Prince Afriyie

Early identification of high risk heart failure (HF) patients is key to timely allocation of life-saving therapies. Hemodynamic assessments can facilitate risk stratification and enhance understanding of HF trajectories. However, risk assessment for HF is a complex, multi-faceted decision-making process that can be challenging. Previous risk models for HF do not integrate invasive hemodynamics or support missing data, and use statistical methods prone to bias or machine learning methods that are not interpretable. To address these limitations, this paper presents CARNA, a hemodynamic risk stratification and phenotyping framework for advanced HF that takes advantage of the explainability and expressivity of machine learned Multi-Valued Decision Diagrams (MVDDs). This interpretable framework learns risk scores that predict the probability of patient outcomes, and outputs descriptive patient phenotypes (sets of features and thresholds) that characterize each predicted risk score. CARNA incorporates invasive hemodynamics and can make predictions on missing data. The CARNA models were trained and validated using a total of five advanced HF patient cohorts collected from previous trials, and compared with six established HF risk scores and three traditional ML risk models. CARNA provides robust risk stratification, outperforming all previous benchmarks. Although focused on advanced HF, the CARNA framework is general purpose and can be used to learn risk stratifications for other diseases and medical applications.

Adjusting yearly pruning severity is a common vineyard management practice employed to manipulate vegetative and reproductive growth in grapevines. Although the effects of pruning on total vegetative growth are well documented, there is little research on the effects of adjusting shoots meter⁻¹ via dormant season pruning on addressing mid-cordon shoot weakness and developmental delays. Cordon-trained, spur-pruned vines are thought, by many growers, to be especially prone to weaker positions and delayed development at mid-cordon positions. This phenomenon is also thought to become more exaggerated as the vine ages. Therefore, the effects of shoot density manipulation, implemented via dormant pruning practices, to homogenize shoot and cluster development along the length of the cordon were examined. In this research, Cabernet Sauvignon grapevines were pruned to either 5.5 shoots meter⁻¹ (5.5) or 11.1 shoots meter⁻¹ (11.1). To control for variations in light interception into the fruiting zone, a control of 11.1 shoots meter⁻¹ with sensor guided leaf thinning (11.1LT) was implemented at full berry set to match the canopy light of the 5.5 shoots meter⁻¹ treatment. It was found that individual shoot growth and yield were directly impacted by manipulation of pruning severity. Shoot growth response varied primarily by growing season, including shoot length and internode length. Yield components were significantly lower in the 5.5 treatment during the first two years of the study but were not significantly different during the last year of the study. The 5.5 treatment resulted in the highest pH and total soluble solids at harvest in 2016 and 2017.