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.

Contrastive Transfer Learning for Prediction of Adverse Events in Hospitalized Patients.

OBJECTIVE: Deterioration index (DI) is a computer-generated score at a specific frequency that represents the overall condition of hospitalized patients using a variety of clinical, laboratory and physiologic data. In this paper, a contrastive transfer learning method is proposed and validated for early prediction of adverse events in hospitalized patients using DI scores. METHODS AND PROCEDURES: An unsupervised contrastive learning (CL) model with a classifier is proposed to predict adverse outcome using a single temporal variable (DI scores). The model is pretrained on an unsupervised fashion with large-scale time series data and fine-tuned with retrospective DI score data. RESULTS: The performance of this model is compared with supervised deep learning models for time series classification. Results show that unsupervised contrastive transfer learning with a classifier outperforms supervised deep learning solutions. Pretraining of the proposed CL model with large-scale time series data and fine-tuning that with DI scores can enhance prediction accuracy. CONCLUSION: A relationship exists between longitudinal DI scores of a patient and the corresponding outcome. DI scores and contrastive transfer learning can be used to predict and prevent adverse outcomes in hospitalized patients. CLINICAL IMPACT: This paper successfully developed an unsupervised contrastive transfer learning algorithm for prediction of adverse events in hospitalized patients. The proposed model can be deployed in hospitals as an early warning system for preemptive intervention in hospitalized patients, which can mitigate the likelihood of adverse outcomes.

Novel machine learning model to improve performance of an early warning system in hospitalized patients: a retrospective multisite cross-validation study.

Background: Threshold-based early warning systems (EWS) are used to predict adverse events (Aes). Machine learning (ML) algorithms that incorporate all EWS scores prior to an event may perform better in hospitalized patients. Methods: The deterioration index (DI) is a proprietary EWS. A threshold of DI >60 is used to predict a composite AE: all-cause mortality, cardiac arrest, transfer to intensive care, and evaluation by the rapid response team in practice. The DI scores were collected for adult patients (≥18 y-o) hospitalized on medical or surgical services during 8-23-2021 to 3-31-2022 from four different Mayo Clinic sites in the United States. A novel ML model was developed and trained on a retrospective cohort of hospital encounters. DI scores were represented in a high-dimensional space using random convolution kernels to facilitate training of a classifier and the area under the receiver operator characteristics curve (AUC) was calculated. Multiple time intervals prior to an AE were analyzed. A leave-one-out cross-validation protocol was used to evaluate performance across separate clinic sites. Findings: Three different classifiers were trained on 59,617 encounter-derived DI scores in high-dimensional feature space and the AUCs were compared to two threshold models. All three tested classifiers improved the AUC over the threshold approaches from 0.56 and 0.57 to 0.76, 0.85 and 0.94. Time interval analysis of the top performing classifier showed best accuracy in the hour before an event occurred (AUC 0.91), but prediction held up even in the 12 h before an AE (AUC 0.80 at minus 12 h, 0.81 at minus 9 h, 0.85 at minus 6 h, and 0.88 at minus 3 h before an AE). Multisite cross-validation using leave-one-out approach on data from four different clinical sites showed broad generalization performance of the top performing ML model with AUC of 0.91, 0.91, 0.95, and 0.91. Interpretation: A novel ML model that incorporates all the longitudinal DI scores prior to an AE in a hospitalized patient performs better at outcome prediction than the currently used threshold model. The use of clinical data, a generalized ML technique, and successful multisite cross-validation demonstrate the feasibility of our model in clinical implementation. Funding: No funding to report.

EDropout: Energy-Based Dropout and Pruning of Deep Neural Networks.

Dropout is a well-known regularization method by sampling a sub-network from a larger deep neural network and training different sub-networks on different subsets of the data. Inspired by the dropout concept, we propose EDropout as an energy-based framework for pruning neural networks in classification tasks. In this approach, a set of binary pruning state vectors (population) represents a set of corresponding sub-networks from an arbitrary original neural network. An energy loss function assigns a scalar energy loss value to each pruning state. The energy-based model (EBM) stochastically evolves the population to find states with lower energy loss. The best pruning state is then selected and applied to the original network. Similar to dropout, the kept weights are updated using backpropagation in a probabilistic model. The EBM again searches for better pruning states and the cycle continuous. This procedure is a switching between the energy model, which manages the pruning states, and the probabilistic model, which updates the kept weights, in each iteration. The population can dynamically converge to a pruning state. This can be interpreted as dropout leading to pruning the network. From an implementation perspective, unlike most of the pruning methods, EDropout can prune neural networks without manually modifying the network architecture code. We have evaluated the proposed method on different flavors of ResNets, AlexNet, l1 pruning, ThinNet, ChannelNet, and SqueezeNet on the Kuzushiji, Fashion, CIFAR-10, CIFAR-100, Flowers, and ImageNet data sets, and compared the pruning rate and classification performance of the models. The networks trained with EDropout on average achieved a pruning rate of more than 50% of the trainable parameters with approximately < 5% and < 1% drop of Top-1 and Top-5 classification accuracy, respectively.

A real-world demonstration of machine learning generalizability in the detection of intracranial hemorrhage on head computerized tomography.

Machine learning (ML) holds great promise in transforming healthcare. While published studies have shown the utility of ML models in interpreting medical imaging examinations, these are often evaluated under laboratory settings. The importance of real world evaluation is best illustrated by case studies that have documented successes and failures in the translation of these models into clinical environments. A key prerequisite for the clinical adoption of these technologies is demonstrating generalizable ML model performance under real world circumstances. The purpose of this study was to demonstrate that ML model generalizability is achievable in medical imaging with the detection of intracranial hemorrhage (ICH) on non-contrast computed tomography (CT) scans serving as the use case. An ML model was trained using 21,784 scans from the RSNA Intracranial Hemorrhage CT dataset while generalizability was evaluated using an external validation dataset obtained from our busy trauma and neurosurgical center. This real world external validation dataset consisted of every unenhanced head CT scan (n = 5965) performed in our emergency department in 2019 without exclusion. The model demonstrated an AUC of 98.4%, sensitivity of 98.8%, and specificity of 98.0%, on the test dataset. On external validation, the model demonstrated an AUC of 95.4%, sensitivity of 91.3%, and specificity of 94.1%. Evaluating the ML model using a real world external validation dataset that is temporally and geographically distinct from the training dataset indicates that ML generalizability is achievable in medical imaging applications.

Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT.

The Coronavirus disease 2019 (COVID-19) presents open questions in how we clinically diagnose and assess disease course. Recently, chest computed tomography (CT) has shown utility for COVID-19 diagnosis. In this study, we developed Deep COVID DeteCT (DCD), a deep learning convolutional neural network (CNN) that uses the entire chest CT volume to automatically predict COVID-19 (COVID+) from non-COVID-19 (COVID-) pneumonia and normal controls. We discuss training strategies and differences in performance across 13 international institutions and 8 countries. The inclusion of non-China sites in training significantly improved classification performance with area under the curve (AUCs) and accuracies above 0.8 on most test sites. Furthermore, using available follow-up scans, we investigate methods to track patient disease course and predict prognosis.

Synthesizing Chest X-Ray Pathology for Training Deep Convolutional Neural Networks.

Medical datasets are often highly imbalanced with over-representation of prevalent conditions and poor representation of rare medical conditions. Due to privacy concerns, it is challenging to aggregate large datasets between health care institutions. We propose synthesizing pathology in medical images as a means to overcome these challenges. We implement a deep convolutional generative adversarial network (DCGAN) to create synthesized chest X-rays based upon a modest sized labeled dataset. We used a combination of real and synthesized images to train deep convolutional neural networks (DCNNs) to detect pathology across five classes of chest X-rays. The comparative study of DCNNs trained with the combination of real and synthesized images showed that these networks can outperform similar networks trained solely with real images in pathology classification. This improved performance is largely attributable to the balancing of the dataset using DCGAN synthesized images, where classes that are lacking in example images are preferentially augmented.