Prevalence, Predictors, and Outcomes of Type 2 NSTEMI in Hospitalized Patients With COVID-19.

BACKGROUND: Data on the incidence of type 2 non-ST-segment-elevation myocardial infarction (T2MI) in hospitalized patients with COVID-19 has been limited to single-center studies. Given that certain characteristics, such as obesity and type 2 diabetes, have been associated with higher mortality in COVID-19 infections, we aimed to define the incidence of T2MI in a national cohort and identify pre-hospital patient characteristics associated with T2MI in hospitalized patients with COVID-19. METHODS AND RESULTS: Using the national American Heart Association COVID-19 Cardiovascular Disease Quality Improvement Registry, we performed a retrospective 4:1 matched (age, sex, race, and body mass index) analysis of controls versus cases with T2MI. We performed (1) conditional multivariable logistic regression to identify predictive pre-hospital patient characteristics of T2MI for patients hospitalized with COVID-19 and (2) stratified proportional hazards regression to investigate the association of T2MI with morbidity and mortality. From January 2020 through May 2021, there were 709 (2.2%) out of 32 015 patients with T2MI. Five hundred seventy-nine cases with T2MI were matched to 2171 controls (mean age 70; 43% female). Known coronary artery disease, heart failure, chronic kidney disease, hypertension, payor source, and presenting heart rate were associated with higher odds of T2MI. Anti-hyperglycemic medication and anti-coagulation use before admission were associated with lower odds of T2MI. Those with T2MI had higher morbidity and mortality (hazard ratio, 1.40 [95% CI, 1.13-1.74]; P=0.002). CONCLUSIONS: In hospitalized patients with COVID-19, those with a T2MI compared with those without had higher morbidity and mortality. Outpatient anti-hyperglycemic and anti-coagulation use were the only pre-admission factors associated with reduced odds of T2MI.

Scaling care coordination through digital engagement: stepped-wedge trial assessing readmissions.

OBJECTIVES: Transitions of care are pivotal, vulnerable times as patients are discharged from the hospital. Telephonic care coordination is standard care, but labor intensive. We implemented a patient postdischarge digital engagement (PDDE) program to scale coordination. We hypothesized that PDDE could reduce readmissions for low-risk patients and supplement care coordination for medium- and high-risk patients. STUDY DESIGN: Pragmatic, stepped-wedge cluster randomization trial with 5 implementation waves based upon primary care clinic region. METHODS: All inpatient hospital discharges between March 2020 and November 2020 were stratified by readmission risk. Low-risk patients were offered access to PDDE, and moderate-risk and high-risk patients were offered access to PDDE and care coordination. Readmission was defined as an unplanned inpatient admission within 30 days from discharge. An intention-to-treat primary analysis was conducted using mixed-effects logistic regression clustering for wave; a treatment-on-the-treated analysis was also conducted to assess the impact among program users. RESULTS: A total of 5490 patient discharges were examined (2735 control; 2755 intervention); 1949 patients were high risk, 2032 were medium risk, and 1509 were low risk. PDDE intervention did not significantly affect readmission among low-risk (95% CI, -0.23 to 0.90; P = .23), medium-risk (95% CI, -0.14 to 0.60; P = .21), and high-risk (95% CI, -0.32 to 0.64; P = .48) groups after adjustment for time and patient factors. In a treatment-on-the-treated analysis, among patients who activated the PDDE program, readmission was also similar among the low-, medium-, and high-risk cohorts. CONCLUSIONS: Our study expanded resource-limited care coordination by offering low-risk patients a service they were unable to receive previously while having no impact on readmission. PDDE efficiently provided additional touch points between patients and providers.

Timing and co-occurrence of symptoms prior to a diagnosis of light chain (AL) amyloidosis.

It is well-established that light chain (AL) amyloidosis patients have multi-organ involvement and are often diagnosed after a lag period of increasing symptoms. We leverage electronic health record (EHR) data from the TriNetX research network to describe the incidence, timing, and co-occurrence of precursor conditions of interests in a cohort of AL amyloidosis patients identified between October 2015-December 2020. Nineteen precursor diagnoses of interest representing features of AL amyloidosis were identified using ICD codes up to 36 months prior to AL amyloidosis diagnosis. Among 1,401 patients with at least 36 months of EHR data prior to AL amyloidosis diagnosis, 46% were females, 16% were non-Hispanic Black, and 6% were Hispanic. The median age was 71 (range, 21-91) years. The median number of precursor diagnoses was 5 with dyspnea and fatigue being the most prevalent. The time from the first occurrence of a precursor to AL diagnosis ranged from 3.2 to 21.4 months. Analyses of pairwise co-occurrence of specific diagnoses indicated a high association (Cole's coefficient > 0.6) among the examined precursor diagnoses. These findings provide novel information about the timing and co-occurrence of key precursor conditions and could be used to develop algorithms for early identification of AL amyloidosis.

The Variation of Withdrawal of Life Sustaining Therapy in Older Adults With Traumatic Brain Injury.

INTRODUCTION: The decision to withdraw life sustaining treatment (WDLST) in older adults with traumatic brain injury is subject to wide variability leading to nonbeneficial interventions and unnecessary use of hospital resources. We hypothesized that patient and hospital factors are associated with WDLST and WDLST timing. METHODS: All traumatic brain injury patients ≥65 with Glasgow coma scores (GCS) of 4-11 from 2018 to 2019 at level I and II centers were selected from the National Trauma Data Bank. Patients with head abbreviated injury scores 5-6 or death within 24 h were excluded. Bayesian additive regression tree analysis was performed to identify the cumulative incidence function (CIF) and the relative risks (RR) over time for withdrawal of care, discharge to hospice (DH), and death. Death alone (no WDLST or DH) served as the comparator group for all analyses. A subanalysis of the composite outcome WDLST/DH (defined as end-of-life-care), with death (no WDLST or DH) as a comparator cohort was performed. RESULTS: We included 2126 patients, of whom 1957 (57%) underwent WDLST, 402 (19%) died, and 469 (22%) were DH. 60% of patients were male, and the mean age was 80 y. The majority of patients were injured by fall (76%, n = 1644). Patients who were DH were more often female (51% DH versus 39% WDLST), had a past medical history of dementia (45% DH versus 18% WDLST), and had lower admission injury severity score (14 DH versus 18.6 WDLST) (P < 0.001). Compared to those who DH, those who underwent WDLST had a lower GCS (9.8 versus 8.4, P < 0.001). CIF of WDSLT and DH increased with age, stabilizing by day 3. At day 3, patients ≥90 y had an increased RR of DH compared to WDLST (RR 2.5 versus 1.4). As GCS increased, CIF and RR of WDLST decreased, while CIF and RR of DH increased (RR on day 3 for GCS 12: WDLST 0.42 versus DH 1.31).Patients at nonprofit institutions were more likely to undergo WDLST (RR 1.15) compared to DH (0.68). Compared to patients of White race, patients of Black race had a lower RR of WDLST at all timepoints. CONCLUSIONS: Patient and hospital factors influence the practice of end-of-life-care (WDLST, DH, and death), highlighting the need to better understand variability to target palliative care interventions and standardize care across populations and trauma centers.

Nonparametric failure time: Time-to-event machine learning with heteroskedastic Bayesian additive regression trees and low information omnibus Dirichlet process mixtures.

Many popular survival models rely on restrictive parametric, or semiparametric, assumptions that could provide erroneous predictions when the effects of covariates are complex. Modern advances in computational hardware have led to an increasing interest in flexible Bayesian nonparametric methods for time-to-event data such as Bayesian additive regression trees (BART). We propose a novel approach that we call nonparametric failure time (NFT) BART in order to increase the flexibility beyond accelerated failure time (AFT) and proportional hazard models. NFT BART has three key features: (1) a BART prior for the mean function of the event time logarithm; (2) a heteroskedastic BART prior to deduce a covariate-dependent variance function; and (3) a flexible nonparametric error distribution using Dirichlet process mixtures (DPM). Our proposed approach widens the scope of hazard shapes including nonproportional hazards, can be scaled up to large sample sizes, naturally provides estimates of uncertainty via the posterior and can be seamlessly employed for variable selection. We provide convenient, user-friendly, computer software that is freely available as a reference implementation. Simulations demonstrate that NFT BART maintains excellent performance for survival prediction especially when AFT assumptions are violated by heteroskedasticity. We illustrate the proposed approach on a study examining predictors for mortality risk in patients undergoing hematopoietic stem cell transplant (HSCT) for blood-borne cancer, where heteroskedasticity and nonproportional hazards are likely present.

Mandibular advancement reduces pharyngeal collapsibility by enlarging the airway rather than affecting velopharyngeal compliance.

Mandibular advancement devices (MADs) are frequently prescribed for obstructive sleep apnea (OSA) patients, but approximately one third of patients experience no therapeutic benefit. Understanding the mechanisms by which MADs prevent pharyngeal collapse may help optimize MAD therapy. This study quantified the relative contributions of changes in airspace cross-sectional area (CSA) versus changes in velopharyngeal compliance in determining MAD efficacy. Sixteen patients with moderate to severe OSA (mean apnea-hypopnea index of 32 ± 15 events/h) underwent measurements of the velopharyngeal closing pressure (PCLOSE ) during drug induced sedated endoscopy (DISE) via stepwise reductions in nasal mask pressure and recording of the intraluminal pressure with a catheter. Airspace CSA was estimated from video endoscopy. Pharyngeal compliance was defined as the slope of the area-pressure relationship of the velopharyngeal airspace. MAD therapy reduced PCLOSE from a median of 0.5 cmH2 O pre-advancement to a median of -2.6 cmH2 O post-advancement (p = 0.0009), increased the minimal CSA at the velopharynx by approximately 20 mm2 (p = 0.0067), but did not have a statistically significant effect on velopharyngeal compliance (p = 0.23). PCLOSE had a strong correlation with CSA but did not correlate with velopharyngeal compliance. Our results suggest that MADs reduce velopharyngeal collapsibility by increasing airway size as opposed to affecting velopharyngeal compliance. This contradicts the speculation of previous literature that the effectiveness of MADs is partially due to a reduction in velopharyngeal compliance resulting from stretching of the soft palate. These findings suggest that quantification of velopharyngeal CSA pre- and post-MAD advancement has potential as a biomarker to predict the success of MAD therapy.

Anatomical determinants of upper airway collapsibility in obstructive sleep apnea: A systematic review and meta-analysis.

Upper airway (UA) collapsibility is one of the key factors that determine the severity of obstructive sleep apnea (OSA). Interventions for OSA are aimed at reducing UA collapsibility, but selecting the optimal alternative intervention for patients who fail CPAP is challenging because currently no validated method predicts how anatomical changes affect UA collapsibility. The gold standard objective measure of UA collapsibility is the pharyngeal critical pressure (Pcrit). A systematic literature review and meta-analysis were performed to identify the anatomical factors with the strongest correlation with Pcrit. A search using the PRISMA methodology was performed on PubMed for English language scientific papers that correlated Pcrit to anatomic variables and OSA severity as measured by the apnea-hypopnea index (AHI). A total of 29 papers that matched eligibility criteria were included in the quantitative synthesis. The meta-analysis suggested that AHI has only a moderate correlation with Pcrit (estimated Pearson correlation coefficient r = 0.46). The meta-analysis identified four key anatomical variables associated with UA collapsibility, namely hyoid position (r = 0.53), tongue volume (r = 0.51), pharyngeal length (r = 0.50), and waist circumference (r = 0.49). In the future, biomechanical models that quantify the relative importance of these anatomical factors in determining UA collapsibility may help identify the optimal intervention for each patient. Many anatomical and structural factors such as airspace cross-sectional areas, epiglottic collapse, and palatal prolapse have inadequate data and require further research.

Patient similarity and other artificial intelligence machine learning algorithms in clinical decision aid for shared decision-making in the Prevention of Cardiovascular Toxicity (PACT): a feasibility trial design.

BACKGROUND: The many improvements in cancer therapies have led to an increased number of survivors, which comes with a greater risk of consequent/subsequent cardiovascular disease. Identifying effective management strategies that can mitigate this risk of cardiovascular complications is vital. Therefore, developing computer-driven and personalized clinical decision aid interventions that can provide early detection of patients at risk, stratify that risk, and recommend specific cardio-oncology management guidelines and expert consensus recommendations is critically important. OBJECTIVES: To assess the feasibility, acceptability, and utility of the use of an artificial intelligence (AI)-powered clinical decision aid tool in shared decision making between the cancer survivor patient and the cardiologist regarding prevention of cardiovascular disease. DESIGN: This is a single-center, double-arm, open-label, randomized interventional feasibility study. Our cardio-oncology cohort of > 4000 individuals from our Clinical Research Data Warehouse will be queried to identify at least 200 adult cancer survivors who meet the eligibility criteria. Study participants will be randomized into either the Clinical Decision Aid Group (where patients will use the clinical decision aid in addition to current practice) or the Control Group (current practice). The primary endpoint of this study is to assess for each patient encounter whether cardiovascular medications and imaging pursued were consistent with current medical society recommendations. Additionally, the perceptions of using the clinical decision tool will be evaluated based on patient and physician feedback through surveys and focus groups. This trial will determine whether a clinical decision aid tool improves cancer survivors' medication use and imaging surveillance recommendations aligned with current medical guidelines. TRIAL REGISTRATION: ClinicalTrials.Gov Identifier: NCT05377320.

Impact of Reintervention During Stage 1 Palliation Hospitalization: A National, Multicenter Study.

BACKGROUND: Stage 1 palliation (S1P) for hypoplastic left heart syndrome remains associated with high morbidity and mortality. Previous studies on burden of reinterventions did not include patients who remain hospitalized before stage 2 palliation (S2P). This study described the rate of reintervention during S1P hospitalization and sought to determine the impact of reintervention on outcomes. METHODS: All participants enrolled in phase II of the National Pediatric Cardiology Quality Improvement Collaborative after S1P were included in this study. The primary outcome was the rate of reintervention during hospitalization after S1P and before hospital discharge or S2P. Reintervention was defined as 1 or more unplanned interventional cardiac catheterizations or surgical reoperations. RESULTS: Between March 1, 2016 and October 1, 2019, 1367 participants underwent S1P and 339 (24.8%) had a reintervention; most commonly to address the source of pulmonary blood flow. Gestational age, weight at S1P, atrioventricular septal defect, heterotaxy, preoperative pulmonary artery bands, hybrid S1P, and an additional bypass run or early extracorporeal membrane oxygenation were significantly associated with reintervention. Participants in the reintervention group experienced higher rates of nearly all postoperative complications, were less likely to be discharged before S2P (57.1% vs 86%; P < .001), and more likely to experience in-hospital mortality (17% vs 5%; P < .001). CONCLUSIONS: Unplanned reintervention during hospitalization after S1P palliation occurred in 25% of participants in a large, registry-based national cohort. Participants who underwent reintervention were more likely to remain as inpatient and were less likely to survive to S2P. Reintervention was associated with a multitude of postoperative complications that affect survival and long-term outcome.

Team principles for successful interdisciplinary research teams.

Interdisciplinary research teams can be extremely beneficial when addressing difficult clinical problems. The incorporation of conceptual and methodological strategies from a variety of research disciplines and health professions yields transformative results. In this setting, the long-term goal of team science is to improve patient care, with emphasis on population health outcomes. However, team principles necessary for effective research teams are rarely taught in health professional schools. To form successful interdisciplinary research teams in cardio-oncology and beyond, guiding principles and organizational recommendations are necessary. Cardiovascular disease results in annual direct costs of $220 billion (about $680 per person in the US) and is the leading cause of death for cancer survivors, including adult survivors of childhood cancers. Optimizing cardio-oncology research in interdisciplinary research teams has the potential to aid in the investigation of strategies for saving hundreds of thousands of lives each year in the United States and mitigating the annual cost of cardiovascular disease. Despite published reports on experiences developing research teams across organizations, specialties and settings, there is no single journal article that compiles principles for cardiology or cardio-oncology research teams. In this review, recurring threads linked to working as a team, as well as optimal methods, advantages, and problems that arise when managing teams are described in the context of career development and research. The worth and hurdles of a team approach, based on practical lessons learned from establishing our multidisciplinary research team and information gleaned from relevant specialties in the development of a successful team are presented.

Novel Pediatric Height Outlier Detection Methodology for Electronic Health Records via Machine Learning With Monotonic Bayesian Additive Regression Trees.

OBJECTIVE: To create a new methodology that has a single simple rule to identify height outliers in the electronic health records (EHR) of children. METHODS: We constructed 2 independent cohorts of children 2 to 8 years old to train and validate a model predicting heights from age, gender, race and weight with monotonic Bayesian additive regression trees. The training cohort consisted of 1376 children where outliers were unknown. The testing cohort consisted of 318 patients that were manually reviewed retrospectively to identify height outliers. RESULTS: The amount of variation explained in height values by our model, R2 , was 82.2% and 75.3% in the training and testing cohorts, respectively. The discriminatory ability to assess height outliers in the testing cohort as assessed by the area under the receiver operating characteristic curve was excellent, 0.841. Based on a relatively aggressive cutoff of 0.075, the outlier sensitivity is 0.713, the specificity 0.793; the positive predictive value 0.615 and the negative predictive value is 0.856. CONCLUSIONS: We have developed a new reliable, largely automated, outlier detection method which is applicable to the identification of height outliers in the pediatric EHR. This methodology can be applied to assess the veracity of height measurements ensuring reliable indices of body proportionality such as body mass index.

Establishing an interdisciplinary research team for cardio-oncology artificial intelligence informatics precision and health equity.

Study objective: A multi-institutional interdisciplinary team was created to develop a research group focused on leveraging artificial intelligence and informatics for cardio-oncology patients. Cardio-oncology is an emerging medical field dedicated to prevention, screening, and management of adverse cardiovascular effects of cancer/ cancer therapies. Cardiovascular disease is a leading cause of death in cancer survivors. Cardiovascular risk in these patients is higher than in the general population. However, prediction and prevention of adverse cardiovascular events in individuals with a history of cancer/cancer treatment is challenging. Thus, establishing an interdisciplinary team to create cardiovascular risk stratification clinical decision aids for integration into electronic health records for oncology patients was considered crucial. Design/setting/participants: Core team members from the Medical College of Wisconsin (MCW), University of Wisconsin-Milwaukee (UWM), and Milwaukee School of Engineering (MSOE), and additional members from Cleveland Clinic, Mayo Clinic, and other institutions have joined forces to apply high-performance computing in cardio-oncology. Results: The team is comprised of clinicians and researchers from relevant complementary and synergistic fields relevant to this work. The team has built an epidemiological cohort of ~5000 cancer survivors that will serve as a database for interdisciplinary multi-institutional artificial intelligence projects. Conclusion: Lessons learned from establishing this team, as well as initial findings from the epidemiology cohort, are presented. Barriers have been broken down to form a multi-institutional interdisciplinary team for health informatics research in cardio-oncology. A database of cancer survivors has been created collaboratively by the team and provides initial insight into cardiovascular outcomes and comorbidities in this population.

Environmental health literacy for Anishinaabe (Great Lakes Native American) fish consumers: A randomized control trial.

BACKGROUND: Fish consumption comprises an important part of what the Anishinaabe (Great Lakes Native Americans) call "minobimaadiziiwin" which translates roughly to "living in a good way". Industrial activity leading to the accumulation of persistent contaminants in fish disrupts minobimaadiziiwin. Our team of academic and Anishinaabe scientists co-developed a fish consumption advisory for the Anishinaabe using software that can be accessed via mobile phones and/or the internet. OBJECTIVES: The software, Gigiigoo'inaan ("our fish") is designed to improve environmental health literacy using culturally congruent messaging and aesthetics. We tested the following hypotheses: 1) the Gigiigoo'inaan would encourage consumption of fish high in Polyunsaturated Omega-3 fatty acids (PFUA-3) whilst minimizing contaminant intake (methylmercury (MeHg) and Polychorinated Biphenyls (PCBs)); and 2) intervention participants will be more likely than controls to achieve a favorable n-3 PUFA/MeHg consumption ratios. METHODS: We conducted a randomized controlled trial with prospective self-reported fish consumption using automated email surveys. One-month pre and one month post, control and intervention outcome variables were calculated per participant as µg/kg/day of MeHg, µg/kg/day of PCB, g of fish, and mg/day of EPA+DHA. These were modeled using an analysis of covariance (ANCOVA) with a-priori covariates: age, sex, and tribal affiliation. RESULTS: Most participants in both trial arms reported eating relatively elevated amounts of fish yet remained within advisory guidelines for contaminants. EPA+DHA:MeHg ratios were also favorable in most participants. Advisory limits for contaminants were exceeded by relatively few participants in the study. DISCUSSION: Gigiigoo'inaan was previously reported to increase confidence, the current user feedback confirms this. Most participants ate fish but did not exceed the advisory limits, which demonstrates Environmental Health Literacy progress in the region despite a lack of observed behavior change during the trial. A small number of participants exceeded contaminant intake guidelines which matches the pilot work for this study.

Lisinopril Mitigates Radiation-Induced Mitochondrial Defects in Rat Heart and Blood Cells.

The genetic bases and disparate responses to radiotherapy are poorly understood, especially for cardiotoxicity resulting from treatment of thoracic tumors. Preclinical animal models such as the Dahl salt-sensitive (SS) rat can serve as a surrogate model for salt-sensitive low renin hypertension, common to African Americans, where aldosterone contributes to hypertension-related alterations of peripheral vascular and renal vascular function. Brown Norway (BN) rats, in comparison, are a normotensive control group, while consomic SSBN6 with substitution of rat chromosome 6 (homologous to human chromosome 14) on an SS background manifests cardioprotection and mitochondrial preservation to SS rats after injury. In this study, 2 groups from each of the 3 rat strains had their hearts irradiated (8 Gy X 5 fractions). One irradiated group was treated with the ACE-inhibitor lisinopril, and a separate group in each strain served as nonirradiated controls. Radiation reduced cardiac end diastolic volume by 9-11% and increased thickness of the interventricular septum (11-16%) and left ventricular posterior wall (14-15%) in all 3 strains (5-10 rats/group) after 120 days. Lisinopril mitigated the increase in posterior wall thickness. Mitochondrial function was measured by the Seahorse Cell Mitochondrial Stress test in peripheral blood mononuclear cells (PBMC) at 90 days. Radiation did not alter mitochondrial respiration in PBMC from BN or SSBN6. However, maximal mitochondrial respiration and spare capacity were reduced by radiation in PBMC from SS rats (p=0.016 and 0.002 respectively, 9-10 rats/group) and this effect was mitigated by lisinopril (p=0.04 and 0.023 respectively, 9-10 rats/group). Taken together, these results indicate injury to the heart by radiation in all 3 strains of rats, although the SS rats had greater susceptibility for mitochondrial dysfunction. Lisinopril mitigated injury independent of genetic background.

Improved Prediction of Older Adult Discharge After Trauma Using a Novel Machine Learning Paradigm.

BACKGROUND: The ability to reliably predict outcomes after trauma in older adults (age ≥ 65 y) is critical for clinical decision making. Using novel machine-learning techniques, we sought to design a nonlinear, competing risks paradigm for prediction of older adult discharge disposition following injury. MATERIALS AND METHODS: The National Trauma Databank (NTDB) was used to identify patients 65+ y between 2007 and 2014. Training was performed on an enriched cohort of diverse patients. Factors included age, comorbidities, length of stay, and physiologic parameters to predict in-hospital mortality and discharge disposition (home versus skilled nursing/long-term care facility). Length of stay and discharge status were analyzed via competing risks survival analysis with Bayesian additive regression trees and a multinomial mixed model. RESULTS: The resulting sample size was 47,037 patients. Admission GCS and age were important in predicting mortality and discharge disposition. As GCS decreased, patients were more likely to die (risk ratio increased by average of 1.4 per 2-point drop in GCS, P < 0.001). As GCS decreased, patients were also more likely to be discharged to a skilled nursing or long-term care facility (risk ratio decreased by 0.08 per 2-point decrease in GCS, P< 0.001). The area under curve for prediction of discharge home was improved in the competing risks model 0.73 versus 0.43 in the traditional multinomial mixed model. CONCLUSIONS: Predicting older adult discharge disposition after trauma is improved using machine learning over traditional regression analysis. We confirmed that a nonlinear, competing risks paradigm enhances prediction on any given hospital day post injury.

Effects of music on the cardiovascular system.

Although music is predominantly utilized for religious, enjoyment or entertainment purposes, it is gradually emerging as a promising non-pharmacological intervention for improving health outcomes in both healthy and diseased populations, especially in those with cardiovascular diseases. As such, music of various genres and types has been postulated to possess features that stimulate or inhibit the autonomic nervous system, which leads to variable effects on cardiovascular function. However, music intervention has not been adequately explored as a cardiovascular therapeutic modality due to the lack of extensive studies with quality methodology. Thus, the aim of this systematic review is to explore the available literature on the effect of music on the cardiovascular system, discuss the limitations of current research, and suggest future directions in this field.

Optimal Donor Selection for Hematopoietic Cell Transplantation Using Bayesian Machine Learning.

PURPOSE: Donor selection practices for matched unrelated donor (MUD) hematopoietic cell transplantation (HCT) vary, and the impact of optimizing donor selection in a patient-specific way using modern machine learning (ML) models has not been studied. METHODS: We trained a Bayesian ML model in 10,318 patients who underwent MUD HCT from 1999 to 2014 to provide patient- and donor-specific predictions of clinically severe (grade 3 or 4) acute graft-versus-host disease or death by day 180. The model was validated in 3,501 patients from 2015 to 2016 with archived records of potential donors at search. Donor selection optimizing predicted outcomes was implemented over either an unlimited donor pool or the donors in the search archives. Posterior mean differences in outcomes from optimal donor selection versus actual practice were summarized per patient and across the population with 95% intervals. RESULTS: Event rates were 33% (training) and 37% (validation). Among donor features, only age affected outcomes, with the effect consistent regardless of patient features. The median (interquartile range) difference in age between the youngest donor at search and the selected donor was 6 (1-10) years, whereas the number of donors per patient younger than the selected donor was 6 (1-36). Fourteen percent of the validation data set had an approximate 5% absolute reduction in event rates from selecting the youngest donor at search versus the actual donor used, leading to an absolute population reduction of 1% (95% interval, 0 to 3). CONCLUSION: We confirmed the singular importance of selecting the youngest available MUD, irrespective of patient features, identified potential for improved HCT outcomes by selecting a younger MUD, and demonstrated use of novel ML models transferable to optimize other complex treatment decisions in a patient-specific way.

Influence of mid-life cognitive activity on cognitive function among men aged 68 years or older.

BACKGROUND: Cognitive activity in early and late life has been associated with increased cognitive function among older adults. There is less evidence on the effects of midlife cognitive activity. AIMS: We examined the association of midlife cognitive activity with cognitive function after age 65. METHODS: We studied 78 men 68 years old or older. We asked participants to assess their current and midlife cognitive activity using adaptations of a measure created by Wilson et al., which includes reading, writing letters, visiting museums and other leisure activities. Our outcomes were validated measures of cognitive and overall function. We compared midlife cognitive activity to our outcome measures in simple bivariable analyses, then adjusted for demographic characteristics using linear regression. RESULTS: Our study population of older (mean age 74.8 years) men was primarily white (87%) and well-educated; 65% had at least some post high school education. Although 67% were retired, household income was high (24% < $30 k and 44% > $50 k). More midlife cognitive activity was related to more current cognitive activity (p = < .0001, r2 = 0.55339). However, midlife activity was not associated with measures of cognitive or overall function, adjusted analyses gave similar results. DISCUSSION: We did not find an association between midlife cognitive activity and later life function. However, the Wilson measure of cognitive activity that we used excludes instrumental cognitive activities such as dealing with finances or healthcare, likely underestimating cognitive activity for many participants. CONCLUSION: Midlife cognitive activity was associated with late-life cognitive activity, suggesting efforts to increase late-life cognitive activity may need to start earlier in life. However, more robust measures of everyday cognitive activity might detect such an association.