Machine Learning-Driven Phenogrouping and Cardiorespiratory Fitness Response in Metastatic Breast Cancer.

Novo RT ，Thomas SM ，Khouri MG ，Alenezi F ，Herndon JE 2nd ，Michalski M ，Collins K ，Nilsen T ，Edvardsen E ，Jones LW ，Scott JM ... -  《JCO Clinical Cancer Informatics》

Phenomapping of patients with heart failure with preserved ejection fraction using machine learning-based unsupervised cluster analysis.

To identify distinct phenotypic subgroups in a highly-dimensional, mixed-data cohort of individuals with heart failure (HF) with preserved ejection fraction (HFpEF) using unsupervised clustering analysis. The study included all Treatment of Preserved Cardiac Function Heart Failure with an Aldosterone Antagonist (TOPCAT) participants from the Americas (n = 1767). In the subset of participants with available echocardiographic data (derivation cohort, n = 654), we characterized three mutually exclusive phenogroups of HFpEF participants using penalized finite mixture model-based clustering analysis on 61 mixed-data phenotypic variables. Phenogroup 1 had higher burden of co-morbidities, natriuretic peptides, and abnormalities in left ventricular structure and function; phenogroup 2 had lower prevalence of cardiovascular and non-cardiac co-morbidities but higher burden of diastolic dysfunction; and phenogroup 3 had lower natriuretic peptide levels, intermediate co-morbidity burden, and the most favourable diastolic function profile. In adjusted Cox models, participants in phenogroup 1 (vs. phenogroup 3) had significantly higher risk for all adverse clinical events including the primary composite endpoint, all-cause mortality, and HF hospitalization. Phenogroup 2 (vs. phenogroup 3) was significantly associated with higher risk of HF hospitalization but a lower risk of atherosclerotic event (myocardial infarction, stroke, or cardiovascular death), and comparable risk of mortality. Similar patterns of association were also observed in the non-echocardiographic TOPCAT cohort (internal validation cohort, n = 1113) and an external cohort of patients with HFpEF [Phosphodiesterase-5 Inhibition to Improve Clinical Status and Exercise Capacity in Heart Failure with Preserved Ejection Fraction (RELAX) trial cohort, n = 198], with the highest risk of adverse outcome noted in phenogroup 1 participants. Machine learning-based cluster analysis can identify phenogroups of patients with HFpEF with distinct clinical characteristics and long-term outcomes.

Segar MW ，Patel KV ，Ayers C ，Basit M ，Tang WHW ，Willett D ，Berry J ，Grodin JL ，Pandey A ... -  《-》

Unsupervised cluster analysis reveals distinct subgroups in healthy population with different exercise responses of cardiorespiratory fitness.

Considerable attention has been paid to interindividual differences in the cardiorespiratory fitness (CRF) response to exercise. However, the complex multifactorial nature of CRF response variability poses a significant challenge to our understanding of this issue. We aimed to explore whether unsupervised clustering can take advantage of large amounts of clinical data and identify latent subgroups with different CRF exercise responses within a healthy population. 252 healthy participants (99 men, 153 women; 36.8 ± 13.4 yr) completed moderate endurance training on 3 days/week for 4 months, with exercise intensity prescribed based on anaerobic threshold (AT). Detailed clinical measures, including resting vital signs, ECG, cardiorespiratory parameters, echocardiography, heart rate variability, spirometry and laboratory data, were obtained before and after the exercise intervention. Baseline phenotypic variables that were significantly correlated with CRF exercise response were identified and subjected to selection steps, leaving 10 minimally redundant variables, including age, BMI, maximal oxygen uptake (VO2max), maximal heart rate, VO2 at AT as a percentage of VO2max, minute ventilation at AT, interventricular septal thickness of end-systole, E velocity, root mean square of heart rate variability, and hematocrit. Agglomerative hierarchical clustering was performed on these variables to detect latent subgroups that may be associated with different CRF exercise responses. Unsupervised clustering revealed two mutually exclusive groups with distinct baseline phenotypes and CRF exercise responses. The two groups differed markedly in baseline characteristics, initial fitness, echocardiographic measurements, laboratory values, and heart rate variability parameters. A significant improvement in CRF following the 16-week endurance training, expressed by the absolute change in VO2max, was observed only in one of the two groups (3.42 ± 0.4 vs 0.58 ± 0.65 ml⋅kg-1∙min-1, P = 0.002). Assuming a minimal clinically important difference of 3.5 ml⋅kg-1∙min-1 in VO2max, the proportion of population response was 56.1% and 13.9% for group 1 and group 2, respectively (P<0.001). Although group 1 exhibited no significant improvement in CRF at group level, a significant decrease in diastolic blood pressure (70.4 ± 7.8 vs 68.7 ± 7.2 mm Hg, P = 0.027) was observed. Unsupervised learning based on dense phenotypic characteristics identified meaningful subgroups within a healthy population with different CRF responses following standardized aerobic training. Our model could serve as a useful tool for clinicians to develop personalized exercise prescriptions and optimize training effects.

Xie L ，Gou B ，Bai S ，Yang D ，Zhang Z ，Di X ，Su C ，Wang X ，Wang K ，Zhang J ... -  《-》

Exercise intensity and cardiovascular health outcomes after 12 months of football fitness training in women treated for stage I-III breast cancer: Results from the football fitness After Breast Cancer (ABC) randomized controlled trial.

To examine the exercise intensity and impact of 12 months of twice-weekly recreational football training on cardiorespiratory fitness (CRF), blood pressure (BP), resting heart rate (HRrest), body fat mass, blood lipids, inflammation, and health-related quality of life in women treated for early-stage breast cancer (BC). Sixty-eight women who had received surgery for stage I-III BC and completed adjuvant chemo- and/or radiation therapy within 5 years were randomized in a 2:1 ratio to a Football Fitness group (FFG, n = 46) or a control group (CON, n = 22). Football Fitness sessions comprised a warm-up, drills and 3-4 × 7 min of small-sided games (SSG). Assessments were performed at baseline, 6 months and 12 months. Outcomes were peak oxygen uptake (VO2peak), blood pressure (BP), HRrest, total body fat mass, and circulating plasma lipids and hs-CRP, and the 36-Item Short Form Health Survey (SF36). Intention-to-treat (ITT) analyses were performed using linear mixed models. Data are means with SD or 95% confidence intervals. Adherence to training in participants completing the 12-months follow-up (n = 33) was 47.1% (22.7), and HR during SSG was ≥80% of HRmax for 69.8% (26.5) of total playing time. At baseline, VO2peak was 28.5 (6.4) and 25.6 (5.9) ml O2/kg/min in FFG and CON, respectively, and no significant changes were observed at 6- or 12 months follow-up. Systolic BP (SBP) was 117.1 (16.4) and 116.9 (14.8) mmHg, and diastolic BP (DBP) was 72.0 (11.2) and 72.4 (8.5) mmHg in FFG and CON, respectively, at baseline, and a 9.4 mmHg decrease in SBP in CON at 12 months resulted in a between-group difference at 12 months of 8.7 mmHg (p = .012). Blood lipids and hs-CRP were within the normal range at baseline, and there were no differences in changes between groups over the 12 months. Similarly, no differences between groups were observed in HRrest and body fat mass at 6- and12-months follow-up. A between-group difference in mean changes of 23.5 (0.95-46.11) points in the role-physical domain of the SF36 survey favored FFG at 6 months. Football Fitness training is an intense exercise form for women treated for breast cancer, and self-perceived health-related limitations on daily activities were improved after 6 months. However, 1 year of Football Fitness training comprising 1 weekly training session on average did not improve CRF, BP, blood lipids, fat mass, or HRrest. The trial was registered at ClinicalTrials.gov with identifier NCT03284567.

Uth J ，Fristrup B ，Sørensen V ，Helge EW ，Christensen MK ，Kjærgaard JB ，Møller TK ，Mohr M ，Helge JW ，Jørgensen NR ，Rørth M ，Vadstrup ES ，Krustrup P ... -  《-》

Heart failure with preserved ejection fraction phenogroup classification using machine learning.

Heart failure (HF) with preserved ejection fraction (HFpEF) is a complex syndrome with a poor prognosis. Phenotyping is required to identify subtype-dependent treatment strategies. Phenotypes of Japanese HFpEF patients are not fully elucidated, whose obesity is much less than Western patients. This study aimed to reveal model-based phenomapping using unsupervised machine learning (ML) for HFpEF in Japanese patients. We studied 365 patients with HFpEF (left ventricular ejection fraction >50%) as a derivation cohort from the Nara Registry and Analyses for Heart Failure (NARA-HF), which registered patients with hospitalization by acute decompensated HF. We used unsupervised ML with a variational Bayesian-Gaussian mixture model (VBGMM) with common clinical variables. We also performed hierarchical clustering on the derivation cohort. We adopted 230 patients in the Japanese Heart Failure Syndrome with Preserved Ejection Fraction Registry as the validation cohort for VBGMM. The primary endpoint was defined as all-cause death and HF readmission within 5 years. Supervised ML was performed on the composite cohort of derivation and validation. The optimal number of clusters was three because of the probable distribution of VBGMM and the minimum Bayesian information criterion, and we stratified HFpEF into three phenogroups. Phenogroup 1 (n = 125) was older (mean age 78.9 ± 9.1 years) and predominantly male (57.6%), with the worst kidney function (mean estimated glomerular filtration rate 28.5 ± 9.7 mL/min/1.73 m2 ) and a high incidence of atherosclerotic factor. Phenogroup 2 (n = 200) had older individuals (mean age 78.8 ± 9.7 years), the lowest body mass index (BMI; 22.78 ± 3.94), and the highest incidence of women (57.5%) and atrial fibrillation (56.5%). Phenogroup 3 (n = 40) was the youngest (mean age 63.5 ± 11.2) and predominantly male (63.5 ± 11.2), with the highest BMI (27.46 ± 5.85) and a high incidence of left ventricular hypertrophy. We characterized these three phenogroups as atherosclerosis and chronic kidney disease, atrial fibrillation, and younger and left ventricular hypertrophy groups, respectively. At the primary endpoint, Phenogroup 1 demonstrated the worst prognosis (Phenogroups 1-3: 72.0% vs. 58.5% vs. 45%, P = 0.0036). We also successfully classified a derivation cohort into three similar phenogroups using VBGMM. Hierarchical and supervised clustering successfully showed the reproducibility of the three phenogroups. ML could successfully stratify Japanese HFpEF patients into three phenogroups (atherosclerosis and chronic kidney disease, atrial fibrillation, and younger and left ventricular hypertrophy groups).

Kyodo A ，Kanaoka K ，Keshi A ，Nogi M ，Nogi K ，Ishihara S ，Kamon D ，Hashimoto Y ，Nakada Y ，Ueda T ，Seno A ，Nishida T ，Onoue K ，Soeda T ，Kawakami R ，Watanabe M ，Nagai T ，Anzai T ，Saito Y ... -  《ESC Heart Failure》