Cost-Effectiveness of Reduced-Intensity Allogeneic Hematopoietic Cell Transplantation for Older Patients With High-Risk Myelodysplastic Syndrome: Analysis of BMT CTN 1102.

PURPOSE: BMT CTN 1102 was a phase III trial comparing reduced-intensity allogeneic hematopoietic cell transplantation (RIC alloHCT) to standard of care for persons with intermediate- or high-risk myelodysplastic syndrome (MDS). We report results of a cost-effectiveness analysis conducted alongside the clinical trial. METHODS: Three hundred eighty-four patients received HCT (n = 260) or standard of care (n = 124) according to availability of a human leukocyte antigen-matched donor. Cost-effectiveness was calculated from US commercial and Medicare perspectives over a 20-year time horizon. Health care utilization and costs were estimated using propensity score-matched cohorts of HCT recipients in the OptumLabs Data Warehouse (age 50-64 years) and Medicare (age 65 years and older). EuroQol 5 Dimension (EQ-5D) surveys of trial participants were used to derive health state utilities. RESULTS: Extrapolated 20-year overall survival for those age 50-64 years was 29% for HCT (n = 105) versus 13% for usual care (n = 44) and 31% for HCT (n = 155) versus 12% for non-HCT (n = 80) for those age 65 years and older. HCT was more effective (+2.36 quality-adjusted life-years [QALYs] for age 50-64 years and +2.92 QALYs for age 65 years and older) and more costly (+$452,242 in US dollars (USD) for age 50-64 years and +$233,214 USD for age 65 years and older) than usual care, with incremental cost-effectiveness ratios of $191,487 (USD)/QALY and $79,834 (USD)/QALY, respectively. For persons age 50-64 years, there was a 29% chance that HCT was cost-effective using a willingness-to-pay (WTP) threshold of $150K (USD)/QALY and 51% at a $200K (USD)/QALY. For persons age 65 years and older, the probability was 100% at a WTP >$150K (USD)/QALY. CONCLUSION: Among patients age 65 years and older with high-risk MDS, RIC HCT is a high-value strategy. For those age 50-64 years, HCT is a lower-value strategy but has similar cost-effectiveness to other therapies commonly used in oncology.

Using Machine Learning to Leverage Biomarker Change and Predict Colorectal Cancer Recurrence.

PURPOSE: The risk of colorectal cancer (CRC) recurrence after primary treatment varies across individuals and over time. Using patients' most up-to-date information, including carcinoembryonic antigen (CEA) biomarker profiles, to predict risk could improve personalized decision making. METHODS: We used electronic health record data from an integrated health system on a cohort of patients diagnosed with American Joint Committee on Cancer stage I-III CRC between 2008 and 2013 (N = 3,970) and monitored until recurrence or end of follow-up. We addressed missingness in recurrence outcomes and longitudinal CEA measures, and engineered CEA features using current and past biomarker values for inclusion in a risk prediction model. We used a discrete time Superlearner model to evaluate various algorithms for predicting recurrence. We evaluated the time-varying discrimination and calibration of the algorithms and assessed the role of individual predictors. RESULTS: Recurrence was documented in 448 (11.3%) patients. XGBoost with depth = 1 (XGB-D1) predicted recurrence substantially better than all other algorithms at all time points, with AUC ranging from 0.87 (95% CI, 0.86 to 0.88) at 6 months to 0.94 (95% CI, 0.92 to 0.96) at 54 months. The only variable used by XGB-D1 was 6-month change in log CEA. Predicted 1-year risk of recurrence was nearly zero for patients whose log CEA did not increase in the last 6 months, between 12.2% and 34.1% for patients whose log CEA increased between 0.10 and 0.40, and 43.6% for those with a log CEA increase >0.40. Compared with XGB, penalized regression approaches (lasso, ridge, and elastic net) performed poorly, with AUCs ranging from 0.58 to 0.69. CONCLUSION: A flexible, machine learning approach that incorporated longitudinal CEA information yielded a simple and high-performing model for predicting recurrence on the basis of 6-month change in log CEA.

Intervention Nonadherence in the TrACER (S1415CD) Study: A Pragmatic Randomized Trial of a Standardized Order Entry for CSF Prescribing.

PURPOSE: We conducted a pragmatic, cluster-randomized trial to test whether a guideline-based standing order entry (SOE) improves use of primary prophylactic CSF (PP-CSF) prescribing for patients receiving myelosuppressive chemotherapy. We investigated variability in adherence to the intervention. METHODS: We conducted a cluster-randomized trial among 32 oncology clinics from the NCI Community Oncology Research Program. Clinics were randomized 3:1 to a guideline-based PP-CSF SOE or usual care. Among SOE sites, automated orders for PP-CSF were included for regimens at high risk for febrile neutropenia (FN) and an alert not to use PP-CSF for low FN risk. A secondary 1:1 randomization was done among intervention sites to either SOE to prescribe or an alert to not prescribe PP-CSF for patients receiving intermediate risk-regimens. Providers were allowed to override the SOE. RESULTS: Overall, PP-CSF use among patients receiving high FN risk treatment was high and not different between arms; however, rates of PP-CSF use varied widely by site, ranging from 48.6% to 100%. Among those receiving low FN risk regimens, PP-CSF use was low and not different between arms; however, PP-CSF use ranged from 0% to 19.4% across sites. In the intermediate-risk substudy, PP-CSF was five-fold higher among sites randomized to SOE; however, there was considerable variability in adherence to intervention assignment: PP-CSF use ranged from 0% to 75% among sites randomized to SOE. Despite an alert to not prescribe, PP-CSF prescribing ranged from 0% to 33%. CONCLUSION: In this randomized pragmatic trial aimed at improving PP-CSF prescribing, there was substantial variability in site adherence to the intervention assignment. Although the ability to opt out of the intervention is a feature of pragmatic trials, planning to estimate nonadherence is critical to ensure adequate power.

Impact of treatment experience on patient knowledge of colony-stimulating factors among patients receiving cancer chemotherapy: evidence from S1415CD-a large pragmatic trial.

PURPOSE: Primary prophylactic granulocyte colony-stimulating factors (PP-CSFs) are prescribed alongside chemotherapy regimens that carry a significant risk of febrile neutropenia (FN). As part of S1415CD, a prospective, pragmatic trial evaluating the impact of automated orders to improve PP-CSF prescribing, we evaluated patients' baseline knowledge of PP-CSF and whether that knowledge improved following the first cycle of chemotherapy. METHODS: Adult patients with breast, colorectal, or non-small-cell lung cancer initiating chemotherapy were enrolled in S1415CD between January 2016 and April 2020. Eight questions assessing knowledge of CSF indications, risks, benefits, and out-of-pocket costs were included in a baseline survey and in a follow-up survey at the end of the first cycle of chemotherapy. Responses were stratified by the trial arm and whether chemotherapy was low, intermediate, or high FN risk. RESULTS: Of the 3605 eligible patients, 3580 (99.3%) completed the baseline survey, and 3420 (95.5%) completed the follow-up survey. At baseline, 803 (22.4%) patients responded "Don't know" to all 8 questions, and all patients averaged 2.75 correct questions. At follow-up, knowledge increased by 0.34 in the high-FN-risk group (p < 0.001) but declined for the other FN-risk groups. In multivariate analysis, receiving a high-FN-risk regimen and younger age were significantly associated with knowledge improvement. CONCLUSION: Chemotherapy patients had poor knowledge of PP-CSF that improved only modestly among recipients of high-FN-risk chemotherapy. Further efforts to inform patients about the risks, benefits, and costs of PP-CSF may be warranted, particularly for those in whom prophylaxis is indicated. TRIAL REGISTRATION: NCT02728596, April 6, 2016.

Underutilization or appropriate care? Assessing adjuvant chemotherapy use and survival in 3 heterogenous subpopulations with stage II/III colorectal cancer within a large integrated health system.

BACKGROUND: Clinical guidelines have recommended adjuvant chemotherapy (ACT) for patients with high-risk stage II colon cancer, although the survival benefit is unclear. ACT is also recommended for patients with stage III colon cancer to reduce the risk of recurrence and mortality. For stage II/III rectal cancer, however, the role of perioperative chemotherapy (PCT, adjuvant or neoadjuvant) remains controversial, resulting in substantial variation in its use in clinical practice. OBJECTIVES: To understand real-world use and predictors of ACT or PCT use and survival outcomes in 3 heterogeneous patient groups with colorectal cancer (CRC), and to inform the evidence gap between guideline-based care and clinical practice. METHODS: This retrospective cohort study included patients with an initial stage II/III CRC diagnosis between 2008 and 2013 identified from Kaiser Permanente Southern California electronic health record databases. Patients were eligible if they were aged 18-74 years at diagnosis and received primary curative surgery. We fitted mixed effects logistic regression models to evaluate predictors of ACT receipt and Cox proportional hazards models on propensity score-matched (PS-matched) samples to assess the association between ACT/PCT receipt and survival. RESULTS: We included 1,690 patients with colon cancer (stage II: 820 and stage III: 870) and 587 patients with rectal cancer (stage II: 241 and stage III: 346). We found that 65% of patients with high-risk stage II colon cancer, 15% of those with stage III colon, and 15% of those with stage II/III rectal cancer did not receive ACT/PCT. Patients with stage II colon cancer with T4 stage (odds ratio [OR] = 5.79, 95% CI = 3.33 - 10.06) and a lower comorbidity score were more likely to receive ACT (high vs low Charlson score: OR = 0.69, 95% CI = 0.55 - 0.87). Patients with stage III rectal cancer were more likely to receive PCT than those with stage II disease (OR = 7.85, 95% CI = 2.07 - 29.74). Patients with another cancer diagnosis prior to CRC diagnosis were less likely to receive PCT (OR = 0.37, 95% CI = 0.16 - 0.85). ACT/PCT use was associated with improved overall survival among patients with high-risk stage II colon cancer (PS-matched hazard ratio [HR] = 0.42, 95% CI = 0.25 - 0.70) and those with stage III CRC (stage III colon: PS-matched HR = 0.3, 95% CI = 0.25 - 0.36; stage III rectal: PS-matched HR = 0.2, 95% CI = 0.13 - 0.31). CONCLUSIONS: We found potential underuse of appropriate chemotherapy treatment in patients with high-risk stage II colon cancer and stage III CRC. Clinicians' and providers' decisions on ACT administration may not be fully guided by the risk of recurrence and 5-year survival benefits in stage II colon cancer. DISCLOSURES: This research was supported by the National Cancer Institute of the National Institutes of Health (NIH) (under R37-CA218413). The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.

Racial Disparities in the Ascertainment of Cancer Recurrence in Electronic Health Records.

PURPOSE: There is growing interest in using computable phenotypes or proxies to identify important clinical outcomes, such as cancer recurrence, in rich electronic health records data. However, the race/ethnicity-specific accuracies of these proxies remain unclear. We examined whether the accuracy of a proxy for colorectal cancer (CRC) recurrence differed by race/ethnicity and the possible mechanisms that drove the differences. METHODS: Using data from a large integrated health care system, we identified a stratified random sample of 282 Black/African American (AA), Hispanic, and non-Hispanic White (NHW) patients with CRC who received primary treatment. Patient 5-year recurrence status was estimated using a utilization-based proxy and evaluated against the true recurrence status obtained using detailed chart review and by race/ethnicity. We used covariate-adjusted probit regression models to estimate the associations between race/ethnicity and misclassification. RESULTS: The recurrence proxy had excellent overall accuracy (positive predictive value [PPV] 89.4%; negative predictive value 96.5%; mean difference in timing 1.96 months); however, accuracy varied by race/ethnicity. Compared with NHW patients, PPV was 14.9% lower (95% CI, 2.53 to 28.6) among Hispanic patients and 4.3% lower (95% CI, -4.8 to 14.8) among Black/AA patients. The proxy disproportionately inflated the 5-year recurrence incidence for Hispanic patients by 10.6% (95% CI, 4.2 to 18.2). Compared with NHW patients, proxy recurrences for Hispanic patients were almost three times as likely to have been misclassified as positive (adjusted risk ratio 2.91 [95% CI, 1.21 to 8.31]). Higher false positives among racial/ethnic minorities may be related to higher prevalence of noncancerous lung-related problems and substantial delays in primary treatment because of insufficient patient-provider communication and abnormal treatment patterns. CONCLUSION: Using a proxy with worse accuracy among racial/ethnic minority patients to estimate population health may misdirect resources and support erroneous conclusions around treatment benefit for these patients.

Racial and Ethnic Bias in Risk Prediction Models for Colorectal Cancer Recurrence When Race and Ethnicity Are Omitted as Predictors.

Importance: Including race and ethnicity as a predictor in clinical risk prediction algorithms has received increased scrutiny, but there continues to be a lack of empirical studies addressing whether simply omitting race and ethnicity from the algorithms will ultimately affect decision-making for patients of minoritized racial and ethnic groups. Objective: To examine whether including race and ethnicity as a predictor in a colorectal cancer recurrence risk algorithm is associated with racial bias, defined as racial and ethnic differences in model accuracy that could potentially lead to unequal treatment. Design, Setting, and Participants: This retrospective prognostic study was conducted using data from a large integrated health care system in Southern California for patients with colorectal cancer who received primary treatment between 2008 and 2013 and follow-up until December 31, 2018. Data were analyzed from January 2021 to June 2022. Main Outcomes and Measures: Four Cox proportional hazards regression prediction models were fitted to predict time from surveillance start to cancer recurrence: (1) a race-neutral model that explicitly excluded race and ethnicity as a predictor, (2) a race-sensitive model that included race and ethnicity, (3) a model with 2-way interactions between clinical predictors and race and ethnicity, and (4) separate models by race and ethnicity. Algorithmic fairness was assessed using model calibration, discriminative ability, false-positive and false-negative rates, positive predictive value (PPV), and negative predictive value (NPV). Results: The study cohort included 4230 patients (mean [SD] age, 65.3 [12.5] years; 2034 [48.1%] female; 490 [11.6%] Asian, Hawaiian, or Pacific Islander; 554 [13.1%] Black or African American; 937 [22.1%] Hispanic; and 2249 [53.1%] non-Hispanic White). The race-neutral model had worse calibration, NPV, and false-negative rates among racial and ethnic minority subgroups than non-Hispanic White individuals (eg, false-negative rate for Hispanic patients: 12.0% [95% CI, 6.0%-18.6%]; for non-Hispanic White patients: 3.1% [95% CI, 0.8%-6.2%]). Adding race and ethnicity as a predictor improved algorithmic fairness in calibration slope, discriminative ability, PPV, and false-negative rates (eg, false-negative rate for Hispanic patients: 9.2% [95% CI, 3.9%-14.9%]; for non-Hispanic White patients: 7.9% [95% CI, 4.3%-11.9%]). Inclusion of race interaction terms or using race-stratified models did not improve model fairness, likely due to small sample sizes in subgroups. Conclusions and Relevance: In this prognostic study of the racial bias in a cancer recurrence risk algorithm, removing race and ethnicity as a predictor worsened algorithmic fairness in multiple measures, which could lead to inappropriate care recommendations for patients who belong to minoritized racial and ethnic groups. Clinical algorithm development should include evaluation of fairness criteria to understand the potential consequences of removing race and ethnicity for health inequities.

Practice Pattern Variation in Adoption of New and Evolving Percutaneous Coronary Intervention Procedures.

Objective: Assess factors contributing to variation in the use of new and evolving diagnostic and interventional procedures for percutaneous coronary intervention (PCI). Background: Evidence-based practices for PCI have the potential to improve outcomes but are variably adopted. Finding possible drivers of PCI procedure-use variability is key for efforts aimed at establishing more uniform practice. Methods: Veterans Affairs Clinical Assessment, Reporting, and Tracking Program data were used to estimate a proportion of variation attributable to hospital-, operator-, and patient-level factors across (a) radial arterial access, (b) intravascular imaging/optical coherence tomography, and (c) atherectomy for PCI. We used random-effects models with hospital, operator, and patient random effects. Overlap between levels generated cumulative variability estimates greater than 100%. Results: A total of 445 operators performed 95,391 PCI procedures across 73 hospitals from 2011 to 2018. The rates of all procedures increased over this time. 24.45% of variability in the use of radial access was attributable to the hospital, 53.04% to the operator, and 57.83% to patient-level characteristics. 9.06% of the variability in intravascular imaging use was attributable to the hospital, 43.92% to the operator, and 21.20% to the patient. Lastly, 20.16% of the variability in use of atherectomy was attributed to the hospital, 34.63% to the operator, and 57.50% to the patient. Conclusions: The use of radial access, intracoronary imaging, and atherectomy is influenced by patient, operator, and hospital factors, but patient and operator-level effects predominate. Efforts to increase the use of evidence-based practices for PCI should consider interventions at these levels.

Cost-Effectiveness of Unrelated Umbilical Cord Blood Transplantation versus HLA-Haploidentical Related Bone Marrow Transplantation: Evidence from BMT CTN 1101.

BMT CTN 1101 was a Phase III randomized controlled trial comparing reduced-intensity conditioning followed by double unrelated umbilical cord blood transplantation (UCBT) versus HLA-haploidentical related donor bone marrow transplantation (haplo-BMT) for patients with high-risk hematologic malignancies. Here we report the results of a parallel cost-effectiveness analysis of these 2 hematopoietic stem cell transplantation (HCT) techniques. In this study, 368 patients were randomized to unrelated UCBT (n = 186) or haplo-BMT (n = 182). We estimated healthcare utilization and costs using propensity score-matched haplo-BMT recipients from the OptumLabs Data Warehouse for trial participants age <65 years and Medicare claims for participants age ≥65 years. Weibull models were used to estimate 20-year survival. EQ-5D surveys by trial participants were used to estimate quality-adjusted life-years (QALYs). At a 5-year follow-up, survival was 42% for haplo-BMT recipients versus 36% for UCBT recipients (P = .06). Over a 20-year time horizon, haplo-BMT is expected to be more effective (+.63 QALY) and more costly (+$118,953) for persons age <65 years. For those age ≥65 years, haplo-BMT is expected to be more effective and less costly. In one-way uncertainty analyses, for persons age <65, the cost per QALY result was most sensitive to life-years and health state utilities, whereas for those age ≥65, life- years were more influential than costs and health state utilities. Compared to UCBT, haplo-BMT was moderately more cost-effective for patients age <65 years and less costly and more effective for persons age ≥65 years. Haplo-BMT is a fair value choice for commercially insured patients with high-risk leukemia and lymphoma who require HCT. For Medicare enrollees, haplo-BMT is a preferred choice when considering costs and outcomes.

Community pharmacist intervention to optimize statin adherence in diabetes care: The GuIDE-S study.

BACKGROUND: Statin use in people with type 2 diabetes (T2D) reduces cardiovascular events, yet adherence remains suboptimal. OBJECTIVE: This study evaluated the impact of a community pharmacist intervention on statin adherence in new users with T2D. METHODS: As part of a quasi-experimental study, community pharmacy staff proactively identified adult patients with T2D who were not prescribed a statin. When appropriate, the pharmacist prescribed a statin via a collaborative practice agreement or facilitated acquisition of a prescription from another prescriber. Patients received individualized education and follow-up and monitoring for 1 year. Adherence was defined as the proportion of days covered (PDC) by a statin over 12 months. Linear and logistic regression were used to compare the effect of the intervention on continuous and a binary adherence threshold, defined as PDC ≥ 80%, respectively. RESULTS: Overall, 185 patients started statin therapy and were matched to 370 control patients for analysis. Adjusted average PDC was 3.1% higher in the intervention group (95% CI -0.037 to 0.098). Patients in the intervention group were 21.2% more likely to have PDC ≥ 80% (95% CI 0.828-1.774). CONCLUSION: The intervention resulted in higher statin adherence than usual care; however, the differences were not statistically significant.

Mimicking Clinical Trials Using Real-World Data: A Novel Method and Applications.

INTRODUCTION: Simulating individual-level trial data when only summary data are available is often useful for meta-analysis, forming external control arms and calibrating trial results to real-world data (RWD). The joint distribution of baseline characteristics in a trial is usually simulated by combining its summary data with RWD's correlations. However, RWD correlations may not be a perfect proxy for the trial. A misspecified correlation structure could bias any analysis in which the outcomes generating models are nonlinear or include effect modifiers. METHODS: We developed an iterative algorithm using copula and resampling, which was based on the estimated propensity score for the likelihood of enrollment in a trial given participants' characteristics. Validation was performed using Monte Carlo simulations under different scenarios in which the marginal and joint distributions of covariates differ between trial samples and RWD. Two applications were illustrated using an actual trial and the Surveillance, Epidemiology, and End Results-Medicare data. We calculated the standardized mean difference (SMD) to assess the generalizability of the trial and explored the feasibility of generating an external control by applying a parametric Weibull model trained in RWD to predict survival in the simulated trial cohort. RESULTS: Across all scenarios, approximated correlations derived from the algorithm were closer to the true correlations than the RWD's correlations. The algorithm also successfully reproduced the joint distribution of characteristics for the actual trial. A similar SMD was observed using simulated data and individual-level trial data. The 95% confidence intervals were overlapped between adjusted survival estimates from the simulated trial and actual trial Kaplan-Meier estimates. CONCLUSIONS: The algorithm could be a feasible way to simulate individual-level data when only summary data are available. Further research is needed to validate our approach with larger sample sizes. HIGHLIGHTS: The correlation structure is crucial to building the joint distribution of patient characteristics, and a misspecified correlation structure could potentially influence predicted outcomes.An iterative algorithm was developed to approximate a trial's correlation structure using published summary trial data and real-world data.The algorithm could be a feasible way to simulate individual-level trial data when only trial summary data are available.

A Pragmatic Cluster-Randomized Trial of a Standing Order Entry Intervention for Colony-Stimulating Factor Use Among Patients at Intermediate Risk for Febrile Neutropenia.

PURPOSE: Primary prophylactic colony-stimulating factors (PP-CSFs) are prescribed to reduce febrile neutropenia (FN) but their benefit for intermediate FN risk regimens is uncertain. Within a pragmatic, randomized trial of a standing order entry (SOE) PP-CSF intervention, we conducted a substudy to evaluate the effectiveness of SOE for patients receiving intermediate-risk regimens. METHODS: TrACER was a cluster randomized trial where practices were randomized to usual care or a guideline-based SOE intervention. In the primary study, sites were randomized 3:1 to SOE of automated PP-CSF orders for high FN risk regimens and alerts against PP-CSF use for low-risk regimens versus usual care. A secondary 1:1 randomization assigned 24 intervention sites to either SOE to prescribe or an alert to not prescribe PP-CSF for intermediate-risk regimens. Clinicians were allowed to over-ride the SOE. Patients with breast, colorectal, or non-small-cell lung cancer were enrolled. Mixed-effect logistic regression models were used to test differences between randomized sites. RESULTS: Between January 2016 and April 2020, 846 eligible patients receiving intermediate-risk regimens were registered to either SOE to prescribe (12 sites: n = 542) or an alert to not prescribe PP-CSF (12 sites: n = 304). Rates of PP-CSF use were higher among sites randomized to SOE (37.1% v 9.9%, odds ratio, 5.91; 95% CI, 1.77 to 19.70; P = .0038). Rates of FN were low and identical between arms (3.7% v 3.7%). CONCLUSION: Although implementation of a SOE intervention for PP-CSF significantly increased PP-CSF use among patients receiving first-line intermediate-risk regimens, FN rates were low and did not differ between arms. Although this guideline-informed SOE influenced prescribing, the results suggest that neither SOE nor PP-CSF provides sufficient benefit to justify their use for all patients receiving first-line intermediate-risk regimens.

Community pharmacist intervention to close statin gaps in diabetes care: The GuIDE-S study.

BACKGROUND: Statin therapy is recommended for people with type 2 diabetes (T2D) to lower cardiovascular risk; however, evidence suggests that significant gaps in statin therapy exist. OBJECTIVE: To evaluate (1) the impact of a community pharmacist-led model for initiating statin therapy in people with type 2 diabetes (T2D) on statin initiation and (2) pharmacists' self-reported perceptions of the intervention feasibility and fidelity to the intervention. METHODS: This was a type 1 hybrid effectiveness-implementation study of 9 intervention and 18 control pharmacies within a community pharmacy chain. Pharmacy staff proactively identified patients with T2D not taking a statin and prescribed a statin via a collaborative practice agreement or facilitated acquisition of a prescription from the patient's preferred prescriber. The eligible population included patients aged 18-84 years with T2D, who had filled ≥60 days' supply of one, noninsulin, diabetes medication in a rolling 6-month period, and who had not filled a statin during the same period. A Cox proportional hazards model was used to compare time to statin initiation. Pharmacists at intervention pharmacies completed a survey at 6 and 12 months after implementation (March and August 2019, respectively) to assess intervention feasibility and fidelity. RESULTS: For the statin initiation analysis, 1670 intervention patients were matched to 3358 control patients. Overall, 26.3% (n=442) of intervention patients and 25.4% (n=854) of control patients initiated a statin within 12 months of their index date. There was no difference in statin initiation likelihood between intervention and control patients (hazard ratio: 1.00; 95% CI: 0.83, 1.21). Fifteen pharmacists completed the 6-month survey (33% response rate), and 12 completed the 12-month survey (26%). The intervention's feasibility score was 4.0 at 6 months and 4.2 at 12 months, indicating an increase in perceived feasibility. Fidelity decreased from 6 to 12 months. CONCLUSION: The community pharmacist-led intervention resulted in more patients initiating statin therapy as compared to usual care; however, the differences were not statistically significant. Pharmacists perceived the intervention to be feasible; however, fidelity decreased over time.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 1-Data From Wearable Devices.

OBJECTIVES: With the emerging use of machine learning (ML) techniques, there has been particular interest in using wearable data for health economics and outcomes research (HEOR). We aimed to understand the emerging patterns of how ML has been applied to wearable data in HEOR. METHODS: We identified studies published in PubMed between January 2016 and March 2021. Studies that included at least 1 HEOR-related Medical Subject Headings term, applied an ML, and used wearable data were eligible for inclusion. Two reviewers abstracted information including ML application types and data on which ML was applied and analyzed them using descriptive analyses. RESULTS: A total of 148 studies were identified from PubMed, among which 32 studies met the inclusion criteria. There has been an increase over time in the number of ML studies using wearable data. ML has been more frequently used for monitoring events in real time (78%) than to predict future events (22%). There has been a wide range of outcomes examined, ranging from general physical or mental health (24%) to more disease-specific outcomes (eg, disease incidence [19%] and progression [13%]) and treatment-related outcomes (eg, treatment adherence [9%] and outcomes [9%]). Data for ML models were more often derived from wearable devices with specific medical purposes (60%) than those without (40%). CONCLUSION: There has been a wide range of applications of ML to wearable data. Both medical and nonmedical wearable devices have been used as a data source, showing the potential for providing rich data for ML studies in HEOR.

An evaluation of stakeholder engagement in comparative effectiveness research: lessons learned from SWOG S1415CD.

Aim: Stakeholder engagement is central to comparative effectiveness research yet there are gaps in definitions of success. We used a framework developed by Lavallee et al. defining effective engagement criteria to evaluate stakeholder engagement during a pragmatic cluster-randomized trial. Methods: Semi-structured interviews were developed from the framework and completed to learn about members' experiences. Interviews were analyzed in a deductive approach for themes related to the effective engagement criteria. Results: Thirteen members participated and described: respect for ideas, time to achieve consensus, access to information and continuous feedback as areas of effective engagement. The primary criticism was lack of diversity. Discussion: Feedback was positive, particularly among themes of respect, trust and competence, and led to development of a list of best practices for engagement. The framework was successful for evaluating engagement. Conclusion: Standardized frameworks allow studies to formally evaluate their stakeholder engagement approach and develop best practices for future research.

What is this article about? This article is about the evaluation of how effective the stakeholder engagement was in a comparative effectiveness research (CER) study funded by the Patient Centered Outcomes Research Institute (PCORI). The research team found a framework (developed by Lavalle et al.) that defined six different criteria for effective stakeholder engagement, and used that criteria to complete semi-structured interviews with the stakeholders involved with our study. These interviews were reviewed to determine what stakeholder engagement processes were successful and helped provide a list of best practices for stakeholder engagement for other researchers doing CER. What were the results? Stakeholders highlighted respect for their ideas, time to achieve consensus, easy access to information and a continuous feedback loop between study team and stakeholders as effective engagement processes. What do the results mean? These results can help other researchers doing CER learn best practices to implement from the outset of a study to best engage stakeholders in their research. The results also show that having a standardized framework to evaluate stakeholder engagement is important and allows for research teams to formally evaluate their engagement approach and learn what was successful and where there are areas for improvement in future studies.

Effects of a Guideline-Informed Clinical Decision Support System Intervention to Improve Colony-Stimulating Factor Prescribing: A Cluster Randomized Clinical Trial.

Importance: Colony-stimulating factors are prescribed to patients undergoing chemotherapy to reduce the risk of febrile neutropenia. Research suggests that 55% to 95% of colony-stimulating factor prescribing is inconsistent with national guidelines. Objective: To examine whether a guideline-based standing order for primary prophylactic colony-stimulating factors improves use and reduces the incidence of febrile neutropenia. Design, Setting, and Participants: This cluster randomized clinical trial, the Trial Assessing CSF Prescribing Effectiveness and Risk (TrACER), involved 32 community oncology clinics in the US. Participants were adult patients with breast, colorectal, or non-small cell lung cancer initiating cancer therapy and enrolled between January 2016 and April 2020. Data analysis was performed from July to October 2021. Interventions: Sites were randomized 3:1 to implementation of a guideline-based primary prophylactic colony-stimulating factor standing order system or usual care. Automated orders were added for high-risk regimens, and an alert not to prescribe was included for low-risk regimens. Risk was based on National Comprehensive Cancer Network guidelines. Main Outcomes and Measures: The primary outcome was to find an increase in colony-stimulating factor use among high-risk patients from 40% to 75%, a reduction in use among low-risk patients from 17% to 7%, and a 50% reduction in febrile neutropenia rates in the intervention group. Mixed model logistic regression adjusted for correlation of outcomes within a clinic. Results: A total of 2946 patients (median [IQR] age, 59.0 [50.0-67.0] years; 2233 women [77.0%]; 2292 White [79.1%]) were enrolled; 2287 were randomized to the intervention, and 659 were randomized to usual care. Colony-stimulating factor use for patients receiving high-risk regimens was high and not significantly different between groups (847 of 950 patients [89.2%] in the intervention group vs 296 of 309 patients [95.8%] in the usual care group). Among high-risk patients, febrile neutropenia rates for the intervention (58 of 947 patients [6.1%]) and usual care (13 of 308 patients [4.2%]) groups were not significantly different. The febrile neutropenia rate for patients receiving high-risk regimens not receiving colony-stimulating factors was 14.9% (17 of 114 patients). Among the 585 patients receiving low-risk regimens, colony-stimulating factor use was low and did not differ between groups (29 of 457 patients [6.3%] in the intervention group vs 7 of 128 patients [5.5%] in the usual care group). Febrile neutropenia rates did not differ between usual care (1 of 127 patients [0.8%]) and the intervention (7 of 452 patients [1.5%]) groups. Conclusions and Relevance: In this cluster randomized clinical trial, implementation of a guideline-informed standing order did not affect colony-stimulating factor use or febrile neutropenia rates in high-risk and low-risk patients. Overall, use was generally appropriate for the level of risk. Standing order interventions do not appear to be necessary or effective in the setting of prophylactic colony-stimulating factor prescribing. Trial Registration: ClinicalTrials.gov Identifier: NCT02728596.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 2-Data From Nonwearables.

OBJECTIVES: Despite the increasing interest in applying machine learning (ML) methods in health economics and outcomes research (HEOR), stakeholders face uncertainties in when and how ML can be used. We reviewed the recent applications of ML in HEOR. METHODS: We searched PubMed for studies published between January 2020 and March 2021 and randomly chose 20% of the identified studies for the sake of manageability. Studies that were in HEOR and applied an ML technique were included. Studies related to wearable devices were excluded. We abstracted information on the ML applications, data types, and ML methods and analyzed it using descriptive statistics. RESULTS: We retrieved 805 articles, of which 161 (20%) were randomly chosen. Ninety-two of the random sample met the eligibility criteria. We found that ML was primarily used for predicting future events (86%) rather than current events (14%). The most common response variables were clinical events or disease incidence (42%) and treatment outcomes (22%). ML was less used to predict economic outcomes such as health resource utilization (16%) or costs (3%). Although electronic medical records (35%) were frequently used for model development, claims data were used less frequently (9%). Tree-based methods (eg, random forests and boosting) were the most commonly used ML methods (31%). CONCLUSIONS: The use of ML techniques in HEOR is growing rapidly, but there remain opportunities to apply them to predict economic outcomes, especially using claims databases, which could inform the development of cost-effectiveness models.

Development and Internal Validation of a Prognostic Model of the Probability of Death or Lung Transplantation Within 2 Years for Patients With Cystic Fibrosis and FEV1 ≤ 50% Predicted.

BACKGROUND: Improved methods are needed to risk-stratify patients with cystic fibrosis (CF) and reduced FEV1. RESEARCH QUESTIONS: What are the predictors of death or lung transplantation (LTx) within 2 years among patients with CF whose FEV1 ≤ 50% predicted? Do these markers similarly predict outcomes among G551D patients taking ivacaftor since 2012? STUDY DESIGN AND METHODS: Patients with CF, age ≥ 6 years with FEV1 ≤ 50% predicted as of December 31, 2014, were identified in a data set that merged Cystic Fibrosis Foundation and United Network for Organ Sharing (UNOS) registries. The least absolute shrinkage and selection operator (LASSO) method was applied to a randomly selected training set to select important prognostic variables. Accuracy and association of the model with death or LTx with 2 years (2-year death or LTx) were validated via logistic regression on an independent test set. Sensitivity analyses explored predictors for patients with UNOS data. RESULTS: FEV1 percent predicted (OR, 1.51 for 5% decrease; 95% CI, 1.27-1.81), number of pulmonary exacerbations treated with IV antibiotics (OR, 1.35; 95% CI, 1.11-1.65), and continuous or nocturnal oxygen (OR, 3.71; 95% CI, 1.81-7.59) were significantly associated with 2-year death or LTx. Our model predicted outcomes with greater sensitivity (ratio of sensitivity, 1.26; 95% CI, 1.02-1.54), ratio of positive predictive value (1.25; 95% CI, 1.05-1.51), and ratio of negative predictive value (1.04; 95% CI, 1.01-1.07) than FEV1 < 30% predicted. Among those taking ivacaftor in 2014, only FEV1 remained associated with 2-year death or LTx. For patients with UNOS data, LASSO identified additional covariates of interest, including noninvasive ventilation use, low hemoglobin, pulmonary arterial systolic pressure, supplemental oxygen, mechanical ventilation, FEV1 percent predicted, and cardiac index. INTERPRETATION: Among individuals with CF and FEV1 ≤ 50% predicted, FEV1 percent predicted, oxygen therapy, and number of pulmonary exacerbations predicted 2-year death or LTx. Although limited by small sample size, only FEV1 remained predictive in patients receiving highly effective modulator therapy. Additional physiologic variables could improve prognostication in CF.

Assessing surveillance utilization and value in commercially insured patients with colorectal cancer.

OBJECTIVES: Real-world patterns of surveillance testing in colorectal cancer (CRC) and the effects on health and cost outcomes are largely unknown. Our objectives were to (1) assess trends in carcinoembryonic antigen (CEA) testing, CT scans, and colonoscopy utilization and (2) examine the value of CEA testing intensity by characterizing receipt of curative treatment for recurrence and measuring direct medical costs. STUDY DESIGN: Prospective cohort study. METHODS: We used an IBM MarketScan database to identify patients with a diagnosis of and treatment for CRC between 2008 and 2015. We used a negative binomial model to assess utilization of CEA testing and logistic models to assess utilization of CT scans and colonoscopies. We used a Cox proportional hazards model to assess surveillance intensity and time to curative treatment. We estimated direct medical costs using the Kaplan-Meier sample average estimator to account for censored costs. RESULTS: We identified 3197 eligible patients. The mean numbers of CEA tests, CT scans, and colonoscopies remained relatively constant in the study period, but adherence to guidelines varied by surveillance. When categorizing individuals by their CEA utilization adherence to guidelines (perfect utilizers and overutilizers), overutilizers had an HR for curative treatment of 2.11 (95% CI, 1.46-3.05) relative to perfect utilizers. Although overutilizers underwent potentially curative procedures for recurrence at higher rates compared with perfect utilizers, direct medical costs were much higher in the overutilizer group. CONCLUSIONS: Higher intensity of surveillance, beyond what is recommended by guidelines, may lead to earlier recurrence detection and subsequent treatment, but this is associated with significantly higher direct medical costs.

Successes and challenges of implementing a cancer care delivery intervention in community oncology practices: lessons learned from SWOG S1415CD.

BACKGROUND: Cancer Care Delivery (CCD) research studies often require practice-level interventions that pose challenges in the clinical trial setting. The SWOG Cancer Research Network (SWOG) conducted S1415CD, one of the first pragmatic cluster-randomized CCD trials to be implemented through the National Cancer Institute (NCI) Community Oncology Program (NCORP), to compare outcomes of primary prophylactic colony stimulating factor (PP-CSF) use for an intervention of automated PP-CSF standing orders to usual care. The introduction of new methods for study implementation created challenges and opportunities for learning that can inform the design and approach of future CCD interventions. METHODS: The order entry system intervention was administered at the site level; sites were affiliated NCORP practices that shared the same chemotherapy order system. 32 sites without existing guideline-based PP-CSF standing orders were randomized to the intervention (n = 24) or to usual care (n = 8). Sites assigned to the intervention participated in tailored training, phone calls and onboarding activities administered by research team staff and were provided with additional funding and external IT support to help them make protocol required changes to their order entry systems. RESULTS: The average length of time for intervention sites to complete reconfiguration of their order sets following randomization was 7.2 months. 14 of 24 of intervention sites met their individual patient recruitment target of 99 patients enrolled per site. CONCLUSIONS: In this paper we share seven recommendations based on lessons learned from implementation of the S1415CD intervention at NCORP community oncology practices representing diverse geographies and patient populations across the U. S. It is our hope these recommendations can be used to guide future implementation of CCD interventions in both research and community settings. TRIAL REGISTRATION: NCT02728596 , registered April 5, 2016.