Interview with Zeeshan Ahmed of UConn Health

Dr. Ahmed’s lab at UConn Health is focused on doing research and development of intelligent big data analytics platforms to improve the quality and transition of healthcare for investigating heterogeneous clinical data to obtain actionable care gap-based information about patients for early detection and prevention of constitutional disorders and cancer, and developing efficient communication across healthcare units and scientific labs. Dr. Ahmed proposes PROMIS-Med; an advanced academic solution with effective, integrative and analytic access to clinical. Read his full bio.

Interview with Zeeshan Ahmed of UConn Health

Q: Artificial intelligence (AI) techniques have sent vast waves across healthcare, even fueling an active discussion of whether AI doctors will eventually replace human physicians in the future. Do you believe that human physicians will be replaced by machines in the foreseeable future?

A: I personally believe that this question is little unfair, why we need to think that will machines replace physicians? Instead, we should think that how machines can play a vital role in improving the practice transformation by helping physicians. So far technology has been very effective and helpful, and looking at its progress, we can predict its bright future in natural and medical sciences.

Q: What are your thoughts?

A: Intelligent, innovative, smart and robust big data platforms are necessary to improve the quality and transition of healthcare by analyzing heterogeneous healthcare and OMICS data. To effectively meet the goals of healthcare data analytics, significant efforts are required from the experts in multidisciplinary sciences, located within one or multiple organizational units. One of the major unsolved challenges is to establish an efficient and secure workflow that can connect all internal and external organizational units, people, and systems to streamline transparent and reproducible data flow, quality inspection, integration, management, analysis, visualization, reporting, and sharing. AI and Data science can play a vital role in confluence of these modules, which will create space for a new era of open data and discovery in public healthcare.

Q: Can you provide some use cases that have already successfully demonstrate the value of AI/Machine Learning in healthcare?

A: There are many in-house, external academic, industrial and collaborative examples demonstrating potential benefits and strengths of AI and Data Science in healthcare. Talking about the institution, I am associated with; UConn Health is actively working at various subjects, which includes development of intelligent healthcare data analytic systems to combine clinical and genetic data from patients with information from scientific research, and apply AI techniques to identify patients at risks. UConn Health has also recently developed remote patient monitoring iPhone app to help patients suffering with heart failure, which in particular requires daily monitoring of many health parameters to enable management success and avoid decompensation and hospitalizations.

Highlighting worldwide efforts e.g., researchers at the University of Pennsylvania Health System have developed a machine learning tool that helps predict patients at highest risk for developing severe sepsis; Harvard and UPenn researchers are using AI to predict mortality for cancer patients; Microsoft and Cleveland Clinic collaborated and used Cortana to identify potential at-risk patients under ICU care; UCLA researchers presented Virtual Interventional Radiologist (VIR) to automatically communicate with referring clinicians; researchers at the University of Cambridge have developed an AI ‘robot scientist’ called Eve, which is designed to make the process of drug discovery faster and more economical; Arthritis Virtual Assistant developed by IBM to learn through interactions with patients and advice concerning medicines, diet, and exercise; and many other bioinformatics tools have been developed for the management and analysis of data leading to chronic medical conditions.

Q: What areas in healthcare will benefit the most from AI/Machine Learning applications and when will that be?

A: Healthcare data includes information about patient life style, medical history, visits to the practice, lab tests, imaging tests, diagnoses, medications, surgical procedures, consulted providers, claims, and OMICS profiles. Theoretically, almost every aspect of healthcare could benefit from Machine learning and Data Science applications e.g., intelligently analyzing healthcare data to predict and identify infection patterns to highlight patients at risk; mining biomedical images to predict cancer and many other serious diseases; developing decision support systems to improve clinical decision making process; implementing smart devices for monitoring, communicating, and helping patients; managing big data quality, analytic and integrity issues; and additionally, contributing in regeneration of artificial tissues and organs etc.

Q: What are some of the challenges to realize AI/Machine learning in healthcare?

A: Some of the neediest areas for AI include implementation of predictive analytics in clinical decision support systems and precision medicine; quick and comprehensive recognition of shifts and patterns in medical imaging data; efficient analysis of Echocardiography scans to detect patterns of heartbeats and diagnose coronary heart disease; and AI robots to efficiently carry out specific tasks in keyhole surgeries etc.

Q: What are the products and/or services UConn Health offers/develops in the AI/Machine Learning sector? What makes UConn Health unique?

A: UConn Health is a vibrant, integrated academic medical center that is entering an era of unprecedented growth in all three areas of its mission: academics, research, and clinical care.
It will be very broad and at large scaled to talk about UConn Health in detail, instead, I would like to draw focus on my lab at the Department of Genetics and Genome Sciences.

Ahmed lab is involved in the research and development of various bioinformatics, healthcare and genomics projects implementing Data Science and AI. However, its major focus is Precision Medicine and recently, we have proposed an innovatively designed big data platform i.e. Precise & Reproducible OMICS-Data Management and Integrative System for Precision Medicine (PROMIS-Med); an advanced academic solution with effective, integrative and analytic access to clinical, epidemiological, metabolomics, proteomics and genomics data of huge volume, velocity, variety, and veracity, and with the potential to advance the field of medicine with best strategies to diagnose and treat patients, and developing better understanding of biology. Aims include the development of one of the world’s largest precision medicine platforms to help patients, providers, practices and scientists.

Q: What are the short-term challenges that Ahmed Lab, at UConn Health and its peers are facing?

A: Doing research is all about finding and addressing challenges, now whether those are scientific, medical, methodological, computational, economical, data or resource oriented. Short-term challenges at my lab includes the allocation of resources for the efficient management, analysis and sharing of healthcare and OMICS data, and its increasing volume. Furthermore, we are actively looking forward to excellent in-house and worldwide collaborations, and funding opportunities.

Q: What is your role at UConn Health and what excites you about your work?

A: I am associated as an Assistant Professor and Assistant Director Bioinformatics: Medical Dean’s Precision Medicine Program at the Department of Genetics and Genome Sciences, School of Medicine, University of Connecticut Health Center (UConn Health), Farmington, CT, USA. I am playing different roles at UConn Health, which include: teaching and mentoring residents, fellows, staff and students; leading different clinical operational and research oriented projects; participating in direct and collaborative grant writing and publications; implementing HIPAA compliant healthcare data analytics platforms; planning development aspects required for Health IT systems including translation engine, data abstraction tools, data warehouse, data marts, analytic tools and healthcare data transport systems, as appropriate for the projects.

I feel excited in establishing my lab at UConn Health with focus on doing research and development of intelligent big data analytics platforms to improve the quality and transition of healthcare for investigating heterogeneous clinical data to obtain actionable care gap-based information about patients for early detection and prevention of constitutional disorders and cancer, and developing efficient communication across healthcare units and scientific labs. Playing my roles and establishing my lab, here, I would like to mention and sincerely acknowledge the strong support and guidance of Prof. Dr. Bruce Liang; Dean UConn School of Medicine, UConn Health. I am grateful to my department’s chair, Prof. Dr. Brenton Graveley, collaborators: Prof. Dr. Anthony Vella and Prof Dr. Melinda Sanders at UConn Health, Dr. Saman Zeeshan at The Jackson Laboratory, and Prof. Dr. Thomas Dandekar at the University of Wuerzburg, Germany.

Q: Is there anything else you would like to share with the PMWC audience?

A: Over a decade ago, earlier joining the fields of bioinformatics and healthcare data analytics, during one of my interviews for first job, I was asked a question that “why you decided to join the field of Computer Science?”, and I answered “because it’s in all fields of life, and I will enjoy working with increasing interests”. I feel proud for being part of it and glad to see the progress of AI and Data Science, when serving the field of medicine for benefiting humanity and saving lives.