Predicting heart failure outcomes by integrating breath-by-breath measurements from cardiopulmonary exercise testing and clinical data through a deep learning survival neural network.

Aims: Mathematical models previously developed to predict outcomes in patients with heart failure (HF) generally have limited performance and have yet to integrate complex data derived from cardiopulmonary exercise testing (CPET), including breath-by-breath data. We aimed to develop and validate a time-to-event prediction model using a deep learning framework using the DeepSurv algorithm to predict outcomes of HF. Methods and results: Inception cohort of 2490 adult patients with high-risk cardiac conditions or HF underwent CPET with breath-by-breath measurements. Potential predictive features included known clinical indicators, standard summary statistics from CPETs, and mathematical features extracted from the breath-by-breath time series of 13 measurements. The primary outcome was a composite of death, heart transplant, or mechanical circulatory support treated as a time-to-event outcomes. Predictive features ranked as most important included many of the features engineered from the breath-by-breath data in addition to traditional clinical risk factors. The prediction model showed excellent performance in predicting the composite outcome with an area under the curve of 0.93 in the training and 0.87 in the validation data sets. Both the predicted vs. actual freedom from the composite outcome and the calibration of the prediction model were excellent. Model performance remained stable in multiple subgroups of patients. Conclusion: Using a combined deep learning and survival algorithm, integrating breath-by-breath data from CPETs resulted in improved predictive accuracy for long-term (up to 10 years) outcomes in HF. DeepSurv opens the door for future prediction models that are both highly performing and can more fully use the large and complex quantity of data generated during the care of patients with HF.

Quantification of the environmental impact of radiotherapy and associated secondary human health effects: a multi-institutional retrospective analysis and simulation.

BACKGROUND: The health-care industry is a substantial contributor to global greenhouse gas emissions, yet the specific environmental impact of radiotherapy, a cornerstone of cancer treatment, remains under-explored. We aimed to quantify the emissions associated with the delivery of radiotherapy in the USA and propose a framework for reducing the environmental impact of oncology care. METHODS: In this multi-institutional retrospective analysis and simulation study, we conducted a lifecycle assessment of external beam radiotherapy (EBRT) for ten anatomical disease sites, adhering to the International Organization for Standardization's standards ISO 14040 and ISO 14044. We analysed retrospective data from Jan 1, 2017, to Oct 1, 2023, encompassing patient and staff travel, medical supplies, and equipment and building energy use associated with the use of EBRT at four academic institutions in the USA. The primary objective was to measure the environmental impacts across ten categories: greenhouse gases (expressed as kg of carbon dioxide equivalents [CO2e]), ozone depletion, smog formation, acidification, eutrophication, carcinogenic and non-carcinogenic potential, respiratory effects, fossil fuel depletion, and ecotoxicity. Human health effects secondary to these environmental impacts were also estimated as disability-adjusted life years. We also assessed the potential benefits of hypofractionated regimens for breast and genitourinary (ie, prostate and bladder) cancers on US greenhouse gas emissions using an analytic model based on the 2014 US National Cancer Database for fractionation patterns and patient commute distances. FINDINGS: We estimated that the mean greenhouse gas emissions associated with a standard 25-fraction EBRT course were 4310 kg CO2e (SD 2910), which corresponded to 0·0035 disability-adjusted life years per treatment course. Transit and building energy usage accounted for 25·73% (1110 kg CO2e) and 73·95% of (3190 kg CO2e) of total greenhouse gas emissions, respectively, whereas supplies contributed only 0·32% (14 kg CO2e). Across the other environmental impact categories, most of the environmental impact also stemmed from patient transit and energy use within facilities, with little environmental impact contributed by supplies used. Hypofractionated treatment simulations suggested a substantial reduction in greenhouse gas emissions-by up to 42% for breast and 77% for genitourinary cancer-and environmental impacts more broadly. INTERPRETATION: This comprehensive lifecycle assessment of EBRT delineates the environmental and secondary health impacts of radiotherapy, and underscores the urgent need for sustainable practices in oncology. The findings serve as a reference for future decarbonisation efforts in cancer care and show the potential environmental benefits of modifying treatment protocols (when clinical equipoise exists). They also highlight strategic opportunities to mitigate the ecological footprint in an era of escalating climate change and increasing cancer prevalence. FUNDING: Mount Zion Health Fund.

Data Quality Degradation on Prediction Models Generated From Continuous Activity and Heart Rate Monitoring: Exploratory Analysis Using Simulation.

BACKGROUND: Limited data accuracy is often cited as a reason for caution in the integration of physiological data obtained from consumer-oriented wearable devices in care management pathways. The effect of decreasing accuracy on predictive models generated from these data has not been previously investigated. OBJECTIVE: The aim of this study is to simulate the effect of data degradation on the reliability of prediction models generated from those data and thus determine the extent to which lower device accuracy might or might not limit their use in clinical settings. METHODS: Using the Multilevel Monitoring of Activity and Sleep in Healthy People data set, which includes continuous free-living step count and heart rate data from 21 healthy volunteers, we trained a random forest model to predict cardiac competence. Model performance in 75 perturbed data sets with increasing missingness, noisiness, bias, and a combination of all 3 perturbations was compared to model performance for the unperturbed data set. RESULTS: The unperturbed data set achieved a mean root mean square error (RMSE) of 0.079 (SD 0.001) in predicting cardiac competence index. For all types of perturbations, RMSE remained stable up to 20%-30% perturbation. Above this level, RMSE started increasing and reached the point at which the model was no longer predictive at 80% for noise, 50% for missingness, and 35% for the combination of all perturbations. Introducing systematic bias in the underlying data had no effect on RMSE. CONCLUSIONS: In this proof-of-concept study, the performance of predictive models for cardiac competence generated from continuously acquired physiological data was relatively stable with declining quality of the source data. As such, lower accuracy of consumer-oriented wearable devices might not be an absolute contraindication for their use in clinical prediction models.

A Phase I Trial of Neoadjuvant Stereotactic Body Radiotherapy Prior to Radical Prostatectomy for Locally Advanced Prostate Cancer.

PURPOSE: Men with locally advanced prostate cancer who undergo radical prostatectomy (RP) often develop recurrence and require postoperative radiotherapy. We aimed to determine the safety of neoadjuvant stereotactic body radiotherapy (SBRT) before RP in this population. METHODS AND PATIENTS: A single-institution phase 1 trial (NCT02946008) of men with high-risk or node-positive prostate cancer were enrolled between March and October 2017. The primary endpoint was to determine the maximum tolerated dose of SBRT based on a composite 30-day post-RP toxicity goal of ≤28% of patients experiencing a dose-limiting toxicity (DLT). Secondary outcomes included toxicity, efficacy, and multiple quality of life (QoL) inventories. SBRT (30-35 Gy/5 fractions) was delivered to the prostate and seminal vesicles, and 25 Gy/5 fractions to the pelvic lymph nodes. RP was performed for a median of 6 weeks post-SBRT. Hormone therapy was not allowed. RESULTS: Median follow-up was 40 months (range, 33-44). Twenty-five percent of the patients (n = 4) experienced a DLT within 30 days post-RP; however, the trial was stopped early (n = 16 of planned 38 patients) owing to the proportion and severity of the late adverse events. Post-RP grade 3 genitourinary and gastrointestinal toxicities occurred in 75% (n = 12) and 25% (n = 4) of patients, respectively. Two patients required cystectomy and urinary diversion ≥2 years post-RP. At 24 months post-RP, 75% (n = 12) of men used ≥1 pad/d and 0% had erections suitable for intercourse. Surgical margins were negative in all patients and 31% (n = 5) had complete or partial (pre-RP) MRI-response to SBRT. Three-year biochemical recurrence and distant metastasis were 45% (95% CI, 5%-68%) and 28% (95% CI, 0%-49%), respectively. CONCLUSIONS: Neoadjuvant SBRT followed by RP resulted in unacceptably high toxicity and severe QoL declines.

Phase II Randomized Study of Salvage Radiation Therapy Plus Enzalutamide or Placebo for High-Risk Prostate-Specific Antigen Recurrent Prostate Cancer After Radical Prostatectomy: The SALV-ENZA Trial.

PURPOSE: We sought to investigate whether enzalutamide (ENZA), without concurrent androgen deprivation therapy, increases freedom from prostate-specific antigen (PSA) progression (FFPP) when combined with salvage radiation therapy (SRT) in men with recurrent prostate cancer after radical prostatectomy (RP). PATIENTS AND METHODS: Men with biochemically recurrent prostate cancer after RP were enrolled into a randomized, double-blind, phase II, placebo-controlled, multicenter study of SRT plus ENZA or placebo (ClinicalTrials.gov identifier: NCT02203695). Random assignment (1:1) was stratified by center, surgical margin status (R0 v R1), PSA before salvage treatment (PSA ≥ 0.5 v < 0.5 ng/mL), and pathologic Gleason sum (7 v 8-10). Patients were assigned to receive either ENZA 160 mg once daily or matching placebo for 6 months. After 2 months of study drug therapy, external-beam radiation (66.6-70.2 Gy) was administered to the prostate bed (no pelvic nodes). The primary end point was FFPP in the intention-to-treat population. Secondary end points were time to local recurrence within the radiation field, metastasis-free survival, and safety as determined by frequency and severity of adverse events. RESULTS: Eighty-six (86) patients were randomly assigned, with a median follow-up of 34 (range, 0-52) months. Trial arms were well balanced. The median pre-SRT PSA was 0.3 (range, 0.06-4.6) ng/mL, 56 of 86 patients (65%) had extraprostatic disease (pT3), 39 of 86 (45%) had a Gleason sum of 8-10, and 43 of 86 (50%) had positive surgical margins (R1). FFPP was significantly improved with ENZA versus placebo (hazard ratio [HR], 0.42; 95% CI, 0.19 to 0.92; P = .031), and 2-year FFPP was 84% versus 66%, respectively. Subgroup analyses demonstrated differential benefit of ENZA in men with pT3 (HR, 0.22; 95% CI, 0.07 to 0.69) versus pT2 disease (HR, 1.54; 95% CI, 0.43 to 5.47; Pinteraction = .019) and R1 (HR, 0.14; 95% CI, 0.03 to 0.64) versus R0 disease (HR, 1.00; 95% CI, 0.36 to 2.76; Pinteraction = .023). There were insufficient secondary end point events for analysis. The most common adverse events were grade 1-2 fatigue (65% ENZA v 53% placebo) and urinary frequency (40% ENZA v 49% placebo). CONCLUSION: SRT plus ENZA monotherapy for 6 months in men with PSA-recurrent high-risk prostate cancer after RP is safe and delays PSA progression relative to SRT alone. The impact of ENZA on distant metastasis or survival is unknown at this time.

A digital self-care intervention for Ugandan patients with heart failure and their clinicians: User-centred design and usability study.

Background: The prevalence of heart failure (HF) is increasing in Uganda. Ugandan patients with HF report receiving limited information about their illness and associated self-care behaviours. Interventions targeted at improving HF self-care have been shown to improve patient quality of life and reduce hospitalizations in high-income countries. However, such interventions remain underutilized in resource-limited settings like Uganda. This study aimed to develop a digital health intervention that enables improved self-care amongst HF patients in Uganda. Methods: We implemented a user-centred design (UCD) process to develop a self-care intervention entitled Medly Uganda. The ideation phase comprised a scoping review and preliminary data collection amongst HF patients and clinicians in Uganda. An iterative design process was then used to advance an initial prototype into a functional digital health intervention. The evaluation phase involved usability testing of the intervention amongst Ugandan patients with HF and their clinicians. Results: Medly Uganda is a digital health intervention that allows patients to report daily HF symptoms, receive tailored treatment advice and connect with a clinician when showing signs of decompensation. The system harnesses Unstructured Supplementary Service Data (USSD) technology that is already widely used in Uganda for mobile phone-based financial transactions. Usability testing showed Medly Uganda to be both acceptable and feasible amongst clinicians, patients and caregivers. Conclusions: Medly Uganda is a functional digital health intervention with demonstrated acceptability and feasibility in enabling Ugandan HF patients to better care for themselves. We are hopeful that the system will improve self-care efficacy amongst HF patients in Uganda.

TrueNTH Sexual Recovery Intervention for couples coping with prostate cancer: Randomized controlled trial results.

BACKGROUND: Despite significant sexual dysfunction and distress after localized prostate cancer treatment, patients typically receive only physiologic erectile dysfunction management. The authors performed a randomized controlled trial of an online intervention supporting couples' posttreatment recovery of sexual intimacy. METHODS: Patients treated with surgery, radiation, or combined radiation and androgen deprivation therapy who had partners were recruited and randomized to an online intervention or a control group. The intervention, tailored to treatment type and sexual orientation, comprised 6 modules addressing expectations for sexual and emotional sequelae of treatment, rehabilitation, and guidance toward sexual intimacy recovery. Couples, recruited from 6 sites nationally, completed validated measures at the baseline and 3 and 6 months after treatment. Primary outcome group differences were assessed with t tests for individual outcomes. RESULTS: Among 142 randomized couples, 105 patients (mostly surgery) and 87 partners completed the 6-month survey; this reflected challenges with recruitment and attrition. There were no differences between the intervention and control arms in Patient-Reported Outcomes Measurement Information System Global Satisfaction With Sex Life scores 6 months after treatment (the primary outcome). Three months after treatment, intervention patients and partners reported more engagement in penetrative and nonpenetrative sexual activities than controls. More than 73% of the intervention participants reported high or moderate satisfaction with module content; more than 85% would recommend the intervention to other couples. CONCLUSIONS: Online psychosexual support for couples can help couples to connect and experience sexual pleasure early after treatment despite patients' sexual dysfunction. Participants' high endorsement of the intervention reflects the importance of sexual health support to couples after prostate cancer treatment. LAY SUMMARY: This study tested a web-based program supporting couples' sexual recovery of sexual intimacy after prostate cancer treatment. One hundred forty-two couples were recruited and randomly assigned to the program (n = 60) or to a control group (n = 82). The program did not result in improvements in participants' satisfaction with their sex life 6 months after treatment, but couples in the intervention group engaged in sexual activity sooner after treatment than couples in the control group. Couples evaluated the program positively and would recommend it to others facing prostate cancer treatment.

Integrating Prostate-specific Antigen Kinetics into Contemporary Predictive Nomograms of Salvage Radiotherapy After Radical Prostatectomy.

BACKGROUND: Salvage radiotherapy (SRT) is an established treatment for men with biochemical recurrence following radical prostatectomy (RP). There are several risk factors associated with adverse outcomes; however, the value of postoperative prostate-specific antigen (PSA) kinetics is less clear in the ultrasensitive PSA era. OBJECTIVE: To characterize the impact of PSA kinetics on outcomes following SRT and generate nomograms to aid in identifying patients with an increased risk of adverse clinical outcomes. DESIGN, SETTING, AND PARTICIPANTS: A multi-institutional analysis was conducted of 1005 patients with prostate cancer treated with SRT after RP, with a median follow-up of 5 years. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Variables examined include immediate postoperative PSA, postoperative PSA doubling time (DT), and pre-SRT PSA, in addition to previously identified predictive factors. Multivariable survival analyses were completed using Fine-Gray competing risk regression. Rates of biochemical failure (BF), distant metastasis (DM), and prostate cancer-specific mortality (PCSM) were estimated by the cumulative incidence method. Nomograms were generated from multivariable competing risk regression with bootstrap cross-validation. RESULTS AND LIMITATIONS: Factors associated with BF after SRT include PSA DT <6 mo, initial postoperative PSA ≥0.2 ng/ml, higher pre-SRT PSA, lack of androgen deprivation therapy, a higher Gleason score (GS), negative margins, seminal vesicle invasion, lack of pelvic nodal radiation, radiation total dose <66 Gy, a longer RP to SRT interval, and older age (p < 0.05 for each). Factors associated with DM include PSA DT <6 mo, pre-SRT PSA, a higher GS, and negative margins. Factors associated with PCSM include PSA DT not calculable or <6 mo and a higher GS. Nomograms were generated to estimate the risks of BF (concordance index [CI] 0.74), DM (CI 0.77), and PCSM (CI 0.77). Limitations include retrospective nature, broad treatment eras, institutional variations, and multiple methods available for the estimation of PSA DT. CONCLUSIONS: Postoperative PSA kinetics, particularly pre-SRT PSA and PSA DT, are strongly associated with adverse oncologic outcomes following SRT and should be considered in management decisions. PATIENT SUMMARY: In this report of men with prostate cancer who developed a prostate-specific antigen (PSA) recurrence after prostatectomy, we found that PSA levels after surgery and how quickly a PSA level doubles significantly impact the chance of prostate cancer recurrence after salvage radiation therapy. Based on this information, we created a tool to calculate a man's chance of cancer recurrence after salvage radiation therapy, and these estimations can be used to discuss whether additional treatment with radiation should be considered.

A Comprehensive Assessment of 68Ga-PSMA-11 PET in Biochemically Recurrent Prostate Cancer: Results from a Prospective Multicenter Study on 2,005 Patients.

We prospectively investigated the performance of the prostate-specific membrane antigen (PSMA) ligand 68Ga-PSMA-11 for detecting prostate adenocarcinoma in patients with elevated levels of prostate-specific antigen (PSA) after initial therapy. Methods:68Ga-PSMA-11 hybrid PET was performed on 2,005 patients at the time of biochemically recurrent prostate cancer after radical prostatectomy (RP) (50.8%), definitive radiation therapy (RT) (19.7%), or RP with postoperative RT (PORT) (29.6%). The presence of prostate cancer was assessed qualitatively (detection rate = positivity rate) and quantitatively on a per-patient and per-region basis, creating a disease burden estimate from the presence or absence of local (prostate/prostate bed), nodal (N1: pelvis), and distant metastatic (M1: distant soft tissue and bone) disease. The primary study endpoint was the positive predictive value (PPV) of 68Ga-PSMA-11 PET/CT confirmed by histopathology. Results: After RP, the scan detection rate increased significantly with rising PSA level (44.8% at PSA < 0.25%-96.2% at PSA > 10 ng/mL; P < 0.001). The detection rate significantly increased with rising PSA level in each individual region, overall disease burden, prior androgen deprivation, clinical T-stage, and Gleason grading from the RP specimen (P < 0.001). After RT, the detection rate for in-gland prostate recurrence was 64.0%, compared with 20.6% prostate bed recurrence after RP and 13.3% after PORT. PSMA-positive pelvic nodal disease was detected in 42.7% after RP, 40.8% after PORT, and 38.8% after RT. In patients with histopathologic validation, the PPV per patient was 0.82 (146/179). The SUVmax of histologically proven true-positive lesions was significantly higher than that of false-positive lesions (median, 11.0 [interquartile range, 6.3-22.2] vs. 5.1 [interquartile range, 2.2-7.4]; P < 0.001). Conclusion: We confirmed a high PPV for 68Ga-PSMA-11 PET in biochemical recurrence and the PSA level as the main predictor of scan positivity.

Megavolt bremsstrahlung measurements from linear induction accelerators demonstrate possible use as a FLASH radiotherapy source to reduce acute toxicity.

Recent studies indicate better efficacy and healthy tissue sparing with high dose-rate FLASH radiotherapy (FLASH-RT) cancer treatment. This technique delivers a prompt high radiation dose rather than fractional doses over time. While some suggest thresholds of > 40 Gy s-1 with a maximal effect at > 100 Gy s-1, accumulated evidence shows that instantaneous dose-rate and irradiation time are critical. Mechanisms are still debated, but toxicity is minimized while inducing apoptosis in malignant tissue. Delivery technologies to date show that a capability gap exists with clinic scale, broad area, deep penetrating, high dose rate systems. Based on these trends, if FLASH-RT is adopted, it may become a dominant approach except in the least technologically advanced countries. The linear induction accelerator (LIA) developed for high instantaneous and high average dose-rate, species independent charged particle acceleration, has yet to be considered for this application. We review the status of LIA technology, explore the physics of bremsstrahlung-converter-target interactions and our work on stabilizing the electron beam. While the gradient of the LIA is low, we present our preliminary work to improve the gradient by an order of magnitude, presenting a point design for a multibeam FLASH-RT system using a single accelerator for application to conformal FLASH-RT.

Prostate radiotherapy in the setting of bilateral hip prostheses: All commonly used photon-based radiation approaches are feasible.

The prevalence of hip prostheses is increasing. Prostate radiation delivery in the setting of hip prostheses is complicated by both imaging artifacts that interfere with volume delineation and dosimetric effects that must be addressed in the planning process. We hypothesized that with specialized planning, any photon-based definitive prostate radiotherapy approach may be utilized in patients with bilateral hip prostheses. Imaging data from sequential patients with prostate cancer and bilateral hip prostheses treated definitively with radiation were retrospectively reviewed. Bimodality imaging was used to define targets and organs at risk (OARs) along with specialized MRI sequences and/or orthopedic metal artifact reduction (OMAR) for MRI and CT artifact suppression, respectively. Multiple VMAT plans were generated for each set of patient images to include three fractionation schemes (conventional, hypofractionated, and SBRT), each with hip avoidance and with simulated normal hip. The ability to meet standard dose constraints was assessed for each plan type. Differences in target and OAR dosing between plans accounting for prosthetic hips via avoidance vs plans with simulated absence of prosthetic hip were also assessed. T-tests were used to compare dosimetric parameters. Ten patients with bilateral hip prostheses were identified, and 6 plans were created for each patient for a total of 60 radiation plans. Prosthetic hip avoidance did not result in failure to meet dose constraints for any patient. Hip avoidance resulted in minimal increases in high dose to the rectum and bladder (increases in mean V80%, V90%, and V95% ranged from 0.1% to 2.4%). Larger increases were seen at lower dose levels, with rectal V50% significantly increased in all three plan types with hip avoidance (conventional: 26.0% [standard deviation, SD 13.9] vs 16.9% [SD 10.2, p = 0.003]; hypofractionation: 26.4% [SD 13.3] vs 17.1% [SD 10.1, p = 0.002]; SBRT: 18.3% [SD 10.7] vs 10.5% [SD 6.9, p = 0.008]). Similarly, hip avoidance resulted in increases in bladder V50% to 31.7% (SD 16.8) vs 23.3% (SD 14.0, p = 0.001), 31.3% (SD 17.0) vs 23.3% (SD 13.8, p = 0.002), and 22.7% (SD 12.3) vs 16.5% (SD 12.6, p < 0.001) for conventional, hypofractionated, and SBRT plans, respectively. Hydrogel spacer resulted in reductions in rectal dose. For example, V70% for hip avoidance plans decreased with spacer presence to 8.3% (SD 6.7) vs 21.1% (SD 5.8, p = 0.021), 8.6% (SD 6.5) vs 21% (SD 5.7, p = 0.022), and 3.7% (SD 3.2) vs 15% (SD 8.2, p = 0.010) for conventional, hypofractionated, and SBRT plans, respectively. Any photon-based definitive prostate radiotherapy approach can be used with bimodality imaging for target and OAR definition and planning techniques to avoid dose attenuation effects of hip prostheses. Hydrogel spacer is a useful adjunct.

Virtual care for prostate cancer survivorship: protocol for an evaluation of a nurse-led algorithm-enhanced virtual clinic implemented at five cancer centres across Canada.

INTRODUCTION: Prostate cancer (PCa) is the most common cancer in Canadian men. Current models of survivorship care are no longer adequate to address the chronic and complex survivorship needs of patients today. Virtual care models for cancer survivorship have recently been associated with comparable clinical outcomes and lower costs to traditional follow-up care, with patients favouring off-site and on-demand visits. Building on their viability, our research group conceived the Ned Clinic-a virtual PCa survivorship model that provides patients with access to lab results, collects patient-reported outcomes, alerts clinicians to emerging issues, and promotes patient self-care. Despite the promise of the Ned Clinic, the model remains limited by its dependence on oncology specialists, lack of an autonomous triage algorithm, and has only been implemented among PCa survivors living in Ontario. METHODS AND ANALYSIS: Our programme of research comprises two main research objectives: (1) to evaluate the process and cost of implementing and sustaining five nurse-led virtual PCa survivorship clinics in three provinces across Canada and identify barriers and facilitators to implementation success and (2) to assess the impact of these virtual clinics on implementation and effectiveness outcomes of enrolled PCa survivors. The design phase will involve developing an autonomous triage algorithm and redesigning the Ned Clinic towards a nurse-led service model. Site-specific implementation plans will be developed to deploy a localised nurse-led virtual clinic at each centre. Effectiveness will be evaluated using a historical control study comparing the survivorship outcomes of 300 PCa survivors enrolled in the Ned Clinic with 300 PCa survivors receiving traditional follow-up care. ETHICS AND DISSEMINATION: Appropriate site-specific ethics approval will be secured prior to each research phase. Knowledge translation efforts will include diffusion, dissemination, and application approaches to ensure that knowledge is translated to both academic and lay audiences.

The Need for Ethnoracial Equity in Artificial Intelligence for Diabetes Management: Review and Recommendations.

There is clear evidence to suggest that diabetes does not affect all populations equally. Among adults living with diabetes, those from ethnoracial minority communities-foreign-born, immigrant, refugee, and culturally marginalized-are at increased risk of poor health outcomes. Artificial intelligence (AI) is actively being researched as a means of improving diabetes management and care; however, several factors may predispose AI to ethnoracial bias. To better understand whether diabetes AI interventions are being designed in an ethnoracially equitable manner, we conducted a secondary analysis of 141 articles included in a 2018 review by Contreras and Vehi entitled "Artificial Intelligence for Diabetes Management and Decision Support: Literature Review." Two members of our research team independently reviewed each article and selected those reporting ethnoracial data for further analysis. Only 10 articles (7.1%) were ultimately selected for secondary analysis in our case study. Of the 131 excluded articles, 118 (90.1%) failed to mention participants' ethnic or racial backgrounds. The included articles reported ethnoracial data under various categories, including race (n=6), ethnicity (n=2), race/ethnicity (n=3), and percentage of Caucasian participants (n=1). Among articles specifically reporting race, the average distribution was 69.5% White, 17.1% Black, and 3.7% Asian. Only 2 articles reported inclusion of Native American participants. Given the clear ethnic and racial differences in diabetes biomarkers, prevalence, and outcomes, the inclusion of ethnoracial training data is likely to improve the accuracy of predictive models. Such considerations are imperative in AI-based tools, which are predisposed to negative biases due to their black-box nature and proneness to distributional shift. Based on our findings, we propose a short questionnaire to assess ethnoracial equity in research describing AI-based diabetes interventions. At this unprecedented time in history, AI can either mitigate or exacerbate disparities in health care. Future accounts of the infancy of diabetes AI must reflect our early and decisive action to confront ethnoracial inequities before they are coded into our systems and perpetuate the very biases we aim to eliminate. If we take deliberate and meaningful steps now toward training our algorithms to be ethnoracially inclusive, we can architect innovations in diabetes care that are bound by the diverse fabric of our society.

Development of a 3D-printed testicular cancer model for testicular examination education.

INTRODUCTION: Testicular cancer is the most commonly diagnosed malignancy in young males. Testicular examination is a non-invasive and inexpensive means of detecting testicular cancer at an early stage. In this project, a set of 3D-printed models was developed to facilitate teaching testicular examination and improving understanding of testicular malignancies among patients and medical learners. METHODS: Five scrotum models were designed: a control model with healthy testes, and four models containing a healthy testicle and a testicle with an endophytic mass of varying size. The anatomy, texture, and composition of the 3D-printed models were refined using an iterative process between the design team and urologists. The completed models were assessed by six urologists, two urology nurse practitioners, and 32 medical learners. Participants were asked to inspect and palpate each model, and to provide feedback using a five-point Likert scale. RESULTS: Clinicians reported that the models enabled accurate simulation of a testicular examination involving both healthy and pathologic testes (χ̄=4.3±1.0). They agreed that the models would be useful teaching tools for both medical learners (χ̄=4.8±0.5) and patients (χ̄=4.8±0.7). Following an educational session with the models, medical learners reported improvements in confidence and skill in performing a testicular examination. CONCLUSIONS: 3D-printed models can effectively simulate palpation of both healthy and pathologic testes. The developed models have the potential to be a useful adjunct in teaching testicular examination and in demonstrating abnormal findings that require further investigation.

Development and Validation of a Clinical Prognostic Stage Group System for Nonmetastatic Prostate Cancer Using Disease-Specific Mortality Results From the International Staging Collaboration for Cancer of the Prostate.

Importance: In 2016, the American Joint Committee on Cancer (AJCC) established criteria to evaluate prediction models for staging. No localized prostate cancer models were endorsed by the Precision Medicine Core committee, and 8th edition staging was based on expert consensus. Objective: To develop and validate a pretreatment clinical prognostic stage group system for nonmetastatic prostate cancer. Design, Setting, and Participants: This multinational cohort study included 7 centers from the United States, Canada, and Europe, the Shared Equal Access Regional Cancer Hospital (SEARCH) Veterans Affairs Medical Centers collaborative (5 centers), and the Cancer of the Prostate Strategic Urologic Research Endeavor (CaPSURE) registry (43 centers) (the STAR-CAP cohort). Patients with cT1-4N0-1M0 prostate adenocarcinoma treated from January 1, 1992, to December 31, 2013 (follow-up completed December 31, 2017). The STAR-CAP cohort was randomly divided into training and validation data sets; statisticians were blinded to the validation data until the model was locked. A Surveillance, Epidemiology, and End Results (SEER) cohort was used as a second validation set. Analysis was performed from January 1, 2018, to November 30, 2019. Exposures: Curative intent radical prostatectomy (RP) or radiotherapy with or without androgen deprivation therapy. Main Outcomes and Measures: Prostate cancer-specific mortality (PCSM). Based on a competing-risk regression model, a points-based Score staging system was developed. Model discrimination (C index), calibration, and overall performance were assessed in the validation cohorts. Results: Of 19 684 patients included in the analysis (median age, 64.0 [interquartile range (IQR), 59.0-70.0] years), 12 421 were treated with RP and 7263 with radiotherapy. Median follow-up was 71.8 (IQR, 34.3-124.3) months; 4078 (20.7%) were followed up for at least 10 years. Age, T category, N category, Gleason grade, pretreatment serum prostate-specific antigen level, and the percentage of positive core biopsy results among biopsies performed were included as variables. In the validation set, predicted 10-year PCSM for the 9 Score groups ranged from 0.3% to 40.0%. The 10-year C index (0.796; 95% CI, 0.760-0.828) exceeded that of the AJCC 8th edition (0.757; 95% CI, 0.719-0.792), which was improved across age, race, and treatment modality and within the SEER validation cohort. The Score system performed similarly to individualized random survival forest and interaction models and outperformed National Comprehensive Cancer Network (NCCN) and Cancer of the Prostate Risk Assessment (CAPRA) risk grouping 3- and 4-tier classification systems (10-year C index for NCCN 3-tier, 0.729; for NCCN 4-tier, 0.746; for Score, 0.794) as well as CAPRA (10-year C index for CAPRA, 0.760; for Score, 0.782). Conclusions and Relevance: Using a large, diverse international cohort treated with standard curative treatment options, a proposed AJCC-compliant clinical prognostic stage group system for prostate cancer has been developed. This system may allow consistency of reporting and interpretation of results and clinical trial design.

Virtual care models for cancer survivorship.

Virtual care models for cancer survivorship are needed to support patients living with the chronic effects of cancer treatment, while increasing health system capacity. Characteristics that may be critical to their success have not been adequately studied. This scoping review summarizes previous efforts to virtualize survivorship care to inform future innovations in the field. Four databases were searched for articles published before January 2020, and 24 articles that met selection criteria were included in this analysis. Rationale for pursuing virtual models of care shared two common objectives: (1) the need for sustainable survivorship care, and (2) the opportunity to improve survivorship outcomes. Breast cancer (N = 10) and prostate cancer (N = 4) were the most targeted cancers for virtual survivorship care. The implemented technologies included web platforms (N = 15), telephone calls (N = 12), and smartphone or tablet applications (N = 5). A variety of healthcare professionals were effectively involved in the provision of virtual care. Future virtual care models may benefit from integrating with existing health systems and services, repurposing common technologies, involving allied health professionals, and engaging patients and caregivers from diverse communities in the design of virtual services.

Lived Experiences and Technological Literacy of Heart Failure Patients and Clinicians at a Cardiac Care Centre in Uganda.

Background: Digital health could serve as a low-cost means of enabling better self-care in patients living with heart failure (HF) in resource-limited settings such as Uganda. However, digital health interventions previously deployed in such settings have been unsuccessful due to a lack of local patient and clinician engagement in the design process. Objective: To engage Ugandan HF patients and clinicians regarding their experiences with HF management and technology, so as to inform the future design of a digital health intervention for HF patients in Uganda. Methods: The study employed a convergent parallel mixed-methods design. Data collection was completed at the Uganda Heart Institute in Kampala, Uganda. Data were ascertained through a patient survey and semi-structured interviews completed with HF patients, caregivers, physicians, and nurses. A conventional content analysis approach was used to qualitatively examine interview transcripts. Findings: Survey data were collected from 101 HF patients (62 female/39 male, aged 54.2 ± 17.5 years). Nearly half (48%) disagreed that they knew what to do in response to changes in their HF symptoms. Almost all patients (98%) had access to a mobile device. Many patients (63%) identified as comfortable in using mobile money - a local set of services that use Unstructured Supplementary Service Data (USSD). Interviews were completed with 19 HF patients, three caregivers, seven physicians, and three nurses. Qualitative analysis revealed four clusters of themes: overdependence of patients on the clinic, inconvenience associated with attending the clinic, inconsistent patient self-care behaviours at home, and technological abilities that favoured USSD-based services. Conclusions: Ugandan HF patients possess unmet information needs that leave them ill-equipped to care for themselves. Future digital health interventions for this population should empower patients with HF-specific information and reassurance in their self-care abilities. Based on patient preferences, such systems should harness USSD technology with which most patients are already comfortable.

Nephroureterectomy of Right-to-Left Crossed Fused Renal Ectopia with Urothelial Carcinoma.

Urothelial carcinoma in a crossed fused renal ectopia (CFRE) is an exceedingly rare clinical finding. We describe the surgical management used to treat upper tract urothelial carcinoma in a 64-year-old man with a right-to-left CFRE. Nephroureterectomy with bladder cuff excision was the treatment of choice. The fused kidney was carefully dissected until an area of demarcation emerged between the vasculature supplying the left and right moieties. Pressure was applied to the isthmus separating the two moieties, and a sharp incision was made to release the left moiety. The operation was completed with limited blood loss. Pathology revealed a high-grade T3 papillary urothelial carcinoma with negative margins. To our knowledge, the case is the first to report urothelial carcinoma in a right-to-left CFRE.

Addition of Androgen-Deprivation Therapy or Brachytherapy Boost to External Beam Radiotherapy for Localized Prostate Cancer: A Network Meta-Analysis of Randomized Trials.

PURPOSE: In men with localized prostate cancer, the addition of androgen-deprivation therapy (ADT) or a brachytherapy boost (BT) to external beam radiotherapy (EBRT) have been shown to improve various oncologic end points. Practice patterns indicate that those who receive BT are significantly less likely to receive ADT, and thus we sought to perform a network meta-analysis to compare the predicted outcomes of a randomized trial of EBRT plus ADT versus EBRT plus BT. MATERIALS AND METHODS: A systematic review identified published randomized trials comparing EBRT with or without ADT, or EBRT (with or without ADT) with or without BT, that reported on overall survival (OS). Standard fixed-effects meta-analyses were performed for each comparison, and a meta-regression was conducted to adjust for use and duration of ADT. Network meta-analyses were performed to compare EBRT plus ADT versus EBRT plus BT. Bayesian analyses were also performed, and a rank was assigned to each treatment after Markov Chain Monte Carlo analyses to create a surface under the cumulative ranking curve. RESULTS: Six trials compared EBRT with or without ADT (n = 4,663), and 3 compared EBRT with or without BT (n = 718). The addition of ADT to EBRT improved OS (hazard ratio [HR], 0.71 [95% CI, 0.62 to 0.81]), whereas the addition of BT did not significantly improve OS (HR, 1.03 [95% CI, 0.78 to 1.36]). In a network meta-analysis, EBRT plus ADT had improved OS compared with EBRT plus BT (HR, 0.68 [95% CI, 0.52 to 0.89]). Bayesian modeling demonstrated an 88% probability that EBRT plus ADT resulted in superior OS compared with EBRT plus BT. CONCLUSION: Our findings suggest that current practice patterns of omitting ADT with EBRT plus BT may result in inferior OS compared with EBRT plus ADT in men with intermediate- and high-risk prostate cancer. ADT for these men should remain a critical component of treatment regardless of radiotherapy delivery method until randomized evidence demonstrates otherwise.

HSD3B1 Genotype and Clinical Outcomes in Metastatic Castration-Sensitive Prostate Cancer.

Importance: The adrenal-restrictive HSD3B1(1245A) allele limits extragonadal dihydrotestosterone synthesis, whereas the adrenal-permissive HSD3B1(1245C) allele augments extragonadal dihydrotestosterone synthesis. Retrospective studies have suggested an association between the adrenal-permissive allele, the frequency of which is highest in white men, and early development of castration-resistant prostate cancer (CRPC). Objective: To examine the association between the adrenal-permissive HSD3B1(1245C) allele and early development of CRPC using prospective data. Design, Setting, and Participants: The E3805 Chemohormonal Therapy vs Androgen Ablation Randomized Trial for Extensive Disease in Prostate Cancer (CHAARTED) was a large, multicenter, phase 3 trial of castration with or without docetaxel treatment in men with newly diagnosed metastatic prostate cancer. From July 28, 2006, through December 31, 2012, 790 patients underwent randomization, of whom 527 had available DNA samples. In this study, the HSD3B1 germline genotype was retrospectively determined in 475 white men treated in E3805 CHAARTED, and clinical outcomes were analyzed by genotype. Data analysis was performed from July 28, 2006, to October 17, 2018. Interventions: Men were randomized to castration plus docetaxel, 75 mg/m2, every 3 weeks for 6 cycles or castration alone. Main Outcomes and Measures: Two-year freedom from CRPC and 5-year overall survival, with results stratified by disease volume. Patients were combined across study arms according to genotype to assess the overall outcome associated with genotype. Secondary analyses by treatment arm evaluated whether the docetaxel outcome varied with genotype. Results: Of 475 white men with DNA samples, 270 patients (56.8%) inherited the adrenal-permissive genotype (≥1 HSD3B1[1245C] allele). Mean (SD) age was 63 (8.7) years. Freedom from CRPC at 2 years was diminished in men with low-volume disease with the adrenal-permissive vs adrenal-restrictive genotype: 51.0% (95% CI, 40.9%-61.2%) vs 70.5% (95% CI, 60.0%-80.9%) (P = .01). Overall survival at 5 years was also worse in men with low-volume disease with the adrenal-permissive genotype: 57.5% (95% CI, 47.4%-67.7%) vs 70.8% (95% CI, 60.3%-81.3%) (P = .03). Hazard ratios were 1.89 (95% CI, 1.13-3.14; P = .02) for CRPC and 1.74 (95% CI, 1.01-3.00; P = .045) for death. There was no association between genotype and outcomes in men with high-volume disease. There was no interaction between genotype and benefit from docetaxel. Conclusions and Relevance: Inheritance of the adrenal-permissive HSD3B1 genotype is associated with earlier castration resistance and shorter overall survival in men with low-volume metastatic prostate cancer and may help identify men more likely to benefit from escalated androgen receptor axis inhibition beyond gonadal testosterone suppression.