Christopher Thompson

Khushboo Verma, Alan Michels, Ergi Gumusaneli et al.

Referral workflow inefficiencies, including misaligned referrals and delays, contribute to suboptimal patient outcomes and higher healthcare costs. In this study, we investigated the possibility of predicting procedural needs based on primary care diagnostic entries, thereby improving referral accuracy, streamlining workflows, and providing better care to patients. A de-identified dataset of 2,086 orthopedic referrals from the University of Texas Health at Tyler was analyzed using machine learning models built on Base General Embeddings (BGE) for semantic extraction. To ensure real-world applicability, noise tolerance experiments were conducted, and oversampling techniques were employed to mitigate class imbalance. The selected optimum and parsimonious embedding model demonstrated high predictive accuracy (ROC-AUC: 0.874, Matthews Correlation Coefficient (MCC): 0.540), effectively distinguishing patients requiring surgical intervention. Dimensionality reduction techniques confirmed the model's ability to capture meaningful clinical relationships. A threshold sensitivity analysis identified an optimal decision threshold (0.30) to balance precision and recall, maximizing referral efficiency. In the predictive modeling analysis, the procedure rate increased from 11.27% to an optimal 60.1%, representing a 433% improvement with significant implications for operational efficiency and healthcare revenue. The results of our study demonstrate that referral optimization can enhance primary and surgical care integration. Through this approach, precise and timely predictions of procedural requirements can be made, thereby minimizing delays, improving surgical planning, and reducing administrative burdens. In addition, the findings highlight the potential of clinical decision support as a scalable solution for improving patient outcomes and the efficiency of the healthcare system.

Christopher Thompson, Josh Introne, Clint Young

'Health utilities' measure patient preferences for perfect health compared to specific unhealthy states, such as asthma, a fractured hip, or colon cancer. When integrated over time, these estimations are called quality adjusted life years (QALYs). Until now, characterizing health utilities (HUs) required detailed patient interviews or written surveys. While reliable and specific, this data remained costly due to efforts to locate, enlist and coordinate participants. Thus the scope, context and temporality of diseases examined has remained limited. Now that more than a billion people use social media, we propose a novel strategy: use natural language processing to analyze public online conversations for signals of the severity of medical conditions and correlate these to known HUs using machine learning. In this work, we filter a dataset that originally contained 2 billion tweets for relevant content on 60 diseases. Using this data, our algorithm successfully distinguished mild from severe diseases, which had previously been categorized only by traditional techniques. This represents progress towards two related applications: first, predicting HUs where such information is nonexistent; and second, (where rich HU data already exists) estimating temporal or geographic patterns of disease severity through data mining.