麻豆村

A recent capstone project by an interdisciplinary team of graduate students from at 麻豆村 and the University of Pittsburgh School of Medicine used artificial intelligence to examine health care data and look for patterns to detect potentially dangerous drug interactions.

Four 麻豆村 master鈥檚 degree students used AI and machine learning to review databases housed at the University of Pittsburgh to look for signals of adverse drug events, adverse drug reactions or medication errors in millions of records from more than 600,000 patients from across three years of routinely collected patient care data.

鈥淲e learned all these applied skills in class 鈥� data cleaning, data analysis 鈥� but then in real-world applications, you start to see all these obstacles that you have to know how to get around,鈥� said Quentin Auster, a student in the 鈥檚 program. He led the capstone project team that also included Joanna Sam and (now-graduate) Alex Liu of the ; and Yue (Zoey) Sun, a student in the .

The research team received access to the data through funding from the Pittsburgh initiative of the Jewish Healthcare Foundation that established Carnegie Mellon鈥檚 (IPSR) in 2022 with a two-year $500,000 grant.

Detecting Adverse Events

The students mined association rules in the medication data using a method often applied to e-commerce data. Instead of suggesting similar products for customers to buy together, in this case they generated the rules from the data to guide the discovery of different medication combinations that may lead to adverse outcomes, said , Trustees Professor of Management Science and Healthcare Informatics in the Heinz College and faculty advisor of the capstone project. The team also collaborated with , digital media and marketing professor in the Heinz College, and Alan Scheller-Wolf, Richard M. Cyert Professor of Operations Management in the Tepper School of Business, both faculty leads at IPSR who facilitated access to the data at the University of Pittsburgh.

Once these combinations are identified, researchers can determine those with the highest frequency within the hundreds of thousands of records in the dataset. Clinicians can use the information to verify the risk of an adverse reaction and identify alternative medications. Detecting and reviewing the importance of the anomalies in the data would be difficult without AI and machine learning, Padman said.

鈥淭hese methods can really help to sift through the vast amounts of data, since every patient might be taking multiple medications, and with thousands of patients, there are many different combinations to examine,鈥� she said. 鈥淲e can apply these methods to extract some useful information.鈥�

Uncovering Patterns Within The Data

The team from Carnegie Mellon collaborated with Richard D. Boyce, Associate Professor of Biomedical Informatics at the University of Pittsburgh, and his research team to obtain secure access to the data, including Pitt鈥檚 (MEARs) database and the U.S. Food and Drug Administration鈥檚 (FAERS), and specialized domain knowledge about MEARs and medication-related errors.

The collaboration allowed for more resources to be dedicated toward eventually making an impact, Scheller-Wolf said.

鈥淭he dream is to solve these really big, complicated problems in society, like adverse medical events, but you鈥檙e not going to have one person solve it, or even one university,鈥� he said. 鈥淲e need a team, and collaborating across Oakland with Pitt has a huge advantage.鈥�

The capstone team conducted research through an open-source approach in a highly secure virtual workbench using a combination of data science tools that included a user-friendly research web application for large-scale analytics developed by the Observational Health Data Sciences and Informatics (or OHDSI, 鈥淥dyssey鈥�) collaborative. As the students progressed, they gained an understanding of patient journeys through visualization and analysis.

The team demonstrated their approach by narrowing their focus to patients taking colchicine, typically used to treat gout but increasingly prescribed to . Then, they looked for the antibiotic clarithromycin and medications like it that influence how the body breaks down colchicine.

鈥淚f you are a doctor practicing every day, you should know this already, so you shouldn鈥檛 have prescribed this combination together,鈥� Sun said. 鈥淲e wouldn鈥檛 expect to see a lot of instances in the EHR (electronic health record) system, which added to the difficulty for us to research and study trying to find this combination.鈥�

In applying association rule-mining to the EHR data, the team noticed the frequent pairing of colchicine with metoprolol, used to treat high blood pressure but potentially exacerbate a patient鈥檚 gout.

Their findings show that nuanced clinical judgment is necessary in the interpretation of data-derived medication patterns, said Sun, who also holds a doctorate in pharmacy, knowledge that was invaluable in helping the team decipher information on pharmaceuticals.

In future work, Padman said the approach used in this project can be evaluated using other known combinations of medications that result in adverse events or reactions, then generalized to detect new combinations that can be verified by domain experts.

鈥淭here鈥檚 really not a flag that鈥檚 specific to say 鈥榓n adverse drug event happened here,鈥� so it鈥檚 a bit like if you lose your keys,鈥� Auster said. 鈥淵ou're going to look around the streetlamp where you might have lost them. The streetlamp in this case was colchicine, which has actual signals of a place where we would expect adverse events to happen.鈥�

Determining Future Solutions

Through the IPSR, Padman is also advising other Ph.D. students on similar patient safety-related research, all part of the Carnegie Mellon鈥檚 , led by , Herbert A. Simon Professor of Computer Science in the Computational Biology Department of the .

鈥淎I does not start at the beginning of the deep network,鈥� Kingsford said. 鈥淵ou can鈥檛 train AI without data. You can鈥檛 do anything without setting up a problem. All that stuff is super-crucial, especially in the health care domain 鈥� structured data, unstructured data, weird specialized terms 鈥� that all have to be put into a model that can be used to train and apply AI.鈥�

About 250,000 to 400,000 people die annually from preventable medical errors, said Karen Feinstein, CEO of the .

Scheller-Wolf said solutions with business optimization in mind could later incentivize health care companies to adopt them.

鈥淚t鈥檚 a big problem, but if we could do something about it even marginally, we could make life better for a lot of people,鈥� he said. 鈥淲e could save a whole slew of money that we could then use to do something good rather than trying to undo something bad, so that鈥檚 a big deal.鈥�

For now, because of the fragmented nature of the health care industry, she said investment in patient safety is difficult to incentivize, but research like this project can help interest in it gain momentum.

鈥淗ealth care systems 鈥� and the data that evaluate their performance 鈥� are complex and confusing,鈥� she said. 鈥淓mployers and patients lack knowledge of the serious safety deficits that put them at risk and lack avenues to express their concerns about safety. In addition, the convoluted payment systems for health care do not reward exceptional performance in quality or safety and regulation has, so far, proved ineffective. This has put health care far behind other industries in their product and services safety. It does, however, leave the door wide open for entrepreneurs, and 麻豆村 is equipping students with the skills and insight to help drive the revolution of tech solutions for patient safety.鈥�