Deep learning predicts postoperative opioids refills in a multi-institutional cohort of surgical patients.

BACKGROUND: To combat the opioid epidemic, several strategies were implemented to limit the unnecessary prescription of opioids in the postoperative period. However, this leaves a subset of patients who genuinely require additional opioids with inadequate pain control. Deep learning models are powerful tools with great potential of optimizing health care delivery through a patient-centered focus. We sought to investigate whether deep learning models can be used to predict patients who would require additional opioid prescription refills in the postoperative period after elective surgery. METHODS: This is a retrospective study of patients who received elective surgical intervention at the Mayo Clinic. Adult English-speaking patients ≥18 years old, who underwent an elective surgical procedure between 2013 and 2019, were eligible for inclusion. Machine learning models, including deep learning, random forest, and eXtreme Gradient Boosting, were designed to predict patients who require opioid refills after discharge from hospital. RESULTS: A total of 9,731 patients with mean age of 62.1 years (51.4% female) were included in the study. Deep learning and random forest models predicted patients who required opioid refills with high accuracy, 0.79 ± 0.07 and 0.78 ± 0.08, respectively. Procedure performed, highest pain score recorded during hospitalization, and total oral morphine milligram equivalents prescribed at discharge were the top 3 predictors for requiring opioid refills after discharge. CONCLUSION: Deep learning models can be used to predict patients who require postoperative opioid prescription refills with high accuracy. Other machine learning models, such as random forest, can perform equal to deep learning, increasing the applicability of machine learning for combating the opioid epidemic.

Quantitative Abdominal Arterial Calcification Correlates with Kidney Transplant Waitlist Mortality.

INTRODUCTION: The scarcity of available organs for kidney transplantation has resulted in a substantial waiting time for patients with end-stage kidney disease. This prolonged wait contributes to an increased risk of cardiovascular mortality. Calcification of large arteries is a high-risk factor in the development of cardiovascular diseases, and it is common among candidates for kidney transplant. The aim of this study was to correlate abdominal arterial calcification (AAC) score value with mortality on the waitlist. METHODS: We modified the coronary calcium score and used it to quantitate the AAC. We conducted a retrospective clinical study of all adult patients who were listed for kidney transplant, between 2005 and 2015, and had abdominal computed tomography scan. Patients were divided into two groups: those who died on the waiting list group and those who survived on the waiting list group. RESULTS: Each 1,000 increase in the AAC score value of the sum score of the abdominal aorta, bilateral common iliac, bilateral external iliac, and bilateral internal iliac was associated with increased risk of death (HR 1.034, 95% CI: 1.013, 1.055) (p = 0.001). This association remained significant even after adjusting for various patient characteristics, including age, tobacco use, diabetes, coronary artery disease, and dialysis status. CONCLUSION: The study highlights the potential value of the AAC score as a noninvasive imaging biomarker for kidney transplant waitlist patients. Incorporating the AAC scoring system into routine imaging reports could facilitate improved risk assessment and personalized care for kidney transplant candidates.

The integration of artificial intelligence in robotic surgery: A narrative review.

BACKGROUND: The rise of high-definition imaging and robotic surgery has independently been associated with improved postoperative outcomes. However, steep learning curves and finite human cognitive ability limit the facility in imaging interpretation and interaction with the robotic surgery console interfaces. This review presents innovative ways in which artificial intelligence integrates preoperative imaging and surgery to help overcome these limitations and to further advance robotic operations. METHODS: PubMed was queried for "artificial intelligence," "machine learning," and "robotic surgery." From the 182 publications in English, a further in-depth review of the cited literature was performed. RESULTS: Artificial intelligence boasts efficiency and proclivity for large amounts of unwieldy and unstructured data. Its wide adoption has significant practice-changing implications throughout the perioperative period. Assessment of preoperative imaging can augment preoperative surgeon knowledge by accessing pathology data that have been traditionally only available postoperatively through analysis of preoperative imaging. Intraoperatively, the interaction of artificial intelligence with augmented reality through the dynamic overlay of preoperative anatomical knowledge atop the robotic operative field can outline safe dissection planes, helping surgeons make critical real-time intraoperative decisions. Finally, semi-independent artificial intelligence-assisted robotic operations may one day be performed by artificial intelligence with limited human intervention. CONCLUSION: As artificial intelligence has allowed machines to think and problem-solve like humans, it promises further advancement of existing technologies and a revolution of individualized patient care. Further research and ethical precautions are necessary before the full implementation of artificial intelligence in robotic surgery.

Academic Surgery in the Era of Large Language Models: A Review.

Importance: This review aims to assess the benefits and risks of implementing large language model (LLM) solutions in an academic surgical setting. Observations: The integration of LLMs and artificial intelligence (AI) into surgical practice has generated international attention with the emergence of OpenAI's ChatGPT and Google's Bard. From an administrative standpoint, LLMs have the potential to revolutionize academic practices by reducing administrative burdens and improving efficiency. LLMs have the potential to facilitate surgical research by increasing writing efficiency, building predictive models, and aiding in large dataset analysis. From a clinical standpoint, LLMs can enhance efficiency by triaging patient concerns and generating automated responses. However, challenges exist, such as the need for improved LLM generalization performance, validating content, and addressing ethical concerns. In addition, patient privacy, potential bias in training, and legal responsibility are important considerations that require attention. Research and precautionary measures are necessary to ensure safe and unbiased use of LLMs in surgery. Conclusions and Relevance: Although limitations exist, LLMs hold promise for enhancing surgical efficiency while still prioritizing patient care. The authors recommend that the academic surgical community further investigate the potential applications of LLMs while being cautious about potential harms.