The advent of advances in machine learning (ML)-based techniques has popularized wide applications of artificial intelligence (AI) in various fields ranging from robotics to medicine. In recent years, there has been a surge in the application of AI to research in cardiovascular medicine, which is largely driven by the availability of large-scale clinical and multi-omics datasets. Such applications are providing a new perspective for a better understanding of cardiovascular disease (CVD), which could be used to develop novel diagnostic and therapeutic strategies. For example, studies have shown that ML has a substantial potential for early diagnosis of different types of CVD, prediction of adverse disease outcomes such as heart failure, and development of newer and personalized treatments. Early diagnosis and accurate classification of cardiovascular diseases are critical for precision medicine in clinical practice. Through the projects undertaken as part of this thesis research, we aimed to explore the use of different machine learning techniques in the field of cardiovascular health, albeit with a new perspective of using gut microbiome data as a new feature to classify individuals with and without cardiovascular disease. The rationale for this choice is that besides genetics and environmental factors, in recent years, gut microbiota has emerged as a new factor influencing CVD. Although cause-effect relationships are not clearly established, the reported associations between alterations in gut microbiota and CVD are prominent. An additional consideration for choosing gut microbiota as the feature of choice is based on previous findings in our laboratory and validated by other groups indicating that dysbiosis of gut microbiota is strongly associated with cardiovascular risk.
This thesis comprises two parts, one of which is in the press for publication (Part 1) and the second one (Part 2) has been peer-reviewed and published. Part 1 is a comprehensive review of artificial intelligence and its application in cardiovascular medicine. In this review, we provide an overview and discuss the current status of a wide range of AI applications, including machine learning, reinforcement learning, and deep learning, in cardiovascular medicine. My contribution to this paper was to gather literature, write various sections of the review, and assemble the sections. Moreover, I also designed the figures, reviewed, and edited the manuscript.
Part 2 catalogs my research project wherein, 16S rRNA microbiome data from the American Gut Project was used for categorizing subjects with and without cardiovascular disease using machine learning. Briefly, we hypothesized that machine learning (ML) could be used for gut microbiome-based diagnostic screening of CVD. To test our hypothesis, fecal 16S rRNA sequencing data of 478 CVD and 473 non-CVD human subjects collected through the American Gut Project were analyzed using 5 supervised ML algorithms including random forest (RF), support vector machine, decision tree, elastic net, and neural networks (NN). Thirty-nine differential bacterial taxa were identified between the CVD and non-CVD groups. ML modeling using these taxonomic features achieved a testing AUC (area under the receiver operating characteristic curves; 0.0: perfect anti-discrimination; 0.5: random guessing; 1.0: perfect discrimination) of ~0.58 (RF and NN). Next, the ML models were trained with the top 500 high-variance features of operational taxonomic units (OTUs), instead of bacterial taxa, and an improved testing AUC of ~0.65 (RF) was achieved. Further, by limiting the selection to only the top 25 highly contributing OTU features, the AUC was further significantly enhanced to ~0.70. Overall, our study is the first to identify dysbiosis of gut microbiota in CVD patients as a group and apply this knowledge to develop a gut microbiome-based ML approach for diagnostic screening of CVD. In conclusion, our study demonstrated the promising potential of using artificial intelligence via ML modeling as a novel approach to classify subjects with or without cardiovascular diseases. My contribution to this publication was in data curation, formal analysis, investigation, methodology, visualization, validation, and writing the original draft of the manuscript, followed by review and editing.