KDnuggets Home » News » 2015 » Mar » Opinions, Interviews, Reports » Interview: Slava Akmaev, Berg on Challenges in Transitioning Analytics to Clinical Utility ( 15:n08 )

Interview: Slava Akmaev, Berg on Challenges in Transitioning Analytics to Clinical Utility


We discuss Analytics use cases, challenges in relating molecular/clinical data to real-life outcomes, Healthcare Analytics trends and more.



Slava AkmaevSlava Akmaev, Ph.D. is Senior Vice President and Chief Analytics Officer at Berg. Dr. Akmaev leads innovation in Big Data analytics applied to fundamental patient management problems in healthcare, drug development, and diagnostics. During his tenure at Berg, Dr. Akmaev has developed and launched Berg Analytics Suite of data science applications that allow the life scientists and clinicians to harvest the power of Big Data and affect real world patient outcomes. He works closely with the drug and biomarker development teams and directs research informatics, healthcare analytics, and personalized medicine programs within Berg and its subsidiary companies.

Dr. Akmaev continues to innovate in the application of Bayesian artificial intelligence in healthcare IT. Prior to joining Berg, he was Vice President of Scientific Affairs at a Big Data analytics company, Scientific Associate Director at Genzyme Genetics and a Bioinformatics lead at Genzyme. Dr. Akmaev holds a Ph.D. in Applied Mathematics from the University of Colorado at Boulder.

First part of interview

Here is second and last part of my interview with him:

Anmol Rajpurohit: Q6. What is your favorite Analytics use case at Berg? What were the results and lessons learned?

cmsSlava Akmaev: We have completed numerous projects within Berg, and in collaboration with other organizations, and every project is remarkable in its own way. One of the more recent case studies that really excited us was the analysis of publically released CMS billing data. We looked at a high level data from 2011 of top 100 billing discharge codes across the largest providers in the U.S. This case study proved to us that hypothesis-free, data driven approaches have merit and are especially viable in Big Data.

AR: Q7. What are the unique challenges of working on molecular and clinical data? Why is it so challenging to relate this data to real-life outcomes (as mentioned on EMRs)?

healthcare-data-challengesSA: As you pointed out in the question, I think the most challenging aspect of working with research molecular and clinical data is the transition from data to clinical utility. We as an industry have been living in the genomics era for more than 15 years. There are thousands of microarray data sets and more than a million gene expression microarray experiments on GEO. There are other publically available omics data linked to extensive clinical information. Again, the healthcare industry is still struggling to make the leap from data to actionable clinical utility. This is where Berg is. We hope to make a difference in creating socially impactful programs from Big Data in healthcare.

AR: Q8. What key trends will drive the growth of Healthcare Analytics for the next 2-3 years? What factors will play a critical role in the success of Healthcare Analytics projects?

patient-focusSA: The Healthcare Analytics industry is rapidly growing. I have seen announcements from dozens of start-ups in the area of healthcare analytics in the last several months - from nurse room dashboard software to complex machine learning and AI based approaches applied to longitudinal patient data. Large corporations are getting involved as well. GE Healthcare is investing heavily in healthcare analytics, IBM is training Watson in clinical oncology, and I am sure Google and Apple are up to something in mobile health and precision medicine. What will continue to drive the growth and sustainability is real world application and utility. Every day, my team at Berg Analytics looks beyond the volumes of data and the complexity of the analysis. Often times the most useful answers are not the most complex. The critical success factor for Healthcare Analytics is our ability to positively affect real world patient outcomes.

AR: Q9. What is the best advice you have got in your career?

SA: The best advice I had in my career, and I am happy to give it to anyone working in healthcare, was to take the time to think about your work having an impact on the patient. Irrespective of the project type and area of the healthcare and pharma/biotech industry you work in, have the patient and the patient benefit come first.

AR: Q10. What key qualities do you look for when interviewing for Data Science related positions on your team?

SA: Outside of basic qualifications that are common in the analytics and bioinformatics space, I look for bright, self-motivated and driven individuals. We have positions open in Analytics for anyone fitting these criteria. Please apply on our website.

AR: Q11. On a personal note, are there any good books that you have been reading lately and would like to recommend? What keeps you busy when you are away from work?

great-prostate-hoaxSA: For better or for worse I mostly read scientific and medical literature. However, I can highlight a book that recently captured my attention, The Great Prostate Hoax, by Dr. Richard Ablin. I would recommend that book to all men in their 40’s and older. It is a compilation of a tremendous amount of information on the history and the present state of urology as it relates to prostate cancer.

On a personal note, I try to find the right work/life balance in my life. When I am not working or not thinking about science and medicine, I spend time with my family.

Related: