“It is not difficult to set up a system that applies the best predictive algorithm on all data available at discharge to gage readmission risk and suggest mitigation strategies.”
Dr. Hill joined Dell through Dell’s acquisition of StatSoft in April 2014, and he is currently the Executive Director for Analytics at Dell’s Information Management Group. Dr. Hill has received numerous academic grants and awards from the National Science Foundation, the National Institute of Health, the Center for Innovation Management, the Electric Power Research Institute, and other institutions. He has completed diverse consulting projects with companies from practically all industries and has worked with the leading financial services, insurance, manufacturing, pharmaceutical, retailing, and other companies in the United States and internationally on identifying and refining effective data mining and predictive modeling solutions for diverse applications.
As a distinguished member of the Institute’s speaker faculty for the upcoming Health IT Summit in San Francisco, taking place,March 3-4, Hill shares insight into his role at Dell.
Institute: Can you start by giving us a brief overview of your role at Dell?
Hill: I came to Dell through the acquisition of StatSoft last year, but my role has not changed that much. For the last 20+ years, I have been responsible for the development of analytic methods and algorithms for the Dell-Statistica analytics platform and solutions. That means I am involved with data scientists and teams of developers to drive core analytics technologies; I am also working with customers and clients to make sure we understand the often complex and multi-faceted requirements facing various businesses. With respect to the latter role and activities, I have been working for the past few years with various businesses involved in healthcare delivery on the provider side, hospital administration side, as well as the health plan side.
Institute: What tools might Dell be able to provide to help engage and provide visibility for post-discharge behavior?
Hill: Dell is in a unique position – that is why I was excited to join Dell; but let me step back for a moment. We all know we live in remarkable times. Today I can literally ask my cellphone to explain to me the symptoms, causes and best treatments for a particular disease. The technology revolution has changed so many aspects of our lives, and it will completely change how healthcare is organized, delivered and paid for not only in the US but worldwide.
But we are only at the beginning of this revolution. I recently coauthored a book on predictive analytics applications for healthcare.1 I call it the “big-book-of-analytics-for-healthcare” because it has many authors, and it is truly voluminous. It reflects the numerous approaches, theoretical, practical and regulatory considerations, as well as use cases around and for healthcare. We are truly at the beginning of an inflection point with big changes and I believe there are tremendous benefits before all of us, including patients, hospitals, doctors, nurses, caregivers or insurers.
Now back to the original question: What can Dell do? Dell has always brought the benefits of “hi-tech” to a broad audience. You can hardly enter an office, laboratory or university where there isn’t “something Dell.” What many people don’t know is that today, Dell has a huge footprint in healthcare and life sciences, in services (e.g., #1 IT healthcare services worldwide for Healthcare Provider according to Gartner), software (Dell is now one of the largest software companies in the world by revenue, with recognized leadership in data integration, security, analytics, etc.), cloud-based technologies and services (e.g., over 100 MEDITECH customers supported with cloud-based deployments), etc.
To be specific, here is my prediction: In five years, diagnostic/medical decisions and treatments will be informed through:
- Data collected via internet-enabled devices and sensors,
- Stored securely and safely in private or public clouds (cloud servers),
- Filtered through advanced automated machine learning algorithms to extract critical information
- Delivered to healthcare providers and patients via tablets, cellphones, or in one-on-one teleconferences between medical specialists and patients who can remain at home
The result will be personalized medicine, delivered more conveniently and efficiently through modern communication technology, and based on big-data analytics that can deliver best practices even to previously underserved populations.
Dell has the hardware and computer expertise, the software to manage big data securely, and the professional and services expertise to deliver real solutions that will augment the ability of hospitals, healthcare providers, as well insurance providers to do what they do best.
In short, it takes the end-to-end capabilities to allow healthcare professionals to focus on their tasks.
Institute: What are some of the current challenges and pitfalls associated with hospital readmissions?
Hill: Actually, most of the challenges I believe have been solved. It is not difficult to set up a system that applies the best predictive algorithm on all data available at discharge to gage readmission risk and suggest mitigation strategies. Nevertheless, it is important to think through how such a system will be used – exactly… I like to point out that every project starts at the end: How do I know I am done, and how do I know I won? How exactly would results look like that are actionable, and how will they be acted upon and by whom? Once that is clear, the rest is just implementation and connecting the wires, data sources and systems.
Institute: What are a few strategies for successfully coordinating care after discharge?
Hill: That depends of course on the specific patient population and conditions. In general, it is through outreach and follow-up to the patient and her or his support system that ambiguities with medication, expected and unexpected symptoms after release, compliance with therapy regimens and so on can be addressed. Ideally, at the point of discharge to the right post-hospitalization environment and services, (predicted to minimize readmission risk) real high-risk discharges can be avoided.
Institute: You will be participating on the panel “Reducing Readmission Rates: Tech Enabled Strategies” at the upcoming Health IT Summit in San Francisco. What can the attendees of the program expect to take away from your participation?
Hill: First, I am greatly looking forward to learning from the insights of other practitioners as well as researchers and administrators “in the trenches.” Dell is in the business of delivering technology-based solutions that make the world a better place, and healthcare is complex, multi-faceted and changing very quickly. I have been involved in delivering analytic solutions across various industries – from pharmaceutical manufacturing to risk modeling for banks or insurance companies – for over 20 years. I hope that I can bring to this panel insights and recommendations that transcend specific applications and help the audience avoid costly or time-consuming mistakes.
Among all the industries and domains, healthcare is special as it affects all of us in very personal and often life-changing ways. I am excited to be part of the predictive-analytics-revolution that has so much to offer to improve the lives of people when they are perhaps most vulnerable.
1See Miner, L.; Bolding, P.; Hilbe, J.; Goldstein, M.; Hill, T.; Nisbet, R.; Walton, N.; Miner, G. (2014). Practical Predictive Analytics and Decisioning Systems for Medicine: Informatics Accuracy and Cost-Effectiveness for Healthcare Administration and Delivery Including Medical Research. Elsevier.
