Goto

Collaborating Authors

Artificial Intelligence Framework for Simulating Clinical Decision-Making: A Markov Decision Process Approach

arXiv.org Artificial Intelligence

In the modern healthcare system, rapidly expanding costs/complexity, the growing myriad of treatment options, and exploding information streams that often do not effectively reach the front lines hinder the ability to choose optimal treatment decisions over time. The goal in this paper is to develop a general purpose (non-disease-specific) computational/artificial intelligence (AI) framework to address these challenges. This serves two potential functions: 1) a simulation environment for exploring various healthcare policies, payment methodologies, etc., and 2) the basis for clinical artificial intelligence - an AI that can think like a doctor. This approach combines Markov decision processes and dynamic decision networks to learn from clinical data and develop complex plans via simulation of alternative sequential decision paths while capturing the sometimes conflicting, sometimes synergistic interactions of various components in the healthcare system. It can operate in partially observable environments (in the case of missing observations or data) by maintaining belief states about patient health status and functions as an online agent that plans and re-plans. This framework was evaluated using real patient data from an electronic health record. Such an AI framework easily outperforms the current treatment-as-usual (TAU) case-rate/fee-for-service models of healthcare (Cost per Unit Change: $189 vs. $497) while obtaining a 30-35% increase in patient outcomes. Tweaking certain model parameters further enhances this advantage, obtaining roughly 50% more improvement for roughly half the costs. Given careful design and problem formulation, an AI simulation framework can approximate optimal decisions even in complex and uncertain environments. Future work is described that outlines potential lines of research and integration of machine learning algorithms for personalized medicine.


Telstra Health wins government cancer-screening database contract

ZDNet

The Commonwealth Department of Health has contracted Telstra Health to construct and run the new Australian National Cancer Screening Register for the next five years, with the database to maintain patient records for cancer testing across the country. Under the contract, Telstra Health will create a database of cancer records for those who have been screened for bowel and cervical cancer, with patients and doctors able to access the register online. The register will integrate eight existing cervical cancer registers and the current bowel cancer register, with more than 11 million separate records being amalgamated onto a single platform. "The register will deliver a single database with one record per patient. People will be able to access their records online, and with patient consent, general practitioners and medical specialists will have access to patient data and records from any state or territory from their clinical desktops," Cynthia Whelan, group executive of International and New Businesses at Telstra Health, said.


The Productivity Paradox in Health Information Technology

Communications of the ACM

"Health information technology connects doctors and patients to more complete and accurate health records ... This technology is critical to improving patient care, enabling coordination between providers and patients, reducing the risk of dangerous drug interactions, and helping patients access prevention and disease management services."-- Health information technology (HIT)--the application of information technologies to enable and enhance the delivery of healthcare services--has been a central point of focus for U.S. healthcare policy since 2007. Both Presidents George W. Bush and Barack Obama outlined bold goals for HIT adoption as a key facet of each of their healthcare reform efforts, promising significant benefits for healthcare providers and patients alike.20 Clinical HIT systems, including electronic health records (EHRs), health information exchanges (HIEs), computerized provider order entry (CPOE), and telemedicine technologies, are seen as critical remedies to the complexity and inefficiency that have long plagued the U.S. healthcare industry.a


Why tech giants are claiming space in healthcare

#artificialintelligence

From cloud platforms for medical data and hospital smart rooms to artificial intelligence and patient-engagement technologies, the giants of the digital world are threatening to disrupt healthcare. Leading the pack is IBM and its centerpiece offering Watson Health. In just the last six months, the company has announced major initiatives into healthcare including a partnership with clinical consultation provider Best Doctors to add Watson's cancer suite to employee benefits packages, a population health management alliance with Siemens Healthineers and an effort linking IBM's PowerAI deep learning software toolkit with NVIDIA's NVLink interconnect technology. The PowerAI is already being used improve diagnoses and care plans by sifting through patient data. In October, Big Blue announced a $200 million investment in its Watson Internet of Things global headquarters in Munich, Germany.


Cleveland Clinic Targets Telemedicine, Big Data and AI to Improve the Future of Care

#artificialintelligence

The Cleveland Clinic has a history of being on the bleeding edge of health IT and its new CEO Tom Mihaljevic has made it clear that the Ohio-based health system will keep pushing ahead as a medical technology pioneer. "Most of our plans for the future will depend on digital platforms: telemedicine, data analytics, artificial intelligence," Mihaljevic said during the State of the Clinic address in late February. "Digital technology will allow us to deliver smarter, more affordable and more accessible [care]. The Cleveland Clinic has always been an early adopter, beginning with our electronic medical records. But now, we have to take technology even more seriously.