Development and validation of a machine learning framework for improved resource allocation in the emergency department.

OBJECTIVE: The Emergency Severity Index (ESI) is the most commonly used system in over 70% of all U.S. emergency departments (ED) that uses predicted resource utilization as a means to triage [1], Mistriage, which includes both undertriage and overtriage has been a persistent issue, affecting 32.2% of total ED visits [2]. Our goal is to develop a machine learning framework that predicts patients' resource needs, thereby improving resource allocation during triage. METHODS: This retrospective study analyzed ED visits from the Medical Information Mart for Intensive Care IV, dividing the data into training (80%) and testing (20%) cohorts. We utilized data available during triage, including patient vital signs, age, gender, mode of arrival, medication history, and chief complaint. Azure AutoML was used to create different machine learning models trained to predict the 144 target columns including laboratory panels and imaging modalities as well as medications required during patients' ED visits. The 144 models' performance was evaluated using the area under the receiver operating characteristic curve (AUROC), F1 score, accuracy, precision and recall. RESULTS: A total of 391,472 ED visits were analyzed. 144 Voting ensemble models were created for each target. All frameworks achieved on average an AUC score of 0.82 and accuracy of 0.76. We gathered the feature importance for each target and observed that 'chief complaint', among others, had a high aggregate feature importance across different targets. CONCLUSION: This study shows the high accuracy in predicting resource needs for patients in the ED using a machine learning model. This can greatly improve patient flow and resource allocation in already resource limited emergency departments.

Aging-associated decrease of PGC-1α promotes pain chronification.

Aging is generally associated with declining somatosensory function, which seems at odds with the high prevalence of chronic pain in older people. This discrepancy is partly related to the high prevalence of degenerative diseases such as osteoarthritis in older people. However, whether aging alters pain processing in the primary somatosensory cortex (S1), and if so, whether it promotes pain chronification is largely unknown. Herein, we report that older mice displayed prolonged nociceptive behavior following nerve injury when compared with mature adult mice. The expression of peroxisome proliferator-activated receptor-gamma coactivator-1α (PGC-1α) in S1 was decreased in older mice, whereas PGC-1α haploinsufficiency promoted prolonged nociceptive behavior after nerve injury. Both aging and PGC-1α haploinsufficiency led to abnormal S1 neural dynamics, revealed by intravital two-photon calcium imaging. Manipulating S1 neural dynamics affected nociceptive behavior after nerve injury: chemogenetic inhibition of S1 interneurons aggravated nociceptive behavior in naive mice; chemogenetic activation of S1 interneurons alleviated nociceptive behavior in older mice. More interestingly, adeno-associated virus-mediated expression of PGC-1α in S1 interneurons ameliorated aging-associated chronification of nociceptive behavior as well as aging-related S1 neural dynamic changes. Taken together, our results showed that aging-associated decrease of PGC-1α promotes pain chronification, which might be harnessed to alleviate the burden of chronic pain in older individuals.