Computing the Cost of Care per Patient per Day for Patients With Metastatic Neuroendocrine Neoplasms.

PURPOSE: Patients with well-differentiated, low-grade metastatic neuroendocrine neoplasms (NENs) usually have a long median survival and require complex, expensive care over many years at multidisciplinary centers. The cost burden for patients and institutions serves as a barrier to care. Understanding the drivers of these costs and whether intense monitoring adds value will help to optimize value-based care. METHODS: We adapted the cost of care per patient per day (CCPD) validated methodology to measure cost while accounting for varying follow-up duration. We queried the Stanford NEN Database, which aggregates data from the electronic health record and other electronic sources, to study patients with metastatic NENs receiving regular care at Stanford. Current Procedural Terminology codes for services incurred during the monitoring period for each patient were mapped to the corresponding cost conversion factor and date in the Medicare fee schedule. RESULTS: Two hundred two patients between 2010 and 2017 were studied with a mean CCPD of $119.11 in US dollars (USD); NEN-specific systemic therapy made up 55% of this cost. Somatostatin analogs were the costliest systemic therapy. Systemic therapy was the driver of cost differences among patients with various primary tumor types, stage of disease, tumor differentiation and grade, and functional hormone status. Patients in the most expensive CCPD group did not have a significant survival benefit (P = .66). CONCLUSION: The CCPD methodology was effective in studying cancer care value in NENs. Systemic therapy, specifically somatostatin analogs, was the primary driver of cost, and intense monitoring and higher-cost care did not improve survival outcomes.

Real-World Impact of Prophylactic Growth Factor Use on Timing of Febrile Neutropenia and Infection After High-Risk Chemotherapy.

BACKGROUND: Prophylactic growth-factor therapy with granulocyte colony-stimulating factor (G-CSF) reduces the risk of febrile neutropenia (FN) in patients with breast cancer initiating myelosuppressive chemotherapy. However, little is known about the protective benefit early in the chemotherapy cycle. METHODS: To assess the relationship between G-CSF prophylaxis and incidence of FN/infection in week 1 versus beyond week 1 of the first chemotherapy cycle, a retrospective study was conducted using Medicare claims from 2005 through 2020 among patients with breast cancer initiating high-risk chemotherapy. Two cohorts were compared based on G-CSF prophylaxis within 3 days following chemotherapy initiation. The primary outcome was FN or infection, defined as hospitalization with neutropenia, fever, or infection diagnosis. Secondary outcomes were a stricter definition of FN and infection-related hospitalization. Unadjusted and regression-adjusted proportions of patients experiencing each outcome during week 1 versus beyond week 1 of the first chemotherapy cycle were compared. RESULTS: Of 78,810 patients meeting all inclusion criteria (>98% female; mean age, 69 years), 79% initiated TC (docetaxel/cyclophosphamide), 14% TCH (docetaxel/carboplatin/trastuzumab), and 7% TAC (docetaxel/doxorubicin/cyclophosphamide). Among patients receiving G-CSF (74%), incidence of first-cycle FN/infection was lower compared with patients not receiving G-CSF (overall, 6% vs 13%; TAC, 12% vs 19%; TC, 6% vs 12%; TCH, 5% vs 15%). However, patients who received G-CSF were generally more likely to experience FN/infection in week 1 (adjusted odds ratio [aOR], 1.24 for all; 1.73 for TAC; 1.35 for TC; and 0.76 for TCH). Results were similar for strictly defined FN (overall aOR, 1.29 for week 1 and 0.12 for beyond week 1) and infection-related hospitalization (overall aOR, 1.33 for week 1 and 0.27 for beyond week 1). CONCLUSIONS: Overall, the rates of chemotherapy-related FN and infection in week 1 of the first chemotherapy cycle are similar for patients receiving and not receiving G-CSF, suggesting continued risk in week 1 despite prophylactic G-CSF.

Machine Learning Applied to Electronic Health Records: Identification of Chemotherapy Patients at High Risk for Preventable Emergency Department Visits and Hospital Admissions.

PURPOSE: Acute care use (ACU) is a major driver of oncologic costs and is penalized by a Centers for Medicare & Medicaid Services quality measure, OP-35. Targeted interventions reduce preventable ACU; however, identifying which patients might benefit remains challenging. Prior predictive models have made use of a limited subset of the data in the electronic health record (EHR). We aimed to predict risk of preventable ACU after starting chemotherapy using machine learning (ML) algorithms trained on comprehensive EHR data. METHODS: Chemotherapy patients treated at an academic institution and affiliated community care sites between January 2013 and July 2019 who met inclusion criteria for OP-35 were identified. Preventable ACU was defined using OP-35 criteria. Structured EHR data generated before chemotherapy treatment were obtained. ML models were trained to predict risk for ACU after starting chemotherapy using 80% of the cohort. The remaining 20% were used to test model performance by the area under the receiver operator curve. RESULTS: Eight thousand four hundred thirty-nine patients were included, of whom 35% had preventable ACU within 180 days of starting chemotherapy. Our primary model classified patients at risk for preventable ACU with an area under the receiver operator curve of 0.783 (95% CI, 0.761 to 0.806). Performance was better for identifying admissions than emergency department visits. Key variables included prior hospitalizations, cancer stage, race, laboratory values, and a diagnosis of depression. Analyses showed limited benefit from including patient-reported outcome data and indicated inequities in outcomes and risk modeling for Black and Medicaid patients. CONCLUSION: Dense EHR data can identify patients at risk for ACU using ML with promising accuracy. These models have potential to improve cancer care outcomes, patient experience, and costs by allowing for targeted, preventative interventions.

Health management via telemedicine: Learning from the COVID-19 experience.

At the onset of the COVID-19 (coronavirus disease 2019) pandemic, telemedicine was rapidly implemented to protect patients and healthcare providers from infection. It is unlikely that care delivery will fully return to the pre-COVID form. Telemedicine offers many opportunities to improve care efficiency, accessibility, and patient outcomes, but many challenges exist related to technology interoperability, the digital divide, and usability. We propose that telemedicine evolve to support continuity of care throughout the patient journey, including multidisciplinary care teams and the seamless integration of data into the clinical workflow to support a learning healthcare system. Importantly, evidence is needed to support this paradigm shift in care delivery to ensure the quality and efficacy of care delivered via telemedicine. Here, we highlight gaps and opportunities that need to be addressed by the biomedical informatics community to move forward with safe and effective healthcare delivery via telemedicine.

Benchmark Method for Cost Computations Across Health Care Systems: Cost of Care per Patient per Day in Breast Cancer Care.

PURPOSE: To estimate the value of cancer care and to compare value among episodes of care, a transparent, reproducible, and standardized cost computation methodology is needed. Charges, claims, and reimbursements are related to cost but are nontransparent and proprietary. We developed a method to measure the cost of the following phases of care: (1) initial treatment with curative intent, (2) surveillance and survivorship care, and (3) relapse and end-of-life care. METHODS: We combined clinical data from our electronic health record, the state cancer registry, and the Social Security Death Index. We analyzed the care of patients with breast cancer and mapped Common Procedural Terminology (CPT) codes to the corresponding cost conversion factor and date in the CMS Medicare fee schedule. To account for varying duration of episodes of care, we computed a cost of care per day (CCPD) for each patient. RESULTS: Median CCPD for initial treatment was $29.45 in US dollars (USD), the CCPD for surveillance and survivorship care was $2.45 USD, and the CCPD for relapse care was $13.80 USD. Among the three breast cancer types (hormone receptor-positive or human epidermal growth factor receptor 2 [HER2]-negative, HER2-positive, and triple-negative), there was no difference in CCPD. Relapsed patients in the most expensive surveillance CCPD group had significantly shorter survival. CONCLUSION: We developed a method to identify high-value oncology care-cost of care per patient per day (CCPD)-in episodes of initial, survivorship, and relapse care. The methodology can help identify positive deviants (who have developed best practices) delivering high-value care. Merging our data with claims data from third-party payers can increase the accuracy and validity of the CCPD.

Real-world Evidence to Estimate Prostate Cancer Costs for First-line Treatment or Active Surveillance.

BACKGROUND: Prostate cancer is the most common cancer in men and second leading cause of cancer-related deaths. Changes in screening guidelines, adoption of active surveillance (AS), and implementation of high-cost technologies have changed treatment costs. Traditional cost-effectiveness studies rely on clinical trial protocols unlikely to capture actual practice behavior, and existing studies use data predating new technologies. Real-world evidence reflecting these changes is lacking. OBJECTIVE: To assess real-world costs of first-line prostate cancer management. DESIGN SETTING AND PARTICIPANTS: We used clinical electronic health records for 2008-2018 linked with the California Cancer Registry and the Medicare Fee Schedule to assess costs over 24 or 60 mo following diagnosis. We identified surgery or radiation treatments with structured methods, while we used both structured data and natural language processing to identify AS. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Our results are risk-stratified calculated cost per day (CCPD) for first-line management, which are independent of treatment duration. We used the Kruskal-Wallis test to compare unadjusted CCPD while analysis of covariance log-linear models adjusted estimates for age and Charlson comorbidity. RESULTS AND LIMITATIONS: In 3433 patients, surgery (54.6%) was more common than radiation (22.3%) or AS (23.0%). Two years following diagnosis, AS ($2.97/d) was cheaper than surgery ($5.67/d) or radiation ($9.34/d) in favorable disease, while surgery ($7.17/d) was cheaper than radiation ($16.34/d) for unfavorable disease. At 5 yr, AS ($2.71/d) remained slightly cheaper than surgery ($2.87/d) and radiation ($4.36/d) in favorable disease, while for unfavorable disease surgery ($4.15/d) remained cheaper than radiation ($10.32/d). Study limitations include information derived from a single healthcare system and costs based on benchmark Medicare estimates rather than actual payment exchanges. PATIENT SUMMARY: Active surveillance was cheaper than surgery (-47.6%) and radiation (-68.2%) at 2 yr for favorable-risk disease, which decreased by 5 yr (-5.6% and -37.8%, respectively). Surgery was less costly than radiation for unfavorable risk for both intervals (-56.1% and -59.8%, respectively).

Extracting Patient-Centered Outcomes from Clinical Notes in Electronic Health Records: Assessment of Urinary Incontinence After Radical Prostatectomy.

OBJECTIVE: To assess documentation of urinary incontinence (UI) in prostatectomy patients using unstructured clinical notes from Electronic Health Records (EHRs). METHODS: We developed a weakly-supervised natural language processing tool to extract assessments, as recorded in unstructured text notes, of UI before and after radical prostatectomy in a single academic practice across multiple clinicians. Validation was carried out using a subset of patients who completed EPIC-26 surveys before and after surgery. The prevalence of UI as assessed by EHR and EPIC-26 was compared using repeated-measures ANOVA. The agreement of reported UI between EHR and EPIC-26 was evaluated using Cohen's Kappa coefficient. RESULTS: A total of 4870 patients and 716 surveys were included. Preoperative prevalence of UI was 12.7 percent. Postoperative prevalence was 71.8 percent at 3 months, 50.2 percent at 6 months and 34.4 and 41.8 at 12 and 24 months, respectively. Similar rates were recorded by physicians in the EHR, particularly for early follow-up. For all time points, the agreement between EPIC-26 and the EHR was moderate (all p < 0.001) and ranged from 86.7 percent agreement at baseline (Kappa = 0.48) to 76.4 percent agreement at 24 months postoperative (Kappa = 0.047). CONCLUSIONS: We have developed a tool to assess documentation of UI after prostatectomy using EHR clinical notes. Our results suggest such a tool can facilitate unbiased measurement of important PCOs using real-word data, which are routinely recorded in EHR unstructured clinician notes. Integrating PCO information into clinical decision support can help guide shared treatment decisions and promote patient-valued care.

Comparison of orthogonal NLP methods for clinical phenotyping and assessment of bone scan utilization among prostate cancer patients.

OBJECTIVE: Clinical care guidelines recommend that newly diagnosed prostate cancer patients at high risk for metastatic spread receive a bone scan prior to treatment and that low risk patients not receive it. The objective was to develop an automated pipeline to interrogate heterogeneous data to evaluate the use of bone scans using a two different Natural Language Processing (NLP) approaches. MATERIALS AND METHODS: Our cohort was divided into risk groups based on Electronic Health Records (EHR). Information on bone scan utilization was identified in both structured data and free text from clinical notes. Our pipeline annotated sentences with a combination of a rule-based method using the ConText algorithm (a generalization of NegEx) and a Convolutional Neural Network (CNN) method using word2vec to produce word embeddings. RESULTS: A total of 5500 patients and 369,764 notes were included in the study. A total of 39% of patients were high-risk and 73% of these received a bone scan; of the 18% low risk patients, 10% received one. The accuracy of CNN model outperformed the rule-based model one (F-measure = 0.918 and 0.897 respectively). We demonstrate a combination of both models could maximize precision or recall, based on the study question. CONCLUSION: Using structured data, we accurately classified patients' cancer risk group, identified bone scan documentation with two NLP methods, and evaluated guideline adherence. Our pipeline can be used to provide concrete feedback to clinicians and guide treatment decisions.

Critical Lessons From High-Value Oncology Practices.

IMPORTANCE: Cancer care is expensive. Cancer care provided by practice organizations varies in total spending incurred by patients and payers during treatment episodes and in quality of care, and this unnecessary variation contributes to the high cost. OBJECTIVE: To use the variation in total spending and quality of care to assess oncology practice attributes distinguishing "high value" that may be tested and adopted by others to produce similar results. DESIGN, SETTING, AND PARTICIPANTS: "Positive deviance" was used in this exploratory mixed-methods (quantitative and qualitative) analysis of interview results. To quantify value, oncology practices located near the US Pacific Northwest and Midwest with low mean insurer-allowed spending were identified. Among those, practices with high quality were selected. A team then conducted site visits to interview practice personnel from June 2, 2015, through October 3, 2015, and to probe for attributes of high-value care. A qualitative analysis of their interview results was performed, and a panel of experienced oncologists was convened to review attributes occurring uniquely or frequently in low-spending practices for their contribution to value improvement and ease of implementation. Four positive deviant (ie, low-spending) oncology practices and 3 oncology practices that ranked near the middle of the spending distribution were studied. MAIN OUTCOMES AND MEASURES: Thematic saturation in a qualitative analysis of high-value care attributes. RESULTS: From the 7 oncology practices studied, 13 attributes within the following 5 themes emerged: treatment planning and goal setting, services supporting the patient journey, technical support and physical layout, care team organization and function, and external context. Five attributes (ie, conservative use of imaging, early discussion of treatment limitations and consequences, single point of contact, maximal use of registered nurses for interventions, and a multicomponent health care system) most sharply distinguished the high-value practice sites. The expert oncologist panel judged 3 attributes (ie, early and normalized palliative care, ambulatory rapid response, and early discussion of treatment limitations and consequences) to carry the highest immediate potential for lowering spending without compromising the quality of care. CONCLUSIONS AND RELEVANCE: Oncology practice attributes warranting further testing were identified that may lower total spending for high-quality oncology care.

Choosing Wisely in Oncology: Are We Ready For Value-Based Care?

INTRODUCTION: In 2012, ASCO created the Top Five Choosing Wisely (CW) list of low-value tests and procedures for which there is little evidence of benefit. ASCO's Quality Oncology Practice Initiative, an oncologist-led practice-based quality assessment program, includes measures on the basis of these recommendations. METHODS: CW test measures from spring and fall 2013, spring 2014, and spring 2015 were evaluated for concordance rates, change in the concordance over time, and variability by practice characteristics. Practice characteristics recorded included geographic location, academic affiliation, number of new cases, number of medical oncologists, and rounds of participation in Quality Oncology Practice Initiative. Medians, interquartile ranges, and percentages were calculated for concordance with recommendations and practice characteristics. Change in recommendation concordance over time was assessed using linear regression models. RESULTS: From 2013 to 2015, 341 unique oncology practices abstracted the CW measures. Performance varied for specific recommendations. The median concordance was best for measure 1 (patients with low or undocumented performance status who received chemotherapy), where concordance ranged from 78.4% to 83.3%. The lowest concordance was for measure 3 (use of biomarkers or advanced imaging tests for surveillance in early breast cancer), where concordance ranged from 67.7% to 74.2%. Performance on CW measures varied markedly by individual practice. Variability over time and by practice characteristics was observed. CONCLUSION: Performance on ASCO's CW demonstrates room for improvement. Concordance rates varied substantially by practice. Further education on CW measures is needed to improve patient care and enhance value.

Improving Care With a Portfolio of Physician-Led Cancer Quality Measures at an Academic Center.

PURPOSE: Development and implementation of robust reporting processes to systematically provide quality data to care teams in a timely manner is challenging. National cancer quality measures are useful, but the manual data collection required is resource intensive, and reporting is delayed. We designed a largely automated measurement system with our multidisciplinary cancer care programs (CCPs) to identify, measure, and improve quality metrics that were meaningful to the care teams and their patients. METHODS: Each CCP physician leader collaborated with the cancer quality team to identify metrics, abiding by established guiding principles. Financial incentive was provided to the CCPs if performance at the end of the study period met predetermined targets. Reports were developed and provided to the CCP physician leaders on a monthly or quarterly basis, for dissemination to their CCP teams. RESULTS: A total of 15 distinct quality measures were collected in depth for the first time at this cancer center. Metrics spanned the patient care continuum, from diagnosis through end of life or survivorship care. All metrics improved over the study period, met their targets, and earned a financial incentive for their CCP. CONCLUSION: Our quality program had three essential elements that led to its success: (1) engaging physicians in choosing the quality measures and prespecifying goals, (2) using automated extraction methods for rapid and timely feedback on improvement and progress toward achieving goals, and (3) offering a financial team-based incentive if prespecified goals were met.

Racial and Ethnic Differences in Breast Cancer Survival: Mediating Effect of Tumor Characteristics and Sociodemographic and Treatment Factors.

PURPOSE: To evaluate the relationship between race/ethnicity and breast cancer-specific survival according to subtype and explore mediating factors. PATIENTS AND METHODS: Participants were women presenting with stage I to III breast cancer between January 2000 and December 2007 at National Comprehensive Cancer Network centers with survival follow-up through December 2009. Cox proportional hazards regression was used to compare breast cancer-specific survival among Asians (n = 533), Hispanics (n = 1,122), and blacks (n = 1,345) with that among whites (n = 14,268), overall and stratified by subtype (luminal A like, luminal B like, human epidermal growth factor receptor 2 type, and triple negative). Model estimates were used to derive mediation proportion and 95% CI for selected risk factors. RESULTS: In multivariable adjusted models, overall, blacks had 21% higher risk of breast cancer-specific death (hazard ratio [HR], 1.21; 95% CI, 1.00 to 1.45). For estrogen receptor-positive tumors, black and white survival differences were greatest within 2 years of diagnosis (years 0 to 2: HR, 2.65; 95% CI, 1.34 to 5.24; year 2 to end of follow-up: HR, 1.50; 95% CI, 1.12 to 2.00). Blacks were 76% and 56% more likely to die as a result of luminal A-like and luminal B-like tumors, respectively. No disparities were observed for triple-negative or human epidermal growth factor receptor 2-type tumors. Asians and Hispanics were less likely to die as a result of breast cancer compared with whites (Asians: HR, 0.56; 95% CI, 0.37 to 0.85; Hispanics: HR, 0.74; 95% CI, 0.58 to 0.95). For blacks, tumor characteristics and stage at diagnosis were significant disparity mediators. Body mass index was an important mediator for blacks and Asians. CONCLUSION: Racial disparities in breast cancer survival vary by tumor subtype. Interventions are needed to reduce disparities, particularly in the first 2 years after diagnosis among black women with estrogen receptor-positive tumors.

Leveraging state cancer registries to measure and improve the quality of cancer care: a potential strategy for California and beyond.

Despite recent increased attention to healthcare performance and the burden of disease from cancer, measures of quality of cancer care are not readily available. In 2013, the California HealthCare Foundation convened an expert workgroup to explore the potential for leveraging data in the California Cancer Registry (CCR), one of the world's largest population-based cancer registries, for measuring and improving the quality of cancer care. The workgroup assessed current registry operations, the value to be gained by linking CCR data with health insurance claims or encounter data and clinical data contained in health system electronic health records, and potential barriers to these linkages. The workgroup concluded that: 1) The CCR mandate should be expanded to include use of its data for quality of cancer care measurement and public reporting; and 2) a system should be developed to support linkage of registry data with both claims data and provider electronic health record data.

Time to diagnosis and breast cancer stage by race/ethnicity.

We examined differences in time to diagnosis by race/ethnicity, the relationship between time to diagnosis and stage, and the extent to which it explains differences in stage at diagnosis across racial/ethnic groups. Our analytic sample includes 21,427 non-Hispanic White (White), Hispanic, non-Hispanic Black (Black) and non-Hispanic Asian/Pacific Islander (Asian) women diagnosed with stage I to IV breast cancer between January 1, 2000 and December 31, 2007 at one of eight National Comprehensive Cancer Network centers. We measured time from initial abnormal mammogram or symptom to breast cancer diagnosis. Stage was classified using AJCC criteria. Initial sign of breast cancer modified the association between race/ethnicity and time to diagnosis. Among symptomatic women, median time to diagnosis ranged from 36 days among Whites to 53.6 for Blacks. Among women with abnormal mammograms, median time to diagnosis ranged from 21 days among Whites to 29 for Blacks. Blacks had the highest proportion (26 %) of Stage III or IV tumors. After accounting for time to diagnosis, the observed increased risk of stage III/IV breast cancer was reduced from 40 to 28 % among Hispanics and from 113 to 100 % among Blacks, but estimates remained statistically significant. We were unable to fully account for the higher proportion of late-stage tumors among Blacks. Blacks and Hispanics experienced longer time to diagnosis than Whites, and Blacks were more likely to be diagnosed with late-stage tumors. Longer time to diagnosis did not fully explain differences in stage between racial/ethnicity groups.