Artificial Intelligence, Healthcare, Clinical Genomics, and Pharmacogenomics Approaches in Precision Medicine

Abdelhalim, Habiba; Berber, Asude; Lodi, Mudassir; Jain, Rihi; Nair, Achuth Suresh; Pappu, Anirudh; Patel, Krishna; Venkat, Vignesh; Venkatesan, Cynthia; Wable, Raghu; Dinatale, Matthew; Fu, Allyson; Iyer, Vikram; Kalove, Ishan; Kleyman, Marc; Koutsoutis, Joseph; Menna, David; Paliwal, Mayank; Patel, Nishi; Patel, Thirth; Rafique, Zara; Samadi, Rothela; Varadhan, Roshan; Bolla, Shreyas; Vadapalli, Sreya; Ahmed, Zeeshan

doi:10.3389/fgene.2022.929736

Cited by 35 publications

(22 citation statements)

References 168 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A persistent challenge in genomic data analysis lies in the handling and integration of large volumes of sequencing data [26]. With the implementation of our novel CIGT AI/ML ready dataset, we have begun to make significant progress to standardize heterogenous data types (genomic and clinical) for more accurate and reliable data analysis and interpretation [27]. Our novel AI/ML methodology uncovered eighteen transcriptomic biomarkers to be linked to CVDs, three of which were novel ( RN7SL593P, AP003419.11 , and CTA-363E6.6 ) and will require further analysis to understand the correlation between them and disease etiology.…”

Section: Discussionmentioning

confidence: 99%

Discovering biomarkers associated and predicting cardiovascular disease with high accuracy using a novel nexus of machine learning techniques for precision medicine

DeGroat,

Abdelhalim,

Patel

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Personalized interventions are deemed vital given the intricate characteristics, advancement, inherent genetic composition, and diversity of cardiovascular diseases (CVDs). The appropriate utilization of artificial intelligence (AI) and machine learning (ML) methodologies can yield novel understandings of CVDs, enabling improved personalized treatments through predictive analysis and deep phenotyping. In this study, we proposed and employed a novel approach combining traditional statistics and a nexus of cutting-edge AI/ML techniques to identify significant biomarkers for our predictive engine by analyzing the complete transcriptome of CVD patients. After robust gene expression data pre-processing, we utilized three statistical tests (Pearson correlation, Chi-square test, and ANOVA) to assess the differences in transcriptomic expression and clinical characteristics between healthy individuals and CVD patients. Next, the Recursive Feature Elimination (RFE) classifier assigned rankings to transcriptomic features based on their relation to the case-control variable. The top ten percent of commonly observed significant biomarkers were evaluated using four unique ML classifiers (Random Forest, Support Vector Machine, Xtreme Gradient Boosting Decision Trees, and k-Nearest Neighbors). After optimizing hyperparameters, the ensembled models, which were implemented using a soft voting classifier, accurately differentiated between patients and healthy individuals. We have uncovered 18 transcriptomic biomarkers that are highly significant in the CVD population that were used to predict disease with up to 96% accuracy. Additionally, we cross-validated our results with clinical records collected from patients in our cohort. The identified biomarkers served as potential indicators for early detection of CVDs. With its successful implementation, our newly developed predictive engine provides a valuable framework for identifying patients with CVDs based on their biomarker profiles.

show abstract

Section: Discussionmentioning

confidence: 99%

Discovering biomarkers associated and predicting cardiovascular disease with high accuracy using a novel nexus of machine learning techniques for precision medicine

DeGroat,

Abdelhalim,

Patel

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, it is extremely difficult to collect, select, or identify sources for evidence-based medical information. This paradox inevitably leads to empirical medicine remaining the dominant medical practice, seriously hindering the transition from clinical practice to evidence-based models (Abdelhalim et al, 2022). The second type of confusion is that of clinical staff.…”

Section: Discussionmentioning

confidence: 99%

Establishment and implementation of a clinical application and research database for surgical robots in China

Ma,

Li,

et al. 2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Robots are widely used in surgeries worldwide. To improve robotic surgical treatments, we established a database of clinical applications and research on surgical robots. Robotics‐related literature included in the China national knowledge infrastructure (CNKI), Wanfang, Vipshop, Chinese science citation database (CSCD), Web of Science, EMBASE, PubMed, and Cochrane databases up to September 2022 was searched and entered into the database. Information on all patients who had undergone robotic surgery at our hospital since 2016 was also included. Literature and case information was classified and evaluated according to standard guidelines and statements. The Gansu Provincial Hospital was the first to use evidence‐based medical research methods to successfully establish a database of clinical applications and research on surgical robots. This database comprised literature search, upload, quality evaluation, risk of bias assessment, case information entry, and access functions. Based on the database, we conducted related studies in general surgery, gynecology, urology, thoracic surgery, and cardiovascular surgery, and published 16 meta‐analyses and 15 clinical studies. Establishing this database removes language, retrieval, and evaluation barriers in clinicians' use of clinical evidence and lays the foundation for the efficient and accurate use of clinical data for future research. Further, it facilitates evidence‐based evaluation of the effectiveness of robotic therapy, which may guide future medical practice. This typical case of interdisciplinary research aims to build a platform to disseminate knowledge and technology in robotic surgery.This article is categorized under: Technologies > Computer Architectures for Data Mining Application Areas > Data Mining Software Tools Application Areas > Education and Learning

show abstract

“…Gene variations in analgesic/sedative drug transporters, drug targets, and metabolizing enzymes in the form of single‐nucleotide polymorphisms (SNPs) may influence response to pharmacotherapy 12 . For a deeper understanding of precision medicine and the common pharmacogenetic mechanisms that influence it, recent reviews and resources on this topic should be consulted 1,12,17 …”

Section: Common Genetic Polymorphisms Leading To Variability In Analg...mentioning

confidence: 99%

A pharmacogenetic precision medicine approach to analgesia and sedation optimization in critically ill adults

2023

View full text Add to dashboard Cite

Precision medicine is a growing field in critical care. Research increasingly demonstrated pharmacogenomic variability to be an important determinant of analgesic and sedative drug response in the intensive care unit (ICU). Genome‐wide association and candidate gene finding studies suggest analgesic and sedatives tailored to an individual's genetic makeup, environmental adaptations, in addition to several other patient‐ and drug‐related factors, will maximize effectiveness and help mitigate harm. However, the number of pharmacogenetic studies in ICU patients remains small and no prospective studies have been published using pharmacogenomic data to optimize analgesic or sedative therapy in critically ill patients. Current recommendations for treating ICU pain and agitation are based on controlled studies having low external validity, including the failure to consider pharmacogenomic factors affecting response. Use of a precision medicine approach to individualize pharmacotherapy focused on optimizing ICU patient comfort and safety may improve the outcomes of critically ill adults. Additionally, benefits and risks of analgesic and/or sedative therapy in an individual may be informed with large, standardized datasets. The purpose of this review was to describe a precision medicine approach focused on optimizing analgesic and sedative therapy in individual ICU patients to optimize clinical outcomes and reduce safety concerns.

show abstract

Artificial Intelligence, Healthcare, Clinical Genomics, and Pharmacogenomics Approaches in Precision Medicine

Cited by 35 publications

References 168 publications

Discovering biomarkers associated and predicting cardiovascular disease with high accuracy using a novel nexus of machine learning techniques for precision medicine

Discovering biomarkers associated and predicting cardiovascular disease with high accuracy using a novel nexus of machine learning techniques for precision medicine

Establishment and implementation of a clinical application and research database for surgical robots in China

A pharmacogenetic precision medicine approach to analgesia and sedation optimization in critically ill adults

Contact Info

Product

Resources

About