high risk of cancer, yet few studies have evaluated cancer screening for these populations and screening rates for many cancers appear low. The findings suggest that intensification of cancer screening for justice-involved populations may address cancer disparities.

Creating a culture for change: Lessons from behavioral economics and complexity science to increase serious illness conversations for patients with cancer.

Patient-centered cancer care requires communication between patients and clinicians about patients' goals, values, and preferences. Serious illness communication improves patient and caregiver outcomes, the value and quality of cancer care, and the well-being of clinicians. Despite these benefits, there are competing factors including time, capacity, bandwidth, and resistance. Health systems and oncology practices have opportunities to invest in pathways that assist patients and clinicians to engage in serious illness conversations. We discuss how applying insights from behavioral economics and complexity science may help clinicians engage in serious illness conversation and improve patient-centered cancer care.

Remote Patient-Reported Outcomes and Activity Monitoring to Improve Patient-Clinician Communication Regarding Symptoms and Functional Status: A Randomized Controlled Trial.

PURPOSE: Routine collection of patient-generated health data (PGHD) may promote earlier recognition of symptomatic and functional decline. This trial assessed the impact of an intervention integrating remote PGHD collection with patient nudges on symptom and functional status understanding between patients with advanced cancer and their oncology team. METHODS: This three-arm randomized controlled trial was conducted from November 19, 2020, to December 17, 2021, at a large tertiary oncology practice. We enrolled patients with stage IV GI and lung cancers undergoing chemotherapy. Over 6 months, patients in two intervention arms received PROStep-weekly text message-based symptom surveys and passive activity monitoring using a wearable accelerometer. PGHD were summarized in dashboards given to patients' oncology team before appointments. One intervention arm received an additional text-based active choice prompt to discuss worsening symptoms or functional status with their clinician. Control patients did not receive PROStep. The coprimary outcomes patient perceptions of oncology team symptom and functional understanding at 6 months were measured on a 1-5 Likert scale (5 = high understanding). RESULTS: One hundred eight patients enrolled: 55% male, 81% White, and 77% had GI cancers. Patient-reported clinician understanding did not differ between control and intervention arms for symptoms (4.5 v 4.5; P = .87) or functional status (4.5 v 4.3; P = .31). In the intervention arms, combined patient adherence to weekly symptom reports and daily activity monitoring was 64% and 53%, respectively. Intervention patients in the PROStep versus PROStep + active choice arms reported low burden from wearing the accelerometer (mean burden [standard deviation], 2.7 [1.3] v 2.1 [1.3]; P = .15) and completing surveys (2.1 [1.2] v 1.9 [1.3]; P = .44). CONCLUSION: Patients receiving PROStep reported high understanding of symptoms and functional status from their oncology team, although this did not differ from controls.

Long-term Effect of Machine Learning-Triggered Behavioral Nudges on Serious Illness Conversations and End-of-Life Outcomes Among Patients With Cancer: A Randomized Clinical Trial.

Importance: Serious illness conversations (SICs) between oncology clinicians and patients are associated with improved quality of life and may reduce aggressive end-of-life care. However, most patients with cancer die without a documented SIC. Objective: To test the impact of behavioral nudges to clinicians to prompt SICs on the SIC rate and end-of-life outcomes among patients at high risk of death within 180 days (high-risk patients) as identified by a machine learning algorithm. Design, Setting, and Participants: This prespecified 40-week analysis of a stepped-wedge randomized clinical trial conducted between June 17, 2019, and April 20, 2020 (including 16 weeks of intervention rollout and 24 weeks of follow-up), included 20 506 patients with cancer representing 41 021 encounters at 9 tertiary or community-based medical oncology clinics in a large academic health system. The current analyses were conducted from June 1, 2021, to May 31, 2022. Intervention: High-risk patients were identified using a validated electronic health record machine learning algorithm to predict 6-month mortality. The intervention consisted of (1) weekly emails to clinicians comparing their SIC rates for all patients against peers' rates, (2) weekly lists of high-risk patients, and (3) opt-out text messages to prompt SICs before encounters with high-risk patients. Main Outcomes and Measures: The primary outcome was SIC rates for all and high-risk patient encounters; secondary end-of-life outcomes among decedents included inpatient death, hospice enrollment and length of stay, and intensive care unit admission and systemic therapy close to death. Intention-to-treat analyses were adjusted for clinic and wedge fixed effects and clustered at the oncologist level. Results: The study included 20 506 patients (mean [SD] age, 60.0 [14.0] years) and 41 021 patient encounters: 22 259 (54%) encounters with female patients, 28 907 (70.5%) with non-Hispanic White patients, and 5520 (13.5%) with high-risk patients; 1417 patients (6.9%) died by the end of follow-up. There were no meaningful differences in demographic characteristics in the control and intervention periods. Among high-risk patient encounters, the unadjusted SIC rates were 3.4% (59 of 1754 encounters) in the control period and 13.5% (510 of 3765 encounters) in the intervention period. In adjusted analyses, the intervention was associated with increased SICs for all patients (adjusted odds ratio, 2.09 [95% CI, 1.53-2.87]; P < .001) and decreased end-of-life systemic therapy (7.5% [72 of 957 patients] vs 10.4% [24 of 231 patients]; adjusted odds ratio, 0.25 [95% CI, 0.11-0.57]; P = .001) relative to controls, but there was no effect on hospice enrollment or length of stay, inpatient death, or end-of-life ICU use. Conclusions and Relevance: In this randomized clinical trial, a machine learning-based behavioral intervention and behavioral nudges to clinicans led to an increase in SICs and reduction in end-of-life systemic therapy but no changes in other end-of-life outcomes among outpatients with cancer. These results suggest that machine learning and behavioral nudges can lead to long-lasting improvements in cancer care delivery. Trial Registration: ClinicalTrials.gov Identifier: NCT03984773.

Association of Oncologist Participation in Medicare's Oncology Care Model With Patient Receipt of Novel Cancer Therapies.

Importance: Medicare's Oncology Care Model (OCM) was an alternative payment model that tied performance-based payments to cost and quality goals for participating oncology practices. A major concern about the OCM regarded inclusion of high-cost cancer therapies, which could potentially disincentivize oncologists from prescribing novel therapies. Objective: To examine whether oncologist participation in the OCM changed the likelihood that patients received novel therapies vs alternative treatments. Design, Setting, and Participants: This cohort study of Surveillance, Epidemiology, and End Results (SEER) Program data and Medicare claims compared patient receipt of novel therapies for patients treated by oncologists participating vs not participating in the OCM in the period before (January 2015-June 2016) and after (July 2016-December 2018) OCM initiation. Participants included Medicare fee-for-service beneficiaries in SEER registries who were eligible to receive 1 of 10 novel cancer therapies that received US Food and Drug Administration approval in the 18 months before implementation of the OCM. The study excluded the Hawaii registry because complete data were not available at the time of the data request. Patients in the OCM vs non-OCM groups were matched on novel therapy cohort, outcome time period, and oncologist specialist status. Analysis was conducted between July 2021 and April 2022. Exposures: Oncologist participation in the OCM. Main Outcomes and Measures: Preplanned analyses evaluated patient receipt of 1 of 10 novel therapies vs alternative therapies specific to the patient's cancer for the overall study sample and for racial subgroups. Results: The study included 2839 matched patients (760 in the OCM group and 2079 in the non-OCM group; median [IQR] age, 72.7 [68.3-77.6] years; 1591 women [56.0%]). Among patients in the non-OCM group, 33.2% received novel therapies before and 40.1% received novel therapies after the start of the OCM vs 39.9% and 50.3% of patients in the OCM group (adjusted difference-in-differences, 3.5 percentage points; 95% CI, -3.7 to 10.7 percentage points; P = .34). In subgroup analyses, second-line immunotherapy use in lung cancer was greater among patients in the OCM group vs non-OCM group (adjusted difference-in-differences, 17.4 percentage points; 95% CI, 4.8-30.0 percentage points; P = .007), but no differences were seen in other subgroups. Over the entire study period, patients with oncologists participating in the OCM were more likely to receive novel therapies than those with oncologists who were not participating (odds ratio, 1.47; 95% CI, 1.09-1.97; P = .01). Conclusions and Relevance: This study found that participation in the OCM was not associated with oncologists' prescribing novel therapies to Medicare beneficiaries with cancer. These findings suggest that OCM financial incentives did not decrease patient access to novel therapies.

Oncologist Perceptions of Algorithm-Based Nudges to Prompt Early Serious Illness Communication: A Qualitative Study.

Background: Early serious illness conversations (SICs) about goals of care and prognosis improve mood, quality of life, and end-of-life care quality. Algorithm-based behavioral nudges to oncologists increase the frequency and timeliness of such conversations. However, clinicians' perspectives on such nudges are unknown. Design: Qualitative study consisting of semistructured interviews among medical oncology clinicians who participated in a stepped-wedge cluster randomized trial of Conversation Connect, an algorithm-based intervention consisting of behavioral nudges to promote early SICs in the outpatient oncology setting. Results: Of 79 eligible oncology clinicians, 56 (71%) were approached to participate in interviews and 25 (45%) accepted. Key facilitators to algorithm-based nudges included prompting documentation of conversations, peer comparisons, performance reports, and validating norms around early conversations. Barriers included cancer-specific heterogeneity in algorithm performance and the frequency and tone of text messages. Areas of improvement included utilizing different information channels, identifying patients earlier in the disease trajectory, and incorporating patient-targeted messaging that emphasizes the value of early conversations. Conclusions: Oncology clinicians identified key facilitators and barriers to Conversation Connect. These insights inform future algorithm-based supportive care interventions in oncology. Controlled trial (NCT03984773).

Patient and clinician nudges to improve symptom management in advanced cancer using patient-generated health data: study protocol for the PROStep randomised controlled trial.

INTRODUCTION: Patients with advanced cancers often face significant symptoms from their cancer and adverse effects from cancer-associated therapy. Patient-generated health data (PGHD) are routinely collected information about symptoms and activity levels that patients either directly report or passively record using devices such as wearable accelerometers. The objective of this study was to test the impact of an intervention integrating remote collection of PGHD with clinician and patient nudges to inform communication between patients with advanced cancer and their oncology team regarding symptom burden and functional status. METHODS AND ANALYSIS: This single-centre prospective randomised controlled trial randomises patients with metastatic gastrointestinal or lung cancers into one of three arms: (A) usual care, (B) an intervention that integrates PGHD (including weekly text-based symptom surveys and passively recorded step counts) into a dashboard delivered to oncology clinicians at each visit and (C) the same intervention as arm B but with an additional text-based active choice intervention to patients to encourage discussing their symptoms with their oncology team. The study will enrol approximately 125 participants. The coprimary outcomes are patient perceptions of their oncology team's understanding of their symptoms and their functional status. Secondary outcomes are intervention utility and adherence. ETHICS AND DISSEMINATION: This study has been approved by the institutional review board at the University of Pennsylvania. Study results will be disseminated using methods that describe the results in ways that key stakeholders can best understand and implement. TRIAL REGISTRATION NUMBERS: NCT04616768 and 843 616.

Impact of Behavioral Nudges on the Quality of Serious Illness Conversations Among Patients With Cancer: Secondary Analysis of a Randomized Controlled Trial.

PURPOSE: Serious Illness Conversations (SICs) are structured conversations between clinicians and patients about prognosis, treatment goals, and end-of-life preferences. Although behavioral interventions may prompt earlier or more frequent SICs, their impact on the quality of SICs is unclear. METHODS: This was a secondary analysis of a randomized clinical trial (NCT03984773) among 78 clinicians and 14,607 patients with cancer testing the impact of an automated mortality prediction with behavioral nudges to clinicians to prompt more SICs. We analyzed 318 randomly selected SICs matched 1:1 by clinicians (159 control and 159 intervention) to compare the quality of intervention vs. control conversations using a validated codebook. Comprehensiveness of SIC documentation was used as a measure of quality, with higher integer numbers of documented conversation domains corresponding to higher quality conversations. A conversation was classified as high-quality if its score was ≥ 8 of a maximum of 10. Using a noninferiority design, mixed effects regression models with clinician-level random effects were used to assess SIC quality in intervention vs. control groups, concluding noninferiority if the adjusted odds ratio (aOR) was not significantly < 0.9. RESULTS: Baseline characteristics of the control and intervention groups were similar. Intervention SICs were noninferior to control conversations (aOR 0.99; 95% CI, 0.91 to 1.09). The intervention increased the likelihood of addressing patient-clinician relationship (aOR = 1.99; 95% CI, 1.23 to 3.27; P < .01) and decreased the likelihood of addressing family involvement (aOR = 0.56; 95% CI, 0.34 to 0.90; P < .05). CONCLUSION: A behavioral intervention that increased SIC frequency did not decrease their quality. Behavioral prompts may increase SIC frequency without sacrificing quality.

Disparities in cancer prevalence, incidence, and mortality for incarcerated and formerly incarcerated patients: A scoping review.

BACKGROUND: Racial and ethnic minority status, structural racism, low educational attainment, and poverty are consistently associated with cancer disparities and with higher rates of incarceration. The objective of this scoping review is to conduct a qualitative synthesis of the literature on cancer prevalence, incidence, mortality, and disparities in these outcomes for incarcerated and formerly incarcerated patients, as this literature is fragmented and heterogenous. METHODS: This scoping review included Bureau of Justice Statistics reports and searched PubMed in May 2021 for all English language studies published between 1990 and 30 April 2021, that reported on cancer prevalence, incidence, or mortality for incarcerated or formerly incarcerated individuals in the United States. RESULTS: Twenty studies were selected. Data on cancer prevalence and incidence were scarce but suggested that incarcerated and formerly incarcerated patients have a similar overall risk of cancer diagnosis as the general population, but elevated risk of certain cancers such as cervical, lung, colorectal, and hepatocellular carcinoma for which effective prevention and screening interventions exist. Cancer mortality data in state and local jails as well as prisons were robust and suggests that both incarcerated and formerly incarcerated patients have higher cancer mortality than the general population. CONCLUSIONS: Incarcerated and formerly incarcerated patients likely have a higher risk of dying from cancer than the general population, but important gaps in our knowledge about the extent and drivers of disparities for this population remain. Additional research is needed to guide interventions to reduce cancer disparities for patients experiencing incarceration.

Treatment utilization patterns of newly initiated oral anticancer agents in a national sample of Medicare beneficiaries.

BACKGROUND: Few studies have examined oral anticancer treatment utilization patterns among Medicare beneficiaries. OBJECTIVE: To assess treatment utilization patterns of newly initiated oral anticancer agents across national samples of Medicare beneficiaries for 5 cancer types: chronic myeloid leukemia (CML), multiple myeloma (MM), metastatic prostate cancer (mPC), metastatic renal cell carcinoma (mRCC), and metastatic breast cancer (mBC). METHODS: This retrospective claims analysis used 100% Medicare Chronic Condition Data Warehouse (CCW) Parts A, B, and D files from 2011 to 2014 (for CML, MM, mPC, and mRCC patients) and a 5% random fee-for-service sample from 2011 to 2013 (for mBC patients). Outcomes of interest were the number of 30-day supply prescriptions, adherence, and discontinuation of newly initiated (ie, index) oral anticancer agents indicated for each of the cancers. Adherence was calculated with both the "traditional" proportion of days covered (PDC) approach, measured over a fixed 1-year period or until hospice/death, and a "modified" PDC approach, measured over the time between the first and last fill of the index oral anticancer agent. Patients with PDC of at least 0.80 were deemed as being adherent. Discontinuation was defined as the presence of a continuous 90-day gap in the availability of days supply of the index oral anticancer agent. RESULTS: Our study included 1,650, 7,461, 6,998, 2,553, and 79 patients for CML, MM, mPC, mRCC, and mBC, respectively. Patients with mRCC had the highest proportion of patients with only 1 fill of their index anticancer agent (28%) followed by mBC (17%), MM (17%), mPC (12%), and CML (12%). Patients with CML had the highest mean (SD) number of 30-day supply equivalent prescriptions (8.3 [4.6]), followed by patients with mPC (6.5 [4.2]), MM (5.7 [4.1]), mBC (4.7 [3.2]), and mRCC (4.5 [3.9]). Using the modified PDC measured between the first and last fills, approximately three-quarters of patients with CML (74%), mRCC (71%), and mBC (70%) were adherent to the index oral anticancer agent. Adherence was highest for patients with mPC (87%) and lowest for patients with MM (58%). The percentage of patients defined as adherent to the index oral anticancer agent decreased for all cancers when using the traditional PDC measure over a fixed 1-year period: CML (54%), MM (35%), mPC (48%), mRCC (37%), and mBC (22%). Rates of discontinuation for patients in our sample were 32% (CML), 38% (mPC), 42% (mRCC), 48% (MM), and 58% (mBC). CONCLUSIONS: Between 13% and 42% of Medicare patients were nonadherent between the first and last fill of their newly initiated oral anticancer therapies across a range of cancers. This study provides a valuable benchmark for stakeholders seeking to measure and improve adherence to oral anticancer agents in Medicare patients. DISCLOSURES: This study was supported by Humana, Inc. (Louisville, KY). The sponsor played a role in the development of the study protocol, interpretation of results, and revisions of the manuscript. The sponsor was not involved in data analysis. Brown is employed by Humana, Inc., and Ward was employed by Humana, Inc., from research inception through initial drafts. Doshi has served as an advisory board member or consultant for Allergan, Ironwood Pharmaceuticals, Janssen, Kite Pharma, Merck, Otsuka, Regeneron, Sarepta, Sage Therapeutics, Sanofi, and Vertex and has received research funding from AbbVie, Biogen, Humana, Janssen, Novartis, PhRMA, Regeneron, Sanofi, and Valeant. Her spouse holds stock in Merck and Pfizer. All other authors have no financial conflicts of interest to report.

Automated Text-Based Symptom Monitoring With Rapid Clinician Triage for Patients With Cancer and Suspected or Confirmed COVID-19.

PURPOSE: Patients with cancer are at greater risk of developing severe symptoms from COVID-19 than the general population. We developed and tested an automated text-based remote symptom-monitoring program to facilitate early detection of worsening symptoms and rapid assessment for patients with cancer and suspected or confirmed COVID-19. METHODS: We conducted a feasibility study of Cancer COVID Watch, an automated COVID-19 symptom-monitoring program with oncology nurse practitioner (NP)-led triage among patients with cancer between April 23 and June 30, 2020. Twenty-six patients with cancer and suspected or confirmed COVID-19 were enrolled. Enrolled patients received twice daily automated text messages over 14 days that asked "How are you feeling compared to 12 hours ago? Better, worse, or the same?" and, if worse, "Is it harder than usual for you to breathe?" Patients who responded worse and yes were contacted within 1 hour by an oncology NP. RESULTS: Mean age of patients was 62.5 years. Seventeen (65%) were female, 10 (38%) Black, and 15 (58%) White. Twenty-five (96%) patients responded to ≥ 1 symptom check-in, and overall response rate was 78%. Four (15%) patients were escalated to the triage line: one was advised to present to the emergency department (ED), and three were managed in the outpatient setting. Median time from escalation to triage call was 11.5 minutes. Four (15%) patients presented to the ED without first escalating their care via our program. Participant satisfaction was high (Net Promoter Score: 100, n = 4). CONCLUSION: Implementation of an intensive remote symptom monitoring and rapid NP triage program for outpatients with cancer and suspected or confirmed COVID-19 infection is possible. Similar tools may facilitate more rapid triage for patients with cancer in future pandemics.

Validation of a Machine Learning Algorithm to Predict 180-Day Mortality for Outpatients With Cancer.

IMPORTANCE: Machine learning (ML) algorithms can identify patients with cancer at risk of short-term mortality to inform treatment and advance care planning. However, no ML mortality risk prediction algorithm has been prospectively validated in oncology or compared with routinely used prognostic indices. OBJECTIVE: To validate an electronic health record-embedded ML algorithm that generated real-time predictions of 180-day mortality risk in a general oncology cohort. DESIGN, SETTING, AND PARTICIPANTS: This prognostic study comprised a prospective cohort of patients with outpatient oncology encounters between March 1, 2019, and April 30, 2019. An ML algorithm, trained on retrospective data from a subset of practices, predicted 180-day mortality risk between 4 and 8 days before a patient's encounter. Patient encounters took place in 18 medical or gynecologic oncology practices, including 1 tertiary practice and 17 general oncology practices, within a large US academic health care system. Patients aged 18 years or older with outpatient oncology or hematology and oncology encounters were included in the analysis. Patients were excluded if their appointment was scheduled after weekly predictions were generated and if they were only evaluated in benign hematology, palliative care, or rehabilitation practices. EXPOSURES: Gradient-boosting ML binary classifier. MAIN OUTCOMES AND MEASURES: The primary outcome was the patients' 180-day mortality from the index encounter. The primary performance metric was the area under the receiver operating characteristic curve (AUC). RESULTS: Among 24 582 patients, 1022 (4.2%) died within 180 days of their index encounter. Their median (interquartile range) age was 64.6 (53.6-73.2) years, 15 319 (62.3%) were women, 18 015 (76.0%) were White, and 10 658 (43.4%) were seen in the tertiary practice. The AUC was 0.89 (95% CI, 0.88-0.90) for the full cohort. The AUC varied across disease-specific groups within the tertiary practice (AUC ranging from 0.74 to 0.96) but was similar between the tertiary and general oncology practices. At a prespecified 40% mortality risk threshold used to differentiate high- vs low-risk patients, observed 180-day mortality was 45.2% (95% CI, 41.3%-49.1%) in the high-risk group vs 3.1% (95% CI, 2.9%-3.3%) in the low-risk group. Integrating the algorithm into the Eastern Cooperative Oncology Group and Elixhauser comorbidity index-based classifiers resulted in favorable reclassification (net reclassification index, 0.09 [95% CI, 0.04-0.14] and 0.23 [95% CI, 0.20-0.27], respectively). CONCLUSIONS AND RELEVANCE: In this prognostic study, an ML algorithm was feasibly integrated into the electronic health record to generate real-time, accurate predictions of short-term mortality for patients with cancer and outperformed routinely used prognostic indices. This algorithm may be used to inform behavioral interventions and prompt earlier conversations about goals of care and end-of-life preferences among patients with cancer.

Effect of Integrating Machine Learning Mortality Estimates With Behavioral Nudges to Clinicians on Serious Illness Conversations Among Patients With Cancer: A Stepped-Wedge Cluster Randomized Clinical Trial.

IMPORTANCE: Serious illness conversations (SICs) are structured conversations between clinicians and patients about prognosis, treatment goals, and end-of-life preferences. Interventions that increase the rate of SICs between oncology clinicians and patients may improve goal-concordant care and patient outcomes. OBJECTIVE: To determine the effect of a clinician-directed intervention integrating machine learning mortality predictions with behavioral nudges on motivating clinician-patient SICs. DESIGN, SETTING, AND PARTICIPANTS: This stepped-wedge cluster randomized clinical trial was conducted across 20 weeks (from June 17 to November 1, 2019) at 9 medical oncology clinics (8 subspecialty oncology and 1 general oncology clinics) within a large academic health system in Pennsylvania. Clinicians at the 2 smallest subspecialty clinics were grouped together, resulting in 8 clinic groups randomly assigned to the 4 intervention wedge periods. Included participants in the intention-to-treat analyses were 78 oncology clinicians who received SIC training and their patients (N = 14 607) who had an outpatient oncology encounter during the study period. INTERVENTIONS: (1) Weekly emails to oncology clinicians with SIC performance feedback and peer comparisons; (2) a list of up to 6 high-risk patients (≥10% predicted risk of 180-day mortality) scheduled for the next week, estimated using a validated machine learning algorithm; and (3) opt-out text message prompts to clinicians on the patient's appointment day to consider an SIC. Clinicians in the control group received usual care consisting of weekly emails with cumulative SIC performance. MAIN OUTCOMES AND MEASURES: Percentage of patient encounters with an SIC in the intervention group vs the usual care (control) group. RESULTS: The sample consisted of 78 clinicians and 14 607 patients. The mean (SD) age of patients was 61.9 (14.2) years, 53.7% were female, and 70.4% were White. For all encounters, SICs were conducted among 1.3% in the control group and 4.6% in the intervention group, a significant difference (adjusted difference in percentage points, 3.3; 95% CI, 2.3-4.5; P < .001). Among 4124 high-risk patient encounters, SICs were conducted among 3.6% in the control group and 15.2% in the intervention group, a significant difference (adjusted difference in percentage points, 11.6; 95% CI, 8.2-12.5; P < .001). CONCLUSIONS AND RELEVANCE: In this stepped-wedge cluster randomized clinical trial, an intervention that delivered machine learning mortality predictions with behavioral nudges to oncology clinicians significantly increased the rate of SICs among all patients and among patients with high mortality risk who were targeted by the intervention. Behavioral nudges combined with machine learning mortality predictions can positively influence clinician behavior and may be applied more broadly to improve care near the end of life. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT03984773.

Integrating machine-generated mortality estimates and behavioral nudges to promote serious illness conversations for cancer patients: Design and methods for a stepped-wedge cluster randomized controlled trial.

INTRODUCTION: Patients with cancer often receive care that is not aligned with their personal values and goals. Serious illness conversations (SICs) between clinicians and patients can help increase a patient's understanding of their prognosis, goals and values. METHODS AND ANALYSIS: In this study, we describe the design of a stepped-wedge cluster randomized trial to evaluate the impact of an intervention that employs machine learning-based prognostic algorithms and behavioral nudges to prompt oncologists to have SICs with patients at high risk of short-term mortality. Data are collected on documented SICs, documented advance care planning discussions, and end-of-life care utilization (emergency room and inpatient admissions, chemotherapy and hospice utilization) for patients of all enrolled clinicians. CONCLUSION: This trial represents a novel application of machine-generated mortality predictions combined with behavioral nudges in the routine care of outpatients with cancer. Findings from the trial may inform strategies to encourage early serious illness conversations and the application of mortality risk predictions in clinical settings. TRIAL REGISTRATION: Clinicaltrials.gov Identifier: NCT03984773.

Leveraging Goals of Care Interventions to Deliver Personalized Care Near the End of Life.

This Viewpoint discusses barriers to and opportunities for incorporating goal of care communications into end-of-life care.