Clinical-transcriptional prioritization of the circulating proteome in human heart failure.

Given expanding studies in epidemiology and disease-oriented human studies offering hundreds of associations between the human "ome" and disease, prioritizing molecules relevant to disease mechanisms among this growing breadth is important. Here, we link the circulating proteome to human heart failure (HF) propensity (via echocardiographic phenotyping and clinical outcomes) across the lifespan, demonstrating key pathways of fibrosis, inflammation, metabolism, and hypertrophy. We observe a broad array of genes encoding proteins linked to HF phenotypes and outcomes in clinical populations dynamically expressed at a transcriptional level in human myocardium during HF and cardiac recovery (several in a cell-specific fashion). Many identified targets do not have wide precedent in large-scale genomic discovery or human studies, highlighting the complementary roles for proteomic and tissue transcriptomic discovery to focus epidemiological targets to those relevant in human myocardium for further interrogation.

Metabolomic profiling identifies novel metabolites associated with cardiac dysfunction.

Metabolic comorbidities, such as obesity and diabetes, are associated with subclinical alterations in both cardiac structure/function and natriuretic peptides prior to the onset of heart failure (HF). Despite this, the exact metabolic pathways of cardiac dysfunction which precede HF are not well-defined. Among older individuals without HF in the Multi-Ethnic Study of Atherosclerosis (MESA), we evaluated the associations of 47 circulating metabolites measured by 1H-NMR with echocardiographic measures of cardiac structure and function. We then evaluated associations of significant metabolites with circulating N-terminal pro-B-type natriuretic peptide (NT-proBNP). In a separate cohort, we evaluated differences between top metabolites in patients with HF with preserved ejection fraction (HFpEF) and comorbidity-matched controls. Genetic variants associated with top metabolites (mQTLs) were then related to echocardiographic measures and NT-proBNP. Among 3440 individuals with metabolic and echocardiographic data in MESA (62 ± 10 years, 52% female, 38% White), 10 metabolites broadly reflective of glucose and amino acid metabolism were associated with at least 1 measure of cardiac structure or function. Of these 10 metabolites, 4 (myo-inositol, glucose, dimethylsulfone, carnitine) were associated with higher NT-proBNP and 2 (d-mannose, acetone) were associated with lower NT-proBNP. In a separate cohort, patients with HFpEF had higher circulating myo-inositol levels compared with comorbidity-matched controls. Genetic analyses revealed that 1 of 6 known myo-inositol mQTLs conferred risk of higher NT-proBNP. In conclusion, metabolomic profiling identifies several novel metabolites associated with cardiac dysfunction in a cohort at high risk for HF, revealing pathways potentially relevant to future HF risk.

DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation.

Designing faithful yet accurate AI models is challenging, particularly in the field of individual treatment effect estimation (ITE). ITE prediction models deployed in critical settings such as healthcare should ideally be (i) accurate, and (ii) provide faithful explanations. However, current solutions are inadequate: state-of-the-art black-box models do not supply explanations, post-hoc explainers for black-box models lack faithfulness guarantees, and self-interpretable models greatly compromise accuracy. To address these issues, we propose DISCRET, a self-interpretable ITE framework that synthesizes faithful, rule-based explanations for each sample. A key insight behind DISCRET is that explanations can serve dually as database queries to identify similar subgroups of samples. We provide a novel RL algorithm to efficiently synthesize these explanations from a large search space. We evaluate DISCRET on diverse tasks involving tabular, image, and text data. DISCRET outperforms the best self-interpretable models and has accuracy comparable to the best black-box models while providing faithful explanations. DISCRET is available at https://github.com/wuyinjun-1993/DISCRET-ICML2024.

The COVID-19 Pandemic Led To A Large Decline In Physician Gross Revenue Across All Specialties In 2020.

US health care use declined during the initial phase of the COVID-19 pandemic in 2020. Although utilization is known to have recovered in 2021 and 2022, it is unknown how revenue in 2020-22 varied by physician specialty and practice setting. This study linked medical claims from a large national federation of commercial health plans to physician and practice data to estimate pandemic-associated impacts on physician revenue (defined as payments to eligible physicians) by specialty and practice characteristics. Surgical specialties, emergency medicine, and medical subspecialties each experienced a greater than 9 percent adjusted gross revenue decline in 2020 relative to prepandemic baselines. By 2022, pathology and psychiatry revenue experienced robust recovery, whereas surgical and oncology revenue remained at or below baseline. Revenue recovery in 2022 was greater for physicians practicing in hospital-owned practices and in practices participating in accountable care organizations. Pandemic-associated revenue recovery in 2021 and 2022 varied by specialty and practice type. Given that physician financial instability is associated with health care consolidation and leaving practice, policy makers should closely monitor revenue trends among physicians in specialties or practice settings with sustained gross revenue reductions during the pandemic.

Ethical Implications of Artificial Intelligence in Gastroenterology: The Co-pilot or the Captain?

Though artificial intelligence (AI) is being widely implemented in gastroenterology (GI) and hepatology and has the potential to be paradigm shifting for clinical practice, its pitfalls must be considered along with its advantages. Currently, although the use of AI is limited in practice to supporting clinical judgment, medicine is rapidly heading toward a global environment where AI will be increasingly autonomous. Broader implementation of AI will require careful ethical considerations, specifically related to bias, privacy, and consent. Widespread use of AI raises concerns related to increasing rates of systematic errors, potentially due to bias introduced in training datasets. We propose that a central repository for collection and analysis for training and validation datasets is essential to overcoming potential biases. Since AI does not have built-in concepts of bias and equality, humans involved in AI development and implementation must ensure its ethical use and development. Moreover, ethical concerns regarding data ownership and health information privacy are likely to emerge, obviating traditional methods of obtaining patient consent that cover all possible uses of patient data. The question of liability in case of adverse events related to use of AI in GI must be addressed among the physician, the healthcare institution, and the AI developer. Though the future of AI in GI is very promising, herein we review the ethical considerations in need of additional guidance informed by community experience and collective expertise.

Hospice Administrators' and Providers' Perspectives on Providing Upstream Palliative Care: Facilitators, Barriers, and Policy Prescriptions.

Background: Among patients with serious illness, palliative care before hospice enrollment is associated with improved quality of life, reduced symptom burden, and earlier transitions to hospice. However, fewer than half of eligible patients receive specialty palliative care referrals. As most hospice clinicians and administrators have experience in specialty palliative care, several emerging programs propose engaging hospice clinicians to provide early palliative care. Objective: We sought to identify barriers and facilitators to upstream palliative care. Design: We conducted a key informant qualitative study among hospice administrators and clinicians. Setting/Subjects: We conducted semi-structured interviews with 23 hospice administrators and clinicians in eight states from March to August 2022. We identified participants using snowball and purposive sampling using states that participate in Medicare Advantage's value-based insurance design Model. Results: Respondents indicated that barriers to early palliative care included inadequate staffing and reimbursement. Hospice clinicians providing community-based palliative care can address access barriers and improve transitions to hospice. Respondents expressed desire for payer guidance in identifying eligible patients but were cautious about payers acting as direct palliative care providers. However, payers could facilitate uptake by broadening and specifying coverage of services to include goals of care conversations and symptom management. Routine referrals initiated by objective measures could potentially increase access. Conclusions: Utilizing hospice providers to provide upstream palliative care can increase access, improve outcomes, and ease the transition to hospice.

Immune cell profiling of the ICAM1 p.K56M heart failure with preserved ejection fraction risk variant.

AIMS: Intercellular adhesion molecule-1 (ICAM-1) facilitates inflammation via leucocyte recruitment and has been implicated in heart failure with preserved ejection fraction (HFpEF). Approximately 35% of African American individuals carry a copy of an ICAM1 missense variant (rs5491; p.K56M), which is associated with an increased risk of HFpEF. The pathways by which rs5491 increases HFpEF risk are not well defined. We evaluated the circulating immune cell profile of rs5491. METHODS: Among African American individuals in the Multi-Ethnic Study of Atherosclerosis, we evaluated the associations of rs5491 with 29 circulating peripheral blood mononuclear cell subsets. The top immune cells were then related to echocardiographic measures of structure and function. RESULTS: Among 502 individuals with immune cell profiling (mean age 63 years, 51% female), 191 individuals (38%) had at least one copy of rs5491. Each additional rs5491 allele was significantly associated with higher proportions of Tc17 CD8+ cytotoxic T cells (ß = 1.34, SE = 0.45, P = 9.5 × 10-5) and Tc2 CD8+ cytotoxic T cells (ß = 1.19, SE = 0.44, P = 0.00012). There were no other associations noted between rs5491 and the remaining immune cells. A higher proportion of Tc17 cells was significantly associated with a higher left ventricular ejection fraction, E/e' average and right ventricular systolic pressure (RVSP), while a higher proportion of Tc2 cells was significantly associated with a higher RVSP. CONCLUSIONS: The ICAM1 p.K56M variant (rs5491) carries a distinct and inflammatory T-cell subset profile. These cytotoxic T cells are in turn associated with alterations in cardiac function and adverse haemodynamics later in life, thus providing insight into pathways by which rs5491 may increase the risk of HFpEF.

Spending Analysis of Machine Learning-Based Communication Nudges in Oncology.

BACKGROUND: Serious illness conversations (SICs) in the outpatient setting may improve mood and quality of life among patients with cancer and decrease aggressive end-of-life care. Interventions informed by behavioral economics may increase rates of SICs between oncology clinicians and patients, but the impact of these interventions on end-of-life spending is unknown. METHODS: This study is a secondary analysis of a stepped-wedge cluster randomized, controlled trial that involved nine medical oncology practices and their high-risk patients at a large academic institution between June 2019 and April 2020. The study included 1187 patients who were identified by a machine-learning algorithm as high risk of 180-day mortality and who died by December 2020. The patients were randomly assigned to standard of care (controls) or to a behavioral intervention designed to increase clinician-initiated SICs. We abstracted spending - defined as inflation-adjusted costs for acute care (inpatient plus emergency room), office/outpatient care, intravenous systemic therapy, other therapy (e.g., radiation), long-term care, and hospice - from the institution's accounting system, and we captured spending at inpatient, outpatient, and pharmacy settings. To evaluate intervention impacts on spending, we used a two-part model, first using logistic regression to model zero versus nonzero spending and second using generalized linear mixed models with gamma distribution and log-link function to model daily mean spending in the last 180days of life. Models were adjusted for clinic and wedge fixed effects, and they were clustered at the oncologist level. For all patients with at least one SIC within 6 months of death, we also calculated their mean daily spending before and after SIC. RESULTS: Median age at death was 68years (interquartile range, 15.5), 317 patients (27%) were Black or of ethnicities other than white, and 448 patients (38%) had an SIC. The intervention was associated with lower unadjusted mean daily spending in the last 6 months of life for the intervention group versus controls ($377.96 vs. $449.92; adjusted mean difference, -$75.33; 95% confidence interval, -$136.42 to -$14.23; P=0.02), translating to $13,747 total adjusted savings per decedent and $13 million in cumulative savings across all decedents in the intervention group. Compared with controls, patients in the intervention group incurred lower mean daily spending for systemic therapy (adjusted difference, -$44.59; P=0.001), office/outpatient care (-$9.62; P=0.001), and other therapy (-$8.65; P=0.04). The intervention was not associated with differences in end-of-life spending for acute care, long-term care, or hospice. Results were consistent for spending in the last 1 and 3 months of life and after adjusting for age, race, and ethnicity. For patients with SICs, mean daily spending decreased by $37.92 following the first SIC ($329.87 vs. $291.95). CONCLUSIONS: A machine learning-based, behaviorally informed intervention to prompt SICs led to end-of-life savings among patients with cancer, driven by decreased systemic therapy and outpatient spending. (Funded by the Penn Center for Precision Medicine and the National Institutes of Health; ClinicalTrials.gov number, NCT03984773.).

Clinician- and Patient-Directed Communication Strategies for Patients With Cancer at High Mortality Risk: A Cluster Randomized Trial.

Importance: Serious illness conversations (SICs) that elicit patients' values, goals, and care preferences reduce anxiety and depression and improve quality of life, but occur infrequently for patients with cancer. Behavioral economic implementation strategies (nudges) directed at clinicians and/or patients may increase SIC completion. Objective: To test the independent and combined effects of clinician and patient nudges on SIC completion. Design, Setting, and Participants: A 2 × 2 factorial, cluster randomized trial was conducted from September 7, 2021, to March 11, 2022, at oncology clinics across 4 hospitals and 6 community sites within a large academic health system in Pennsylvania and New Jersey among 163 medical and gynecologic oncology clinicians and 4450 patients with cancer at high risk of mortality (≥10% risk of 180-day mortality). Interventions: Clinician clusters and patients were independently randomized to receive usual care vs nudges, resulting in 4 arms: (1) active control, operating for 2 years prior to trial start, consisting of clinician text message reminders to complete SICs for patients at high mortality risk; (2) clinician nudge only, consisting of active control plus weekly peer comparisons of clinician-level SIC completion rates; (3) patient nudge only, consisting of active control plus a preclinic electronic communication designed to prime patients for SICs; and (4) combined clinician and patient nudges. Main Outcomes and Measures: The primary outcome was a documented SIC in the electronic health record within 6 months of a participant's first clinic visit after randomization. Analysis was performed on an intent-to-treat basis at the patient level. Results: The study accrued 4450 patients (median age, 67 years [IQR, 59-75 years]; 2352 women [52.9%]) seen by 163 clinicians, randomized to active control (n = 1004), clinician nudge (n = 1179), patient nudge (n = 997), or combined nudges (n = 1270). Overall patient-level rates of 6-month SIC completion were 11.2% for the active control arm (112 of 1004), 11.5% for the clinician nudge arm (136 of 1179), 11.5% for the patient nudge arm (115 of 997), and 14.1% for the combined nudge arm (179 of 1270). Compared with active control, the combined nudges were associated with an increase in SIC rates (ratio of hazard ratios [rHR], 1.55 [95% CI, 1.00-2.40]; P = .049), whereas the clinician nudge (HR, 0.95 [95% CI, 0.64-1.41; P = .79) and patient nudge (HR, 0.99 [95% CI, 0.73-1.33]; P = .93) were not. Conclusions and Relevance: In this cluster randomized trial, nudges combining clinician peer comparisons with patient priming questionnaires were associated with a marginal increase in documented SICs compared with an active control. Combining clinician- and patient-directed nudges may help to promote SICs in routine cancer care. Trial Registration: ClinicalTrials.gov Identifier: NCT04867850.

Association of disproportionate liver fat with markers of heart failure: The multi-ethnic study of atherosclerosis.

BACKGROUND: Metabolic dysfunction associated steatotic liver disease (MASLD) has been linked to heart failure with preserved ejection fraction (HFpEF). We sought to understand association between individuals with amounts of liver adiposity greater than would be predicted by their body mass index (BMI) in order to understand whether this disproportionate liver fat (DLF) represents a proxy of metabolic risk shared between liver and heart disease. METHODS: We studied 2,932 participants in the Multi-Ethnic Study of Atherosclerosis (MESA) who received computed tomography (CT) measurements of hepatic attenuation. Quartiles of DLF were compared and multivariable linear regression was performed to evaluate the association of DLF with clinical, echocardiographic, and quality of life metrics. RESULTS: Compared to the lowest quartile of DLF, individuals in the highest quartile of DLF were more likely to be male (52.0% vs 47.1%, P < .001), less likely to be Black or African American (14.8 % vs 38.1% P < .001), have higher rates of dysglycemia (31.9% vs 16.6%, P < .001) and triglycerides (140 [98.0, 199.0] vs 99.0 [72.0, 144.0] mg/dL, P > .001). These individuals had lower global longitudinal strain (-0.13 [-0.25, -0.02], P = .02), stroke volumes (-1.05 [-1.76, -0.33], P < .01), lateral e' velocity (-0.10 [-0.18, -0.02], P = .02), and 6-minute walk distances (-4.25 [-7.62 to -0.88], P = .01). CONCLUSION: DLF is associated with abnormal metabolic profiles and ventricular functional changes known to be associated with HFpEF and may serve as an early metric to assess for those that may progress to clinical HFpEF.

Kidney Outcomes Among Medicare Beneficiaries After Hospitalization for Heart Failure.

Importance: Kidney health has received increasing focus as part of comprehensive heart failure (HF) treatment efforts. However, the occurrence of clinically relevant kidney outcomes in contemporary populations with HF has not been well studied. Objective: To examine rates of incident dialysis and acute kidney injury (AKI) among Medicare beneficiaries after HF hospitalization. Design, Setting, and Participants: This retrospective cohort study evaluated adults aged 65 years or older who were hospitalized for HF across 372 sites in the Get With The Guidelines-Heart Failure registry in the US between January 1, 2014, and December 31, 2018. Patients younger than 65 years or requiring dialysis either during or prior to hospitalization were excluded. Data were analyzed from May 4, 2021, to March 8, 2024. Main Outcomes and Measures: The primary outcome was inpatient dialysis initiation in the year after HF hospitalization and was ascertained via linkage with Medicare claims data. Other all-cause and cause-specific hospitalizations were also evaluated. The covariate-adjusted association between discharge estimated glomerular filtration rate (eGFR) and 1-year postdischarge outcomes was examined using Cox proportional hazards regression models. Results: Overall, among 85 298 patients included in the analysis (mean [SD] age, 80 [9] years; 53% women) mean (SD) left ventricular ejection fraction was 47% (16%) and mean (SD) eGFR was 53 (29) mL/min per 1.73 m2; 54 010 (63%) had an eGFR less than 60 mL/min per 1.73 m2. By 1 year after HF hospitalization, 6% had progressed to dialysis, 7% had progressed to dialysis or end-stage kidney disease, and 7% had been readmitted for AKI. Incident dialysis increased steeply with lower discharge eGFR category: compared with patients with an eGFR of 60 mL/min per 1.73 m2 or more, individuals with an eGFR of 45 to less than 60 and of less than 30 mL/min per 1.73 m2 had higher rates of dialysis readmission (45 to <60: adjusted hazard ratio [AHR], 2.16 [95% CI, 1.86-2.51]; <30: AHR, 28.46 [95% CI, 25.25-32.08]). Lower discharge eGFR (per 10 mL/min per 1.73 m2 decrease) was independently associated with a higher rate of readmission for dialysis (AHR, 2.23; 95% CI, 2.14-2.32), dialysis or end-stage kidney disease (AHR, 2.34; 95% CI, 2.24-2.44), and AKI (AHR, 1.25; 95% CI, 1.23-1.27), with similar findings for all-cause mortality, all-cause readmission, and HF readmission. Baseline left ventricular ejection fraction did not modify the covariate-adjusted association between lower discharge eGFR and kidney outcomes. Conclusions and Relevance: In this study, older adults with HF had substantial risk of kidney complications, with an estimated 6% progressing to dialysis in the year after HF hospitalization. These findings emphasize the need for health care approaches prioritizing kidney health in this high-risk population.

Association of Remote Patient-Reported Outcomes and Step Counts With Hospitalization or Death Among Patients With Advanced Cancer Undergoing Chemotherapy: Secondary Analysis of the PROStep Randomized Trial.

BACKGROUND: Patients with advanced cancer undergoing chemotherapy experience significant symptoms and declines in functional status, which are associated with poor outcomes. Remote monitoring of patient-reported outcomes (PROs; symptoms) and step counts (functional status) may proactively identify patients at risk of hospitalization or death. OBJECTIVE: The aim of this study is to evaluate the association of (1) longitudinal PROs with step counts and (2) PROs and step counts with hospitalization or death. METHODS: The PROStep randomized trial enrolled 108 patients with advanced gastrointestinal or lung cancers undergoing cytotoxic chemotherapy at a large academic cancer center. Patients were randomized to weekly text-based monitoring of 8 PROs plus continuous step count monitoring via Fitbit (Google) versus usual care. This preplanned secondary analysis included 57 of 75 patients randomized to the intervention who had PRO and step count data. We analyzed the associations between PROs and mean daily step counts and the associations of PROs and step counts with the composite outcome of hospitalization or death using bootstrapped generalized linear models to account for longitudinal data. RESULTS: Among 57 patients, the mean age was 57 (SD 10.9) years, 24 (42%) were female, 43 (75%) had advanced gastrointestinal cancer, 14 (25%) had advanced lung cancer, and 25 (44%) were hospitalized or died during follow-up. A 1-point weekly increase (on a 32-point scale) in aggregate PRO score was associated with 247 fewer mean daily steps (95% CI -277 to -213; P<.001). PROs most strongly associated with step count decline were patient-reported activity (daily step change -892), nausea score (-677), and constipation score (524). A 1-point weekly increase in aggregate PRO score was associated with 20% greater odds of hospitalization or death (adjusted odds ratio [aOR] 1.2, 95% CI 1.1-1.4; P=.01). PROs most strongly associated with hospitalization or death were pain (aOR 3.2, 95% CI 1.6-6.5; P<.001), decreased activity (aOR 3.2, 95% CI 1.4-7.1; P=.01), dyspnea (aOR 2.6, 95% CI 1.2-5.5; P=.02), and sadness (aOR 2.1, 95% CI 1.1-4.3; P=.03). A decrease in 1000 steps was associated with 16% greater odds of hospitalization or death (aOR 1.2, 95% CI 1.0-1.3; P=.03). Compared with baseline, mean daily step count decreased 7% (n=274 steps), 9% (n=351 steps), and 16% (n=667 steps) in the 3, 2, and 1 weeks before hospitalization or death, respectively. CONCLUSIONS: In this secondary analysis of a randomized trial among patients with advanced cancer, higher symptom burden and decreased step count were independently associated with and predictably worsened close to hospitalization or death. Future interventions should leverage longitudinal PRO and step count data to target interventions toward patients at risk for poor outcomes. TRIAL REGISTRATION: ClinicalTrials.gov NCT04616768; https://clinicaltrials.gov/study/NCT04616768. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1136/bmjopen-2021-054675.

Activation of enamine by photoexcited organocatalyst assisted singlet oxygen: synthesis of oxazoles and quinoxalines.

Herein, a novel transition-metal-free thiol-based donor-acceptor organophotocatalyst-assisted, singlet-oxygen-mediated tandem oxidative cyclization for the synthesis of substituted oxazoles in moderate-to-good yields is described. The developed method demonstrates applicability for the synthesis of various substituted quinoxalines in good-to-excellent yields. The metal-free methodology shows a practical route for the synthesis of oxazole and quinoxaline derivatives, which are privileged moieties prevalent in various biologically active compounds and natural products. To the best of our knowledge, both the thiol photocatalyst and synthesis of oxazoles by visible-light irradiation are reported for the first time.

Cancer Treatment Before and After Physician-Pharmacy Integration.

Importance: Integration of pharmacies with physician practices, also known as medically integrated dispensing, is increasing in oncology. However, little is known about how this integration affects drug use, expenditures, medication adherence, or time to treatment initiation. Objective: To examine the association of physician-pharmacy integration with oral oncology drug expenditures, use, and patient-centered measures. Design, Setting, and Participants: This cohort study used claims data from a large commercial insurer in the US to analyze changes in outcome measures among patients treated by pharmacy-integrating vs nonintegrating community oncologists in 14 states between January 1, 2011, and December 31, 2019. Commercially insured patients were aged 18 to 64 years with 1 of the following advanced-stage diagnoses: breast cancer, colorectal cancer, kidney cancer, lung cancer, melanoma, or prostate cancer. Data analysis was conducted from May 2023 to March 2024. Exposure: Treatment by a pharmacy-integrating oncologist, ascertained by the presence of an on-site pharmacy or nonpharmacy dispensing site. Main Outcomes and Measures: Oral, intravenous (IV), total, and out-of-pocket drug expenditures for a 6-month episode of care; share of patients prescribed oral drugs; days' supply of oral drugs; medication adherence measured by proportion of days covered; and time to treatment initiation. The association between an oncologist's pharmacy integration and each outcome of interest was estimated using the difference-in-differences estimator. Results: Between 2012 and 2019, 3159 oncologists (745 females [27.1%], 2002 males [72.9%]) treated 23 968 patients (66.4% female; 53.4% aged 55-64 years). Of the 3159 oncologists, 578 (18.3%) worked in practices that integrated with pharmacies (with a low rate in 2011 of 0% and a high rate in 2019 of 31.5%). In the full sample (including all cancer sites), after physician-pharmacy integration, no significant changes were found in oral drug expenditures, IV drug expenditures, or total drug expenditures. There was, however, an increase in days' supply of oral drugs (5.96 days; 95% CI, 0.64-11.28 days; P = .001). There were no significant changes in out-of-pocket expenditures, medication adherence, or time to treatment initiation of oral drugs. In the breast cancer sample, there was an increase in oral drug expenditures ($244; 95% CI, $41-$446; P = .02) and a decrease in IV drug expenditures (-$4187; 95% CI, -$8293 to -$80; P = .05). Conclusions and Relevance: Results of this cohort study indicated that the integration of oncology practices with pharmacies was not associated with significant changes in expenditures or clear patient-centered benefits.

Real-world evaluation of deep learning algorithms to classify functional pathogenic germline variants.

Deep learning models for variant pathogenicity prediction can recapitulate expert-curated annotations, but their performance remains unexplored on actual disease phenotypes in a real-world setting. Here, we apply three state-of-the-art pathogenicity prediction models to classify hereditary breast cancer gene variants in the UK Biobank. Predicted pathogenic variants in BRCA1, BRCA2 and PALB2, but not ATM and CHEK2, were associated with increased breast cancer risk. We explored gene-specific score thresholds for variant pathogenicity, finding that they could improve model performance. However, when specifically tasked with classifying variants of uncertain significance, the deep learning models were generally of limited clinical utility.