Role of simulation-based training and assessment to improve brachytherapy competency among radiation oncology residents.

Simulation is a technique used in healthcare to replicate clinical scenarios and improve patient safety, efficacy, and efficiency. Simulation-based medical education facilitates training and assessment in healthcare without increasing risk to patients, supported by ample evidence from surgical/procedural specialties. Simulation in radiation oncology has been leveraged to an extent, with successful examples of both screen-based and hands-on simulators that have improved confidence and performance in trainees. In the current era, evidence substantiates a significant deficit in brachytherapy procedure education, with radiation oncology residents reporting low confidence in this procedural skill, largely attributable to insufficient caseloads at some centers. Simulation-based medical education can facilitate structured training and competency-based assessment in brachytherapy skills. This review discusses existing advances and future directions in brachytherapy simulation, using examples from simulation in surgical specialties.

Same day discharge colon surgery: is it financially worth it?

AIM: Same day discharge (SDD) for colorectal surgery shows increasing promise in the era of enhanced recovery after surgery protocols and minimally invasive surgery. It has become increasingly relevant due to the constraints posed by the COVID-19 pandemic. The aim of this study was to compare SDD and postoperative day 1 (POD1) discharge to understand the clinical outcomes and financial impact on factors such as cost, charge, revenue, contribution margin and readmission. METHOD: A retrospective review of colectomies was performed at a single institution over a 2-year period (n = 143). Two populations were identified: SDD (n = 51) and POD1 (n = 92). Patients were selected by International Statistical Classification of Diseases and Related Health Problems-10 (ICD-10) and Diagnosis Related Grouper (DRG) codes. RESULTS: There was a statistically significant difference favouring SDD in total hospital cost (p < 0.0001), average direct costs (p < 0.0001) and average charges (p < 0.0016). SDD average hospital costs were $8699 (values in USD throughout) compared with $11 652 for POD 1 (p < 0.0001), and average SDD hospital charges were $85 506 compared with $97 008 for POD1 (p < 0.0016). The net revenue for SDD was $22 319 while for POD1 it was $26 173 (p = 0.14). Upon comparison of contribution margins (SDD $13 620 vs. POD1 $14 522), the difference was not statistically significant (p = 0.73). There were no identified statistically significant differences in operating room time, robotic console time, readmission rates or surgical complications. CONCLUSIONS: Amidst the pandemic-related constraints, we found that SDD was associated with lower hospital costs and comparable contribution margins compared with POD1. Additionally, the study was unable to identify any significant difference between operating time, readmissions, and surgical complications when performing SDD.

Using Sacubitril/Valsartan to Decrease Health care Costs in Population Health Patients.

Value-based care is the foundation of population health. The Health care Economic Efficiency Ratio (HEERO) scoring system is a promising new tool to measure the cost benefits of care in our Accountable Care Organization. HEERO score compares actual costs spent (utilizing insurance claims) and expected costs spent (estimated using the Centers for Medicare/Medicaid Services Risk score). Scores <1 suggest economic benefit. Sacubitril/valsartan has been shown to decrease readmissions for patients with heart failure (HF) and decrease health care costs. We explored the utility of sacubitril/valsartan in reducing HEERO scores and decreasing overall health care expenditure in patients with HF. Patients with HF in the population health cohort were enrolled. HEERO score was calculated for patients taking sacubitril/valsartan and other HF medications at 3-month intervals up to a year. We compared the average and total health care expenditure and inpatient days for patients on sacubitril/valsartan, spironolactone, ß blocker (BB) along with spironolactone, BB and angiotensin-converting enzyme inhibitor/angiotensin receptor blocker. For patients on sacubitril/valsartan, HEERO scores and inpatient days decreased (decreased health care expenditure) as the number of days of utilization increased (p <0.0001). In total, 270+ days of sacubitril/valsartan decreased health care costs by 22%. This cost reduction was mainly attributed to decreased inpatient days. Additionally, the combination of sacubitril/valsartan, spironolactone, and BB showed decreased HEERO score and inpatient days compared with spironolactone, BB and angiotensin-converting enzyme inhibitor/angiotensin receptor blocker in male patients. Sacubitril/valsartan use beyond 270 days resulted in decreased health care expenditure in a population health cohort compared with other HF medications. This economic benefit is achieved through the reduction in hospitalizations. Sacubitril/valsartan is an integral part of value-based care providing high-value, cost-effective care, and bolstering the economic wellbeing of patient care. Payor sources should consider this in subsidizing the cost of the medicine.

The American Society for Radiation Oncology Workforce Taskforce Review of the United States Radiation Oncology Workforce Analysis.

Over the past decade, concerns have arisen in radiation oncology regarding potential workforce supply and demand imbalance. The American Society for Radiation Oncology commissioned an independent analysis in 2022, looking at supply and demand in the United States radiation oncology workforce and projecting future trends for 2025 and 2030. The final report, titled Projected Supply and Demand for Radiation Oncologists in the U.S. in 2025 and 2030, is now available. The analysis included evaluating radiation oncologist (RO) supply (new graduates, exits from the specialty), potential changes in demand (growth of Medicare beneficiaries, hypofractionation, loss of indications, new indications) as well as RO productivity (growth of work relative value units [wRVUs] produced), and demand per beneficiary. The results demonstrated a relative balance between radiation oncology supply and demand for radiation services; the growth in ROs was balanced by the rapid growth of Medicare beneficiaries over the same period. The primary factors driving the model were found to be growth of Medicare beneficiaries and change in wRVU productivity, with hypofractionation and loss of indication having only a moderate effect; although the most likely scenario was a balance of workforce supply and demand, scenarios did demonstrate the possibility of over- and undersupply. Oversupply may become a concern if RO wRVU productivity reaches the highest region; beyond 2030, this is also possible if growth in RO supply does not parallel Medicare beneficiary growth, which is projected to decline and will require corresponding supply adjustment. Limitations of the analysis included uncertainty regarding the true number of ROs, the lack of inclusion of most technical reimbursement and its effect as well as failing to account for stereotactic body radiation therapy. A modeling tool is available to allow individuals to evaluate different scenarios. Moving forward, continued study will be needed to evaluate trends (particularly wRVU productivity and Medicare beneficiary growth) to allow for continued assessment of workforce supply and demand in radiation oncology.

Cost-Effectiveness Analysis of Ultra-Hypofractionated Whole Breast Radiation Therapy Alone Versus Hormone Therapy Alone or Combined Treatment for Low-Risk ER-Positive Early Stage Breast Cancer in Women Aged 65 Years and Older.

PURPOSE: The optimal management of early-stage, low-risk, hormone-positive breast cancer in older women remains controversial. Recent trials have shown that 5-fraction ultrahypofractionated whole-breast irradiation (U-WBI) has similar outcomes to longer courses, reducing the cost and inconvenience of treatment. We performed a cost-utility analysis to compare U-WBI to hormone therapy alone or their combination. METHODS AND MATERIALS: We simulated 3 different treatment approaches for women age 65 years or older with pT1-2N0 ER-positive invasive ductal carcinoma treated with lumpectomy with negative margins using a Markov microsimulation model. The strategies were U-WBI performed with a 3-dimensional conformal technique over 5 fractions without a boost ("radiation therapy [RT] alone"), adjuvant hormone therapy (anastrozole for 5 years) without RT ("aromatase-inhibitor [AI] alone"), or the combination of the 2. The combination strategy was calibrated to match trial results, and the relative effectiveness of the RT alone and AI alone strategies were inferred from previous randomized trials. The primary endpoint was the cost-effectiveness of the 3 strategies over a lifetime horizon as measured by the incremental cost-effectiveness ratio (ICER), with a value of $100,000/quality-adjusted life-year deemed "cost-effective." RESULTS: The model results compared with the prespecified target outcomes. On average, RT alone was the least expensive strategy ($14,775), with AI alone slightly more ($14,998), and combination therapy the costliest ($19,802). RT alone dominated AI alone (the incremental cost-effectiveness ratio [ICER] -$5089). Combination therapy, compared with RT alone, was slightly more expensive than our definition of cost-effective (ICER $113,468) but was cost-effective compared with AI alone (ICER $54,451). Probabilistic sensitivity analysis demonstrated RT alone to be cost-effective in 50% of trials, with combination therapy in 36% and AI alone in 14%. CONCLUSIONS: U-WBI alone appears the more cost-effective de-escalation strategy for these low-risk patients, compared with AI alone. Combining U-WBI and AI appears more costly but may be preferred by some patients.

Bioimpedance spectroscopy for breast cancer-related lymphedema assessment: clinical practice guidelines.

PURPOSE: Breast cancer-related lymphedema (BCRL) represents a significant concern for patients following breast cancer treatment, and assessment for BCRL represents a key component of survivorship efforts. Growing data has demonstrated the benefits of early detection and treatment of BCRL. Traditional diagnostic modalities are less able to detect reversible subclinical BCRL while newer techniques such as bioimpedance spectroscopy (BIS) have shown the ability to detect subclinical BCRL, allowing for early intervention and low rates of chronic BCRL with level I evidence. We present updated clinical practice guidelines for BIS utilization to assess for BCRL. METHODS AND RESULTS: Review of the literature identified a randomized controlled trial and other published data which form the basis for the recommendations made. The final results of the PREVENT trial, with 3-year follow-up, demonstrated an absolute reduction of 11.3% and relative reduction of 59% in chronic BCRL (through utilization of compression garment therapy) with BIS as compared to tape measurement. This is in keeping with real-world data demonstrating the effectiveness of BIS in a prospective surveillance model. For optimal outcomes patients should receive an initial pre-treatment measurement and subsequently be followed at a minimum quarterly for first 3 years then biannually for years 4-5, then annually as appropriate, consistent with previous guidelines; the target for intervention has been changed from a change in L-Dex of 10 to 6.5. The lack of pre-operative measure does not preclude inclusion in the prospective surveillance model of care. CONCLUSION: The updated clinical practice guidelines present a standardized approach for a prospective model of care using BIS for BCRL assessment and supported by evidence from a randomized controlled trial as well as real-world data.

Impact of a COPD care bundle on hospital readmission rates.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is one of the leading causes of mortality worldwide and contributes considerably to morbidity and health care costs. In October 2014, the Centers for Medicare and Medicaid Services introduced financial penalties followed by bundled payments for care improvement initiatives in patients hospitalized with COPD. OBJECTIVES: This study seeks to evaluate whether an evidence-based interprofessional COPD care bundle focused on inpatient, transitional, and outpatient care would reduce hospital readmission rates. METHODS: A pre- and postintervention analysis comparing readmission rates after a hospitalization for COPD in subjects who received standard of care versus an interprofessional team-led COPD care bundle was conducted. The primary outcome was 30-day all-cause readmissions; secondary outcomes included 60- and 90-day all-cause readmissions, escalation of pharmacotherapy, interprofessional interventions, and hospital length of stay. RESULTS: A total of 189 subjects were included in the control arm and 127 subjects in the COPD care bundle arm. A reduction in 30-day all-cause readmissions between the control arm and COPD care bundle arm (21.7% vs. 11.8%, P = 0.017) was seen. Similar outcomes were seen in 60-day (18% vs. 8.7%, P = 0.013) and 90-day all-cause readmissions (19.6% vs. 4.7%, P < 0.001). Pharmacists consulted with 68.5% of subjects and assisted with access to outpatient medications in 45.7% of subjects in the COPD care bundle arm. An escalation in maintenance therapy occurred more often in the COPD care bundle arm (22.2% vs. 44.9%, P < 0.001) than the control arm. CONCLUSIONS: An interprofessional team-led COPD care bundle resulted in significant reductions in all-cause hospital readmissions at 30, 60, and 90 days.

How private equity achieves return on investment in ophthalmology.

PURPOSE OF REVIEW: To review how private equity entities generate profit for investors and ophthalmologists. RECENT FINDINGS: There is a preponderance of private equity acquisitions and consolidation in ophthalmology. These private equity entities generate revenue by growth, profit improvement, and efficient use of capital structure. Physician partners sell their revenue and assets to a private equity entity while retaining a percentage of future profit. In general, a greater percentage going forward, will result in a smaller initial buyout. Partners typically receive payment in the form of cash and stock in the private equity entity, aligning incentives of both parties to grow and succeed. Junior associates and future partners typically do not benefit from the cash buyout but might have opportunity to buy shares in the private equity entity. SUMMARY: The ophthalmology job market has changed significantly with the rise in private equity. Private equity investors profit from organic growth, economies of scale, and future revenue of ophthalmology practices. Ophthalmology partners benefit from often sizeable buyouts and potentially profitable shares in the private equity entity. Junior and future ophthalmologist may be less likely to succeed financially compared with their contemporaries. Some private equity entities will thrive and other may fail, particularly if they are unable to attract talented new ophthalmologists.

Determining the Impact of the COVID-19 Pandemic on Hand Surgery Fellowship Education.

The purpose of this study is to report the impact of COVID-19 on hand surgery fellow learning and preparedness for practice. A multi-dimensional questionnaire was distributed to current hand fellows and fellowship directors across the United States. Survey questions included fellowship location, institutional response, impact on practice, education and job search. Thirty-two hand surgery fellows and 14 fellowship directors completed the survey. Of fellows, 59% reported a greater than 75% decrease in case volume. Mean hours worked per week per fellow decreased by 52%. All fellowship directors and 94% of fellows did not expect COVID-19 to impact their ability to graduate, and nearly all fellows felt prepared to start practice after fellowship training. However, many fellows expressed concern about job opportunities. The work hours and exposure of hand surgery fellows to elective surgical cases have been adversely impacted by COVID-19. Nevertheless, current hand fellows feel prepared to enter practice. (Journal of Surgical Orthopaedic Advances 31(1):048-052, 2022).

The Impact of a Home Respiratory Therapist to Reduce 30-Day Readmission Rates for Exacerbation of COPD.

BACKGROUND: In 2015, the Centers for Medicare and Medicaid Services limited payments to hospitals with high readmission rates for patients admitted with COPD exacerbation. Decreasing readmissions in this patient population improves patient health and decreases health care utilization of resources. We hypothesized a COPD disease management program delivered by a respiratory therapist (RT) in the patient's home may reduce readmission rates for COPD exacerbation. METHODS: We performed a pre/post interventional study comparing hospital readmissions for subjects with COPD exacerbation that received standard of care in the home versus an RT-led home COPD disease management program. Subjects discharged home from Atlantic Health System with COPD exacerbation were enrolled in the pre-intervention group. Subsequently, an evidence-based home COPD disease management program was implemented by an RT from At Home Medical in the home. The home COPD Disease Management Program was implemented from April 2017-September 2019, and this served as the post-intervention group. The primary end point was readmission rates at 30 d. Secondary end points included 60-d and 90-d readmission rates. RESULTS: A total of 1,093 participants were included in the study, 658 in the pre-intervention cohort and 435 participants in the post-intervention group. Approximately 22.3% (n = 147) of subjects in the pre-intervention group was readmitted within 30 d of discharge compared to 12.2% (n = 53) in the post-intervention group (P < .001). A reduction in 60-d (33.9% vs 12.0%, P < .001) and 90-d all-cause readmissions (43.5% vs 13.1%, P < .001) was also seen. Participation in the COPD Disease Management Program was significantly associated with decreased 30-, 60-, and 90-d readmission rates adjusting for age, gender, race, ethnicity, and smoking status (odds ratio 0.48 [95% CI 0.33-0.70]; odds ratio 0.26 [95% CI 0.18-0.38]; odds ratio 0.20 [95% CI 0.14-0.27];P < .001, for all 3 readmission rates). CONCLUSIONS: The COPD Disease Management Program is significantly associated with decreased readmission adjusting for demographics and smoking status.

The economic impact of circulating tumor-tissue modified HPV DNA for the post-treatment surveillance of HPV-driven oropharyngeal cancer: A simulation.

PURPOSE: Following treatment of HPV-driven oropharynx cancer, surveillance nasopharyngoscopy and imaging are often performed but are expensive and frequently ineffective. A novel plasma circulating tumor-tissue modified viral HPV DNA (TTMV-HPV-DNA) assay accurately detects recurrences. We modeled the cost of the new assay. METHODS: We designed and validated a partitioned survival model which replicated the results of the RTOG 1016 study and calculated cumulative surveillance costs from the payer's perspective. Two strategies were considered: a standard of routine endoscopy with imaging as needed and an alternative strategy which omitted scopes and imaging but obtained serial TTMV-HPV-DNA samples. No difference in effectiveness (QALY or LY) was assumed in the base case. A 5-year horizon was used, costs were reported in 2020 U.S. dollars discounted by 3%. Seven scenarios tested model assumptions and practice variation. Deterministic and probabilistic sensitivity analyses assessed parameter uncertainty. RESULTS: In the base case, at the list TTMV-HPV-DNA price, the cumulative cost of surveillance was $11,674 for the standard strategy and $20,756 for the TTMV-HPV-DNA strategy (+$9082 over 5 years). Probabilistic sensitivity analysis demonstrated the cost difference ranged from $4917-$12,047. The TTMV-HPV-DNA strategy was most likely to be either cost saving or cost-effective if future data demonstrate small improvements in quality or quantity of life (approximately 33 quality-adjusted life-days), if the assay reduces utilization of imaging, and if the periodicity of TTMV-HPV-DNA draws could be reduced from that on clinical trials. CONCLUSIONS: This data informs providers seeking to design more accurate, accessible, and economical post-treatment surveillance strategies.

Prognostic Risk Assessment and Prediction of Radiotherapy Benefit for Women with Ductal Carcinoma In Situ (DCIS) of the Breast, in a Randomized Clinical Trial (SweDCIS).

Prediction of radiotherapy (RT) benefit after breast-conserving surgery (BCS) for DCIS is crucial. The aim was to validate a biosignature, DCISionRT®, in the SweDCIS randomized trial. Women were randomly assigned to RT or not after BCS, between 1987 and 2000. Tumor blocks were collected, and slides were sent to PreludeDxTM for testing. In 504 women with complete data and negative margins, DCISionRT divided 52% women into Elevated (DS > 3) and 48% in Low (DS ≤ 3) Risk groups. In the Elevated Risk group, RT significantly decreased relative 10-year ipsilateral total recurrence (TotBE) and 10-year ipsilateral invasive recurrence (InvBE) rates, HR 0.32 and HR 0.24, with absolute decreases of 15.5% and 9.3%. In the Low Risk group, there were no significant risk differences observed with radiotherapy. Using a cutoff of DS > 3.0, the test was not predictive for RT benefit (p = 0.093); however, above DS > 2.8 RT benefit was greater for InvBE (interaction p = 0.038). Recurrences at 10 years without radiotherapy increased significantly per 5 DS units (TotBE HR:1.5 and InvBE HR:1.5). Continuous DS was prognostic for TotBE risk although categorical DS did not reach significance. Absolute 10-year TotBE and InvBE risks appear sufficiently different to indicate that DCISionRT can aid physicians in selecting individualized adjuvant DCIS treatment strategies. Further analyses are planned in combined cohorts to increase statistical power.

Disproportionate Negative Impact of the Radiation Oncology Alternative Payment Model on Rural Providers: A Cost Identification Analysis of Medicare Claims.

PURPOSE: The Radiation Oncology Alternative Payment Model (APM) is a Medicare demonstration project that will test whether prospective bundled payments to a randomly selected group of physician practices, hospital outpatient departments, and freestanding radiation therapy centers reduce overall expenditures while preserving or enhancing the quality of care for beneficiaries. The Model follows a complicated pricing methodology that blends historical reimbursements for a defined set of services made to professional and technical providers to create a weighted payment average for each of 16 cancer types. These averages are then adjusted by various factors to determine APM payments specific to each participating provider. METHODS: This impact study segregates APM participants into rural and urban groups and analyzes the effect of the Radiation Oncology Alternative Payment Model on their fee-for-service reimbursements. RESULTS: The main findings of this study are (1) the greater net-negative revenue impact on rural facilities versus urban facilities that would have participated in the Model this year and (2) the relative lack of high-value treatment services (ie, stereotactic radiotherapy and brachytherapy) delivered by rural facilities that exacerbates their negative impact. CONCLUSION: As such, rural providers participating in the Model in its current form may face greater risk to their economic viability and greater difficulty in funding technology improvements necessary for the achievement of high-quality care compared with their urban counterparts.

Assessment of the Association of COPD and Asthma with In-Hospital Mortality in Patients with COVID-19. A Systematic Review, Meta-Analysis, and Meta-Regression Analysis.

Together, chronic obstructive pulmonary disease (COPD) and asthma account for the most common non-infectious respiratory pathologies. Conflicting preliminary studies have shown varied effect for COPD and asthma as prognostic factors for mortality in coronavirus disease 2019 (COVID-19). The aim of this study was to explore the association of COPD and asthma with in-hospital mortality in patients with COVID-19 by systematically reviewing and synthesizing with a meta-analysis the available observational studies. MEDLINE, Scopus, and medRxiv databases were reviewed. A random-effects model meta-analysis was used, and I-square was utilized to assess for heterogeneity. In-hospital mortality was defined as the primary endpoint. Sensitivity and meta-regression analyses were performed. Thirty studies with 21,309 patients were included in this meta-analysis (1465 with COPD and 633 with asthma). Hospitalized COVID-19 patients with COPD had higher risk of death compared to those without COPD (OR: 2.29; 95% CI: 1.79-2.93; I2 59.6%). No significant difference in in-hospital mortality was seen in patients with and without asthma (OR: 0.87; 95% CI: 0.68-1.10; I2 0.0%). The likelihood of death was significantly higher in patients with COPD that were hospitalized with COVID-19 compared to patients without COPD. Further studies are needed to assess whether this association is independent or not. No significant difference was demonstrated in COVID-19-related mortality between patients with and without asthma.

Cost-Effectiveness Analysis of No Adjuvant Therapy Versus Partial Breast Irradiation Alone Versus Combined Treatment for Treatment of Low-Risk DCIS: A Microsimulation.

PURPOSE: Adjuvant therapy in patients with ductal carcinoma in situ who undergo partial mastectomy remains controversial, particularly for low-risk patients (60 years or older, estrogen-positive, tumor extent < 2.5 cm, grade 1 or 2, and margins ≥ 3 mm). We performed a cost-effectiveness analysis comparing three strategies: no adjuvant treatment after surgery, a five-fraction course of accelerated partial breast irradiation using intensity-modulated radiation therapy (accelerated partial breast irradiation [APBI]-alone), or APBI plus an aromatase inhibitor for 5 years. MATERIALS AND METHODS: Outcomes including local recurrence, distant metastases, and survival as well as toxicity data were modeled by a patient-level Markov microsimulation model, which were validated against trial data. Costs of treatment and possible adverse events were included from the societal perspective over a lifetime horizon, adjusted to 2019 US dollars and extracted from Medicare reimbursement data. Quality-adjusted life-years (QALYs) were calculated based on utilities extracted from the literature. RESULTS: No adjuvant therapy was the least costly approach ($5,744), followed by APBI-alone ($11,070); combined therapy was costliest ($16,052). Adjuvant therapy resulted in slightly higher QALYs (no adjuvant, 11.320; APBI-alone, 11.343; and combination, 11.381). In the base case, no treatment was the cost-effective strategy, with an incremental cost-effectiveness ratio of $239,109/QALY for APBI-alone and $171,718/QALY for combined therapy. The incremental cost-effectiveness ratio for combined therapy compared with APBI-alone was $131,949. Probabilistic sensitivity analyses found that no therapy was cost effective (defined as $100,000/QALY of lower) in 63% of trials, APBI-alone in 19%, and the combination in 18%. CONCLUSION: No adjuvant therapy represents the most cost-effective approach for postmenopausal women 60 years or older who receive partial mastectomy for low-risk ductal carcinoma in situ.

Reducing time to treatment and patient costs with breast cancer: the impact of patient visits.

BACKGROUND: The purpose of this study was to evaluate the impact of processes aimed at reducing time to treatment initiation (TTI) on minimizing the days spent to complete pretreatment visits and the associated costs for patients with nonmetastatic breast cancer. METHODS: System-wide initiatives were implemented in 2014 to minimize TTI, by incorporating multiple strategies (eg, creation of teams, patient liaisons, process mapping) and enhanced communication to increase coordinated visits. Average number of days spent to complete visits, TTI, and associated patient costs including driving expenses, parking, food, childcare, and lost wages were calculated and compared between the years 2015 and 2018. RESULTS: In 2015, the median TTI was 43.5 days and the average number of separate days spent to attend multidisciplinary visits prior to first treatment was 1.86. These were reduced to 29 days and 1.52 visits, respectively, in 2018 (p < 0.0001 for both). When evaluating treatment visits by surgical procedure, the average number of visits was reduced regardless of surgical procedure. The average number of visits was highest for patients undergoing mastectomy with reconstruction (2.34 in 2015, reduced to 1.65 in 2018, p < 0.0001). A single visit to complete treatment planning was associated with patient costs of $249 as compared with multiple trips costing $491 for 2 visits and up to $1,226 for 5 visits. CONCLUSIONS: In breast cancer patients, implementing processes to reduce time to treatment was associated with fewer visits required prior to treatment initiation, resulting in lower patient costs.

Machine Learning-Based Risk Assessment for Cancer Therapy-Related Cardiac Dysfunction in 4300 Longitudinal Oncology Patients.

Background The growing awareness of cardiovascular toxicity from cancer therapies has led to the emerging field of cardio-oncology, which centers on preventing, detecting, and treating patients with cardiac dysfunction before, during, or after cancer treatment. Early detection and prevention of cancer therapy-related cardiac dysfunction (CTRCD) play important roles in precision cardio-oncology. Methods and Results This retrospective study included 4309 cancer patients between 1997 and 2018 whose laboratory tests and cardiovascular echocardiographic variables were collected from the Cleveland Clinic institutional electronic medical record database (Epic Systems). Among these patients, 1560 (36%) were diagnosed with at least 1 type of CTRCD, and 838 (19%) developed CTRCD after cancer therapy (de novo). We posited that machine learning algorithms can be implemented to predict CTRCDs in cancer patients according to clinically relevant variables. Classification models were trained and evaluated for 6 types of cardiovascular outcomes, including coronary artery disease (area under the receiver operating characteristic curve [AUROC], 0.821; 95% CI, 0.815-0.826), atrial fibrillation (AUROC, 0.787; 95% CI, 0.782-0.792), heart failure (AUROC, 0.882; 95% CI, 0.878-0.887), stroke (AUROC, 0.660; 95% CI, 0.650-0.670), myocardial infarction (AUROC, 0.807; 95% CI, 0.799-0.816), and de novo CTRCD (AUROC, 0.802; 95% CI, 0.797-0.807). Model generalizability was further confirmed using time-split data. Model inspection revealed several clinically relevant variables significantly associated with CTRCDs, including age, hypertension, glucose levels, left ventricular ejection fraction, creatinine, and aspartate aminotransferase levels. Conclusions This study suggests that machine learning approaches offer powerful tools for cardiac risk stratification in oncology patients by utilizing large-scale, longitudinal patient data from healthcare systems.