Development and validation of machine learning models to identify high-risk surgical patients using automatically curated electronic health record data (Pythia): A retrospective, single-site study

Development and validation of machine learning models for early diagnosis and prognosis of lung adenocarcinoma using miRNA expression profiles

ObjectiveStudy aims to develop diagnostic and prognostic models for lung adenocarcinoma (LUAD) using Machine learning（ML）algorithms, aiming to enhance clinical decision-making accuracy.MethodsData from The Cancer Genome Atlas (TCGA) for LUAD patients were split into training (n = 196) and test sets (n = 133). Feature selection (Least Absolute Shrinkage and Selection Operator (LASSO), Random Forest (RF), and Support Vector Machine (SVM)) identified miRNAs distinguishing stage I LUAD. Six ML algorithms predicted pulmonary node classification. Model performance was evaluated using Receiver Operating Characteristic (ROC) curve, Precision-Recall (PR) curves, and Error Rates (CE). A prognostic model was constructed using Lasso Cox regression. Risk score plots were generated, and model performance was assessed using Kaplan-Meier (K-M) and time-dependent ROC curves. Functional enrichment analyses investigated miRNA function and mechanism.ResultsThe feature selection results identified five miRNA molecules as distinguishing characteristics between early-stage LUAD and adjacent non-cancerous tissues. A prognostic model using 13 miRNAs predicted poorer outcomes for patients with higher risk scores, supported by time-dependent ROC curves and a nomogram. Functional enrichment analysis identified cancer-related signaling pathways for the biomarkers.ConclusionML identified a diagnostic five-miRNA signature and a prognostic 13-miRNA model for LUAD, both robust and reliable.

The present and future of digital health, digital medicine, and digital therapeutics for allergic diseases

BACKGROUND

Digital health, digital medicine, and digital therapeutics integrate advanced computer technologies into healthcare, aiming to improve efficiency and patient outcomes. These technologies offer innovative solutions for the management of allergic diseases, which affect a significant proportion of the global population and are increasing in prevalence. BODY: This review examines the current progress and future potential of digital health in allergic disease management. It highlights key advancements, including telehealth, mobile health (mHealth), artificial intelligence, clinical decision support systems (CDSS), and digital biomarkers, with a focus on their relevance to allergic disease management. The role of digital tools in improving treatment adherence, enabling remote care, and integrating environmental and patient data into personalized care models is discussed. Challenges such as data privacy, interoperability, and equitable access are addressed, alongside potential strategies to overcome these barriers.

CONCLUSION

Digital therapy will play an important role in allergic diseases, and the further development of digital therapies will effectively promote the development of clinical research, digital biomarkers, hypoallergenic environments and digital twins. More research is needed to support the progress of digital therapy for allergic diseases.

LightGBM is an Effective Predictive Model for Postoperative Complications in Gastric Cancer: A Study Integrating Radiomics with Ensemble Learning

Postoperative complications of radical gastrectomy seriously affect postoperative recovery and require accurate risk prediction. Therefore, this study aimed to develop a prediction model specifically tailored to guide perioperative clinical decision-making for postoperative complications in patients with gastric cancer. A retrospective analysis was conducted on patients who underwent radical gastrectomy at the First Affiliated Hospital of Nanjing Medical University between April 2022 and June 2023. A total of 166 patients were enrolled. Patient demographic characteristics, laboratory examination results, and surgical pathological features were recorded. Preoperative abdominal CT scans were used to segment the visceral fat region of the patients through 3Dslicer, a 3D Convolutional Neural Network (3D-CNN) to extract image features and the LASSO regression model was employed for feature selection. Moreover, an ensemble learning strategy was adopted to train the features and predict postoperative complications of gastric cancer. The prediction performance of the LGBM (Light Gradient Boosting Machine), XGB (XGBoost), RF (Random Forest), and GBDT (Gradient Boosting Decision Tree) models was evaluated through fivefold cross-validation. This study successfully constructed a model for predicting early complications following radical gastrectomy based on the optimal algorithm, LGBM. The LGBM model yielded an AUC value of 0.9232 and an accuracy of 87.28% (95% CI, 75.61-98.95%), surpassing the performance of other models. Through ensemble learning and integration of perioperative clinical data and visceral fat radiomics, a predictive LGBM model was established. This model has the potential to facilitate individualized clinical decision-making and the early recovery of patients with gastric cancer post-surgery.

Maximizing Survival in Pediatric Congenital Cardiac Surgery Using Machine Learning, Explainability, and Simulation Techniques

Background: Pediatric and congenital heart surgery (PCHS) is highly risky. Complications associated with this surgical procedure are mainly caused by the severity of the disease or the unnecessary, late, or premature execution of the procedure, which can be fatal. In this context, prognostic models are crucial to reduce the uncertainty of the decision to perform surgery; however, these models alone are insufficient to maximize the probability of success or to reverse a future scenario of patient death. Method: A new approach is proposed to reverse the prognosis of death in PCHS through the use of (1) machine learning (ML) models to predict the outcome of surgery; (2) an explainability technique (ET) to determine the impact of main risk factors; and (3) a simulation method to design health scenarios that potentially reverse a negative prognosis. Results: Accuracy levels of 96% in the prediction of mortality and survival were achieved using a dataset of 565 patients undergoing PCHS and assessing 10 risk factors. Three case studies confirmed that the ET known as LIME provides explanations that are consistent with the observed results, and the simulation of one real case managed to reverse the initial prognosis of death to one of survival. Conclusions: An innovative method that integrates ML models, ETs, and Simulation has been developed to reverse the prognosis of death in patients undergoing PCHS. The experimental results validate the relevance of this approach in medical decision-making, demonstrating its ability to reverse negative prognoses and provide a solid basis for more informed and personalized medical decisions.

Challenges and opportunities in enhanced recovery after surgery programs: An overview

Enhanced Recovery After Surgery (ERAS) programs were developed as evidence-based, multi-disciplinary interventions in all the perioperative phases to minimise the surgical stress response, reduce complications, and enhance outcomes. The results across various surgical procedures have been positive, with a reduction in medical complications, a reduction in length of hospital stay, and a reduction in care costs without increased re-admission rates. However, implementation for many institutions has not been easy and suboptimal at best. The robust and pervasive adoption of these programs should be based on effective change management, dynamic and engaged clinical leadership, adherence to the principles of continuous quality improvement programs, and the adoption of evidence-based and data-driven changes in pathway development and implementation. Rapid cycle, randomised/quasi-randomised quality improvement projects must be the core foundation of an ERAS program. Finally, research methodologies should focus on controlling for adherence to the core elements of the pathways and testing for the effectiveness of an individual intervention in a randomised controlled trial.

Development and Validation of a Natural Language Processing Model to Identify Low-Risk Pulmonary Embolism in Real Time to Facilitate Safe Outpatient Management

STUDY OBJECTIVE

This study aimed to (1) develop and validate a natural language processing model to identify the presence of pulmonary embolism (PE) based on real-time radiology reports and (2) identify low-risk PE patients based on previously validated risk stratification scores using variables extracted from the electronic health record at the time of diagnosis. The combination of these approaches yielded an natural language processing-based clinical decision support tool that can identify patients presenting to the emergency department (ED) with low-risk PE as candidates for outpatient management.

METHODS

Data were curated from all patients who received a PE-protocol computed tomography pulmonary angiogram (PE-CTPA) imaging study in the ED of a 3-hospital academic health system between June 1, 2018 and December 31, 2020 (n=12,183). The "preliminary" radiology reports from these imaging studies made available to ED clinicians at the time of diagnosis were adjudicated as positive or negative for PE by the clinical team. The reports were then divided into development, internal validation, and temporal validation cohorts in order to train, test, and validate an natural language processing model that could identify the presence of PE based on unstructured text. For risk stratification, patient- and encounter-level data elements were curated from the electronic health record and used to compute a real-time simplified pulmonary embolism severity (sPESI) score at the time of diagnosis. Chart abstraction was performed on all low-risk PE patients admitted for inpatient management.

RESULTS

When applied to the internal validation and temporal validation cohorts, the natural language processing model identified the presence of PE from radiology reports with an area under the receiver operating characteristic curve of 0.99, sensitivity of 0.86 to 0.87, and specificity of 0.99. Across cohorts, 10.5% of PE-CTPA studies were positive for PE, of which 22.2% were classified as low-risk by the sPESI score. Of all low-risk PE patients, 74.3% were admitted for inpatient management.

CONCLUSION

This study demonstrates that a natural language processing-based model utilizing real-time radiology reports can accurately identify patients with PE. Further, this model, used in combination with a validated risk stratification score (sPESI), provides a clinical decision support tool that accurately identifies patients in the ED with low-risk PE as candidates for outpatient management.

Artificial intelligence and nonoperating room anesthesia

PURPOSE OF REVIEW

The integration of artificial intelligence (AI) in nonoperating room anesthesia (NORA) represents a timely and significant advancement. As the demand for NORA services expands, the application of AI is poised to improve patient selection, perioperative care, and anesthesia delivery. This review examines AI's growing impact on NORA and how it can optimize our clinical practice in the near future.

RECENT FINDINGS

AI has already improved various aspects of anesthesia, including preoperative assessment, intraoperative management, and postoperative care. Studies highlight AI's role in patient risk stratification, real-time decision support, and predictive modeling for patient outcomes. Notably, AI applications can be used to target patients at risk of complications, alert clinicians to the upcoming occurrence of an intraoperative adverse event such as hypotension or hypoxemia, or predict their tolerance of anesthesia after the procedure. Despite these advances, challenges persist, including ethical considerations, algorithmic bias, data security, and the need for transparent decision-making processes within AI systems.

SUMMARY

The findings underscore the substantial benefits of AI in NORA, which include improved safety, efficiency, and personalized care. AI's predictive capabilities in assessing hypoxemia risk and other perioperative events, have demonstrated potential to exceed human prognostic accuracy. The implications of these findings advocate for a careful yet progressive adoption of AI in clinical practice, encouraging the development of robust ethical guidelines, continual professional training, and comprehensive data management strategies. Furthermore, AI's role in anesthesia underscores the need for multidisciplinary research to address the limitations and fully leverage AI's capabilities for patient-centered anesthesia care.

Development and preliminary assessment of a machine learning model to predict myocardial infarction and cardiac arrest after major operations

INTRODUCTION

Accurate prediction of complications often informs shared decision-making. Derived over 10 years ago to enhance prediction of intra/post-operative myocardial infarction and cardiac arrest (MI/CA), the Gupta score has been criticized for unreliable calibration and inclusion of a wide spectrum of unrelated operations. In the present study, we developed a novel machine learning (ML) model to estimate perioperative risk of MI/CA and compared it to the Gupta score.

METHODS

Patients undergoing major operations were identified from the 2016-2020 ACS-NSQIP. The Gupta score was calculated for each patient, and a novel ML model was developed to predict MI/CA using ACS NSQIP-provided data fields as covariates. Discrimination (C-statistic) and calibration (Brier score) of the ML model were compared to the existing Gupta score within the entire cohort and across operative subgroups.

RESULTS

Of 2,473,487 patients included for analysis, 25,177 (1.0%) experienced MI/CA (55.2% MI, 39.1% CA, 5.6% MI and CA). The ML model, which was fit using a randomly selected training cohort, exhibited higher discrimination within the testing dataset compared to the Gupta score (C-statistic 0.84 vs 0.80, p < 0.001). Furthermore, the ML model had significantly better calibration in the entire cohort (Brier score 0.0097 vs 0.0100). Model performance was markedly improved among patients undergoing thoracic, aortic, peripheral vascular and foregut surgery.

CONCLUSIONS

The present ML model outperformed the Gupta score in the prognostication of MI/CA across a heterogenous range of operations. Given the growing integration of ML into healthcare, such models may be readily incorporated into clinical practice and guide benchmarking efforts.

Testing Machine Learning Models to Predict Postoperative Ileus after Colorectal Surgery

Background: Postoperative ileus (POI) is a common complication after colorectal surgery, leading to increased hospital stay and costs. This study aimed to explore patient comorbidities that contribute to the development of POI in the colorectal surgical population and compare machine learning (ML) model accuracy to existing risk instruments. Study Design: In a retrospective study, data were collected on 316 adult patients who underwent colorectal surgery from January 2020 to December 2021. The study excluded patients undergoing multi-visceral resections, re-operations, or combined primary and metastatic resections. Patients lacking follow-up within 90 days after surgery were also excluded. Eight different ML models were trained and cross-validated using 29 patient comorbidities and four comorbidity risk indices (ASA Status, NSQIP, CCI, and ECI). Results: The study found that 6.33% of patients experienced POI. Age, BMI, gender, kidney disease, anemia, arrhythmia, rheumatoid arthritis, and NSQIP score were identified as significant predictors of POI. The ML models with the greatest accuracy were AdaBoost tuned with grid search (94.2%) and XG Boost tuned with grid search (85.2%). Conclusions: This study suggests that ML models can predict the risk of POI with high accuracy and may offer a new frontier in early detection and intervention for postoperative outcome optimization. ML models can greatly improve the prediction and prevention of POI in colorectal surgery patients, which can lead to improved patient outcomes and reduced healthcare costs. Further research is required to validate and assess the replicability of these results.

Improving Clinical Documentation with Artificial Intelligence: A Systematic Review

Clinicians dedicate significant time to clinical documentation, incurring opportunity cost. Artificial Intelligence (AI) tools promise to improve documentation quality and efficiency. This systematic review overviews peer-reviewed AI tools to understand how AI may reduce opportunity cost. PubMed, Embase, Scopus, and Web of Science databases were queried for original, English language research studies published during or before July 2024 that report a new development, application, and validation of an AI tool for improving clinical documentation. 129 studies were extracted from 673 candidate studies. AI tools improve documentation by structuring data, annotating notes, evaluating quality, identifying trends, and detecting errors. Other AI-enabled tools assist clinicians in real-time during office visits, but moderate accuracy precludes broad implementation. While a highly accurate end-to-end AI documentation assistant is not currently reported in peer-reviewed literature, existing techniques such as structuring data offer targeted improvements to clinical documentation workflows.

Improving Clinical Documentation with Artificial Intelligence: A Systematic Review

Clinicians dedicate significant time to clinical documentation, incurring opportunity cost. Artificial Intelligence (AI) tools promise to improve documentation quality and efficiency. This systematic review overviews peer-reviewed AI tools to understand how AI may reduce opportunity cost. PubMed, Embase, Scopus, and Web of Science databases were queried for original, English language research studies published during or before July 2024 that report a new development, application, and validation of an AI tool for improving clinical documentation. 129 studies were extracted from 673 candidate studies. AI tools improve documentation by structuring data, annotating notes, evaluating quality, identifying trends, and detecting errors. Other AI-enabled tools assist clinicians in real-time during office visits, but moderate accuracy precludes broad implementation. While a highly accurate end-to-end AI documentation assistant is not currently reported in peer-reviewed literature, existing techniques such as structuring data offer targeted improvements to clinical documentation workflows.

Predicting Colonic Neoplasia Surgical Complications: A Machine Learning Approach

BACKGROUND

A range of statistical approaches have been used to help predict outcomes associated with colectomy. The multifactorial nature of complications suggests that machine learning algorithms may be more accurate in determining postoperative outcomes by detecting nonlinear associations, which are not readily measured by traditional statistics.

OBJECTIVE

The aim of this study was to investigate the utility of machine learning algorithms to predict complications in patients undergoing colectomy for colonic neoplasia.

DESIGN

Retrospective analysis using decision tree, random forest, and artificial neural network classifiers to predict postoperative outcomes.

SETTINGS

National Inpatient Sample database (2003-2017).

PATIENTS

Adult patients who underwent elective colectomy with anastomosis for neoplasia.

MAIN OUTCOME MEASURES

Performance was quantified using sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve to predict the incidence of anastomotic leak, prolonged length of stay, and inpatient mortality.

RESULTS

A total of 14,935 patients (4731 laparoscopic, 10,204 open) were included. They had an average age of 67 ± 12.2 years, and 53% of patients were women. The 3 machine learning models successfully identified patients who developed the measured complications. Although differences between model performances were largely insignificant, the neural network scored highest for most outcomes: predicting anastomotic leak, area under the receiver operating characteristic curve 0.88/0.93 (open/laparoscopic, 95% CI, 0.73-0.92/0.80-0.96); prolonged length of stay, area under the receiver operating characteristic curve 0.84/0.88 (open/laparoscopic, 95% CI, 0.82-0.85/0.85-0.91); and inpatient mortality, area under the receiver operating characteristic curve 0.90/0.92 (open/laparoscopic, 95% CI, 0.85-0.96/0.86-0.98).

LIMITATIONS

The patients from the National Inpatient Sample database may not be an accurate sample of the population of all patients undergoing colectomy for colonic neoplasia and does not account for specific institutional and patient factors.

CONCLUSIONS

Machine learning predicted postoperative complications in patients with colonic neoplasia undergoing colectomy with good performance. Although validation using external data and optimization of data quality will be required, these machine learning tools show great promise in assisting surgeons with risk-stratification of perioperative care to improve postoperative outcomes. See Video Abstract .

PREDICCIN DE LAS COMPLICACIONES QUIRRGICAS DE LA NEOPLASIA DE COLON UN ENFOQUE DE MODELO DE APRENDIZAJE AUTOMTICO

ANTECEDENTES:Se han utilizado una variedad de enfoques estadísticos para ayudar a predecir los resultados asociados con la colectomía. La naturaleza multifactorial de las complicaciones sugiere que los algoritmos de aprendizaje automático pueden ser más precisos en determinar los resultados posoperatorios al detectar asociaciones no lineales, que generalmente no se miden en las estadísticas tradicionales.OBJETIVO:El objetivo de este estudio fue investigar la utilidad de los algoritmos de aprendizaje automático para predecir complicaciones en pacientes sometidos a colectomía por neoplasia de colon.DISEÑO:Análisis retrospectivo utilizando clasificadores de árboles de decisión, bosques aleatorios y redes neuronales artificiales para predecir los resultados posoperatorios.AJUSTE:Base de datos de la Muestra Nacional de Pacientes Hospitalizados (2003-2017).PACIENTES:Pacientes adultos sometidos a colectomía electiva con anastomosis por neoplasia.INTERVENCIONES:N/A.PRINCIPALES MEDIDAS DE RESULTADO:El rendimiento se cuantificó utilizando la sensibilidad, especificidad, precisión y la característica operativa del receptor del área bajo la curva para predecir la incidencia de fuga anastomótica, duración prolongada de la estancia hospitalaria y mortalidad de los pacientes hospitalizados.RESULTADOS:Se incluyeron un total de 14.935 pacientes (4.731 laparoscópicos, 10.204 abiertos). Presentaron una edad promedio de 67 ± 12,2 años y el 53% eran mujeres. Los tres modelos de aprendizaje automático identificaron con éxito a los pacientes que desarrollaron las complicaciones medidas. Aunque las diferencias entre el rendimiento del modelo fueron en gran medida insignificantes, la red neuronal obtuvo la puntuación más alta para la mayoría de los resultados: predicción de fuga anastomótica, característica operativa del receptor del área bajo la curva 0,88/0,93 (abierta/laparoscópica, IC del 95%: 0,73-0,92/0,80-0,96); duración prolongada de la estancia hospitalaria, característica operativa del receptor del área bajo la curva 0,84/0,88 (abierta/laparoscópica, IC del 95%: 0,82-0,85/0,85-0,91); y mortalidad de pacientes hospitalizados, característica operativa del receptor del área bajo la curva 0,90/0,92 (abierto/laparoscópico, IC del 95%: 0,85-0,96/0,86-0,98).LIMITACIONES:Los pacientes de la base de datos de la Muestra Nacional de Pacientes Hospitalizados pueden no ser una muestra precisa de la población de todos los pacientes sometidos a colectomía por neoplasia de colon y no tienen en cuenta factores institucionales y específicos del paciente.CONCLUSIONES:El aprendizaje automático predijo con buen rendimiento las complicaciones postoperatorias en pacientes con neoplasia de colon sometidos a colectomía. Aunque será necesaria la validación mediante datos externos y la optimización de la calidad de los datos, estas herramientas de aprendizaje automático son muy prometedoras para ayudar a los cirujanos con la estratificación de riesgos de la atención perioperatoria para mejorar los resultados posoperatorios. (Traducción-Dr. Fidel Ruiz Healy ).

New Horizons of Artificial Intelligence in Medicine and Surgery

Background: Ideas about Artificial intelligence appeared about half a century ago, but only now is it becoming an essential element of everyday life. The data provided are becoming a bigger pool and we need artificial intelligence that will help us with its superhuman powers. Its interaction with medicine is improving more and more, with medicine being a domain that continues to be perfected. Materials and Methods: The most important databases were used to perform this detailed search that addresses artificial intelligence in the medical and surgical fields. Discussion: Machine learning, deep learning, neural networks and computer vision are some of the mechanisms that are becoming a trend in healthcare worldwide. Developed countries such as Japan, France and Germany have already implemented artificial intelligence in their medical systems. The help it gives is in medical diagnosis, patient monitoring, personalized therapy and workflow optimization. Artificial intelligence will help surgeons to perfect their skills, to standardize techniques and to choose the best surgical techniques. Conclusions: The goal is to predict complications, reduce diagnostic times, diagnose complex pathologies, guide surgeons intraoperatively and reduce medical errors. We are at the beginning of this, and the potential is enormous, but we must not forget the impediments that may appear and slow down its implementation.

Pushing the Limits of Minimally Invasive Spine Surgery-From Preoperative to Intraoperative to Postoperative Management

The introduction of minimally invasive surgery ushered in a new era of spine surgery by minimizing the undue iatrogenic injury, recovery time, and blood loss, among other complications, of traditional open procedures. Over time, technological advancements have further refined the care of the operative minimally invasive spine patient. Moreover, pre-, and postoperative care have also undergone significant change by way of artificial intelligence risk stratification, advanced imaging for surgical planning and patient selection, postoperative recovery pathways, and digital health solutions. Despite these advancements, challenges persist necessitating ongoing research and collaboration to further optimize patient care in minimally invasive spine surgery.

ChatGPT provides inconsistent risk-stratification of patients with atraumatic chest pain

BACKGROUND

ChatGPT-4 is a large language model with promising healthcare applications. However, its ability to analyze complex clinical data and provide consistent results is poorly known. Compared to validated tools, this study evaluated ChatGPT-4's risk stratification of simulated patients with acute nontraumatic chest pain.

METHODS

Three datasets of simulated case studies were created: one based on the TIMI score variables, another on HEART score variables, and a third comprising 44 randomized variables related to non-traumatic chest pain presentations. ChatGPT-4 independently scored each dataset five times. Its risk scores were compared to calculated TIMI and HEART scores. A model trained on 44 clinical variables was evaluated for consistency.

RESULTS

ChatGPT-4 showed a high correlation with TIMI and HEART scores (r = 0.898 and 0.928, respectively), but the distribution of individual risk assessments was broad. ChatGPT-4 gave a different risk 45-48% of the time for a fixed TIMI or HEART score. On the 44-variable model, a majority of the five ChatGPT-4 models agreed on a diagnosis category only 56% of the time, and risk scores were poorly correlated (r = 0.605).

CONCLUSION

While ChatGPT-4 correlates closely with established risk stratification tools regarding mean scores, its inconsistency when presented with identical patient data on separate occasions raises concerns about its reliability. The findings suggest that while large language models like ChatGPT-4 hold promise for healthcare applications, further refinement and customization are necessary, particularly in the clinical risk assessment of atraumatic chest pain patients.

A Novel Digital Health Platform With Health Coaches to Optimize Surgical Patients: Feasibility Study at a Large Academic Health System

BACKGROUND

Pip is a novel digital health platform (DHP) that combines human health coaches (HCs) and technology with patient-facing content. This combination has not been studied in perioperative surgical optimization.

OBJECTIVE

This study's aim was to test the feasibility of the Pip platform for deploying perioperative, digital, patient-facing optimization guidelines to elective surgical patients, assisted by an HC, at predefined intervals in the perioperative journey.

METHODS

We conducted an institutional review board-approved, descriptive, prospective feasibility study of patients scheduled for elective surgery and invited to enroll in Pip from 2.5 to 4 weeks preoperatively through 4 weeks postoperatively at an academic medical center between November 22, 2022, and March 27, 2023. Descriptive primary end points were patient-reported outcomes, including patient satisfaction and engagement, and Pip HC evaluations. Secondary end points included mean or median length of stay (LOS), readmission at 7 and 30 days, and emergency department use within 30 days. Secondary end points were compared between patients who received Pip versus patients who did not receive Pip using stabilized inverse probability of treatment weighting.

RESULTS

A total of 283 patients were invited, of whom 172 (60.8%) enrolled in Pip. Of these, 80.2% (138/172) patients had ≥1 HC session and proceeded to surgery, and 70.3% (97/138) of the enrolled patients engaged with Pip postoperatively. The mean engagement began 27 days before surgery. Pip demonstrated an 82% weekly engagement rate with HCs. Patients attended an average of 6.7 HC sessions. Of those patients that completed surveys (95/138, 68.8%), high satisfaction scores were recorded (mean 4.8/5; n=95). Patients strongly agreed that HCs helped them throughout the perioperative process (mean 4.97/5; n=33). The average net promoter score was 9.7 out of 10. A total of 268 patients in the non-Pip group and 128 patients in the Pip group had appropriate overlapping distributions of stabilized inverse probability of treatment weighting for the analytic sample. The Pip cohort was associated with LOS reduction when compared to the non-Pip cohort (mean 2.4 vs 3.1 days; median 1.9, IQR 1.0-3.1 vs median 3.0, IQR 1.1-3.9 days; mean ratio 0.76; 95% CI 0.62-0.93; P=.009). The Pip cohort experienced a 49% lower risk of 7-day readmission (relative risk [RR] 0.51, 95% CI 0.11-2.31; P=.38) and a 17% lower risk of 30-day readmission (RR 0.83, 95% CI 0.30-2.31; P=.73), though these did not reach statistical significance. Both cohorts had similar 30-day emergency department returns (RR 1.06, 95% CI 0.56-2.01, P=.85).

CONCLUSIONS

Pip is a novel mobile DHP combining human HCs and perioperative optimization content that is feasible to engage patients in their perioperative journey and is associated with reduced hospital LOS. Further studies assessing the impact on clinical and patient-reported outcomes from the use of Pip or similar DHPs HC combinations during the perioperative journey are required.

Preoperative Prediction of Postoperative Infections Using Machine Learning and Electronic Health Record Data

OBJECTIVE

To estimate preoperative risk of postoperative infections using structured electronic health record (EHR) data.

BACKGROUND

Surveillance and reporting of postoperative infections is primarily done through costly, labor-intensive manual chart reviews on a small sample of patients. Automated methods using statistical models applied to postoperative EHR data have shown promise to augment manual review as they can cover all operations in a timely manner. However, there are no specific models for risk-adjusting infectious complication rates using EHR data.

METHODS

Preoperative EHR data from 30,639 patients (2013-2019) were linked to the American College of Surgeons National Surgical Quality Improvement Program preoperative data and postoperative infection outcomes data from 5 hospitals in the University of Colorado Health System. EHR data included diagnoses, procedures, operative variables, patient characteristics, and medications. Lasso and the knockoff filter were used to perform controlled variable selection. Outcomes included surgical site infection, urinary tract infection, sepsis/septic shock, and pneumonia up to 30 days postoperatively.

RESULTS

Among >15,000 candidate predictors, 7 were chosen for the surgical site infection model and 6 for each of the urinary tract infection, sepsis, and pneumonia models. Important variables included preoperative presence of the specific outcome, wound classification, comorbidities, and American Society of Anesthesiologists physical status classification. The area under the receiver operating characteristic curve for each model ranged from 0.73 to 0.89.

CONCLUSIONS

Parsimonious preoperative models for predicting postoperative infection risk using EHR data were developed and showed comparable performance to existing American College of Surgeons National Surgical Quality Improvement Program risk models that use manual chart review. These models can be used to estimate risk-adjusted postoperative infection rates applied to large volumes of EHR data in a timely manner.

Innovations in Spine Surgery: A Narrative Review of Current Integrative Technologies

Neurosurgical technologies have become increasingly more adaptive, featuring real-time and patient-specific guidance in preoperative, intraoperative, and postoperative settings. This review offers insight into how these integrative innovations compare with conventional approaches in spine surgery, focusing on machine learning (ML), artificial intelligence, augmented reality and virtual reality, and spinal navigation systems. Data on technology applications, diagnostic and procedural accuracy, intraoperative times, radiation exposures, postoperative outcomes, and costs were extracted and compared with conventional methods to assess their advantages and limitations. Preoperatively, augmented reality and virtual reality have applications in surgical training and planning that are more immersive, case specific, and risk-free and have been shown to enhance accuracy and reduce complications. ML algorithms have demonstrated high accuracy in predicting surgical candidacy (up to 92.1%) and tailoring personalized treatments based on patient-specific variables. Intraoperatively, advantages include more accurate pedicle screw insertion (96%-99% with ML), enhanced visualization, reduced radiation exposure (49 μSv with O-arm navigation vs. 556 μSv with fluoroscopy), increased efficiency, and potential for fewer intraoperative complications compared with conventional approaches. Postoperatively, certain ML and artificial intelligence models have outperformed conventional methods in predicting all postoperative complications of >6000 patients as well as predicting variables contributing to in-hospital and 90-day mortality. However, applying these technologies comes with limitations, such as longer operative times (up to 35.6% longer) with navigation, dependency on datasets, costs, accessibility, steep learning curve, and inherent software malfunctions. As these technologies advance, continuing to assess their efficacy and limitations will be crucial to their successful integration within spine surgery.

Development and validation of a point-of-care clinical risk score to predict surgical site complication-associated readmissions following open spine surgery

Background

Surgical site complications (SSCs) contribute to increased healthcare costs. Predictive analytics can aid in identifying high-risk patients and implementing optimization strategies. This study aimed to develop and validate a risk-assessment score for SSC-associated readmissions (SSC-ARs) in patients undergoing open spine surgery.

Methods

The Premier Healthcare Database (PHD) of adult patients (n=157,664; 3,182 SSC-ARs) between January 2019 and September 2020 was used for retrospective data analysis to create an SSC risk score using mixed effects logistic regression modeling. Full and reduced models were developed using patient-, facility-, or procedure-related predictors. The full model used 37 predictors and the reduced used 19.

Results

The reduced model exhibited fair discriminatory capability (C-statistic =74.12%) and demonstrated better model fit [Pearson chi-square/degrees of freedom (DF) =0.93] compared to the full model (C-statistic =74.56%; Pearson chi-square/DF =0.92). The risk scoring system, based on the reduced model, comprised the following factors: female (1 point), blood disorder [2], congestive heart failure [2], dementia [3], chronic pulmonary disease [2], rheumatic disease [3], hypertension [2], obesity [2], severe comorbidity [2], nicotine dependence [1], liver disease [2], paraplegia and hemiplegia [3], peripheral vascular disease [2], renal disease [2], cancer [1], diabetes [2], revision surgery [2], operative hours ≥5 [4], emergency/urgent surgery [2]. A final risk score (sum of the points for each surgery; range, 0-40) was validated using a 1,000-surgery random hold-out sample (C-statistic =85.16%).

Conclusions

The resulting SSC-AR risk score, composed of readily obtainable clinical information, could serve as a robust predictive tool for unplanned readmissions related to wound complications in the preoperative setting of open spine surgery.

Development and validation of 'Patient Optimizer' (POP) algorithms for predicting surgical risk with machine learning

BACKGROUND

Pre-operative risk assessment can help clinicians prepare patients for surgery, reducing the risk of perioperative complications, length of hospital stay, readmission and mortality. Further, it can facilitate collaborative decision-making and operational planning.

OBJECTIVE

To develop effective pre-operative risk assessment algorithms (referred to as Patient Optimizer or POP) using Machine Learning (ML) that predict the development of post-operative complications and provide pilot data to inform the design of a larger prospective study.

METHODS

After institutional ethics approval, we developed a base model that encapsulates the standard manual approach of combining patient-risk and procedure-risk. In an automated process, additional variables were included and tested with 10-fold cross-validation, and the best performing features were selected. The models were evaluated and confidence intervals calculated using bootstrapping. Clinical expertise was used to restrict the cardinality of categorical variables (e.g. pathology results) by including the most clinically relevant values. The models were created with logistic regression (LR) and extreme gradient-boosted trees using XGBoost (Chen and Guestrin, 2016). We evaluated performance using the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). Data was obtained from a metropolitan university teaching hospital from January 2015 to July 2020. Data collection was restricted to adult patients undergoing elective surgery.

RESULTS

A total of 11,475 adult admissions were included. The performance of XGBoost and LR was very similar across endpoints and metrics. For predicting the risk of any post-operative complication, kidney failure and length-of-stay (LOS), POP with XGBoost achieved an AUROC (95%CI) of 0.755 (0.744, 0.767), 0.869 (0.846, 0.891) and 0.841 (0.833, 0.847) respectively and AUPRC of 0.651 (0.632, 0.669), 0.336 (0.282, 0.390) and 0.741 (0.729, 0.753) respectively. For 30-day readmission and in-patient mortality, POP with XGBoost achieved an AUROC (95%CI) of 0.610 (0.587, 0.635) and 0.866 (0.777, 0.943) respectively and AUPRC of 0.116 (0.104, 0.132) and 0.031 (0.015, 0.072) respectively.

CONCLUSION

The POP algorithms effectively predicted any post-operative complication, kidney failure and LOS in the sample population. A larger study is justified to improve the algorithm to better predict complications and length of hospital stay. A larger dataset may also improve the prediction of additional specific complications, readmission and mortality.

Artificial Intelligence in Urology: Current Status and Future Perspectives

Surgical fields, especially urology, have shifted increasingly toward the use of artificial intelligence (AI). Advancements in AI have created massive improvements in diagnostics, outcome predictions, and robotic surgery. For robotic surgery to progress from assisting surgeons to eventually reaching autonomous procedures, there must be advancements in machine learning, natural language processing, and computer vision. Moreover, barriers such as data availability, interpretability of autonomous decision-making, Internet connection and security, and ethical concerns must be overcome.

A framework for understanding label leakage in machine learning for health care

INTRODUCTION

The pitfalls of label leakage, contamination of model input features with outcome information, are well established. Unfortunately, avoiding label leakage in clinical prediction models requires more nuance than the common advice of applying "no time machine rule."

FRAMEWORK

We provide a framework for contemplating whether and when model features pose leakage concerns by considering the cadence, perspective, and applicability of predictions. To ground these concepts, we use real-world clinical models to highlight examples of appropriate and inappropriate label leakage in practice.

RECOMMENDATIONS

Finally, we provide recommendations to support clinical and technical stakeholders as they evaluate the leakage tradeoffs associated with model design, development, and implementation decisions. By providing common language and dimensions to consider when designing models, we hope the clinical prediction community will be better prepared to develop statistically valid and clinically useful machine learning models.

Revolutionizing hysteroscopy outcomes: AI-powered uterine myoma diagnosis algorithm shortens operation time and reduces blood loss

Background

The application of artificial intelligence (AI) powered algorithm in clinical decision-making is globally popular among clinicians and medical scientists. In this research endeavor, we harnessed the capabilities of AI to enhance the precision of hysteroscopic myomectomy procedures.

Methods

Our multidisciplinary team developed a comprehensive suite of algorithms, rooted in deep learning technology, addressing myomas segmentation tasks. We assembled a cohort comprising 56 patients diagnosed with submucosal myomas, each of whom underwent magnetic resonance imaging (MRI) examinations. Subsequently, half of the participants were randomly designated to undergo AI-augmented procedures. Our AI system exhibited remarkable proficiency in elucidating the precise spatial localization of submucosal myomas.

Results

The results of our study showcased a statistically significant reduction in both operative duration (41.32 ± 17.83 minutes vs. 32.11 ± 11.86 minutes, p=0.03) and intraoperative blood loss (10.00 (6.25-15.00) ml vs. 10.00 (5.00-15.00) ml, p=0.04) in procedures assisted by AI.

Conclusion

This work stands as a pioneering achievement, marking the inaugural deployment of an AI-powered diagnostic model in the domain of hysteroscopic surgery. Consequently, our findings substantiate the potential of AI-driven interventions within the field of gynecological surgery.

The Not-So-Distant Future or Just Hype? Utilizing Machine Learning to Predict 30-Day Post-Operative Complications in Laparoscopic Colectomy Patients

BACKGROUND

Complex machine learning (ML) models have revolutionized predictions in clinical care. However, for laparoscopic colectomy (LC), prediction of morbidity by ML has not been adequately analyzed nor compared against traditional logistic regression (LR) models.

METHODS

All LC patients, between 2017 and 2019, in the National Surgical Quality Improvement Program (NSQIP) were identified. A composite outcome of 17 variables defined any post-operative morbidity. Seven of the most common complications were additionally analyzed. Three ML models (Random Forests, XGBoost, and L1-L2-RFE) were compared with LR.

RESULTS

Random Forests, XGBoost, and L1-L2-RFE predicted 30-day post-operative morbidity with average area under the curve (AUC): .709, .712, and .712, respectively. LR predicted morbidity with AUC = .712. Septic shock was predicted with AUC ≤ .9, by ML and LR.

CONCLUSION

There was negligible difference in the predictive ability of ML and LR in post-LC morbidity prediction. Possibly, the computational power of ML cannot be realized in limited datasets.

Prediction of complications associated with general surgery using a Bayesian network

BACKGROUND

Numerous attempts have been made to identify risk factors for surgery complications, but few studies have identified accurate methods of predicting complex outcomes involving multiple complications.

METHODS

We performed a prospective cohort study of general surgical inpatients who attended 4 regionally representative hospitals in China from January to June 2015 and January to June 2016. The risk factors were identified using logistic regression. A Bayesian network model, consisting of directed arcs and nodes, was used to analyze the relationships between risk factors and complications. Probability ratios for complications for a given node state relative to the baseline probability were calculated to quantify the potential effects of risk factors on complications or of complications on other complications.

RESULTS

We recruited 19,223 participants and identified 21 nodes, representing 9 risk factors and 12 complications, and 55 direct relationships between these. Respiratory failure was at the center of the network, directly affected by 5 risk factors, and directly affected 7 complications. Cardiopulmonary resuscitation and sepsis or septic shock also directly affected death. The area under the receiver operating characteristic curve for the ability of the network to predict complications was >0.7. Notably, the probability of other severe complications or death significantly increased when a severe complication occurred. Most importantly, there was a 141-fold higher risk of death when cardiopulmonary resuscitation was required.

CONCLUSION

We have created a Bayesian network that displays how risk factors affect complications and their interrelationships and permits the accurate prediction of complications and the creation of appropriate preventive guidelines.

Temporal Generalizability of Machine Learning Models for Predicting Postoperative Delirium Using Electronic Health Record Data: Model Development and Validation Study

BACKGROUND

Although machine learning models demonstrate significant potential in predicting postoperative delirium, the advantages of their implementation in real-world settings remain unclear and require a comparison with conventional models in practical applications.

OBJECTIVE

The objective of this study was to validate the temporal generalizability of decision tree ensemble and sparse linear regression models for predicting delirium after surgery compared with that of the traditional logistic regression model.

METHODS

The health record data of patients hospitalized at an advanced emergency and critical care medical center in Kumamoto, Japan, were collected electronically. We developed a decision tree ensemble model using extreme gradient boosting (XGBoost) and a sparse linear regression model using least absolute shrinkage and selection operator (LASSO) regression. To evaluate the predictive performance of the model, we used the area under the receiver operating characteristic curve (AUROC) and the Matthews correlation coefficient (MCC) to measure discrimination and the slope and intercept of the regression between predicted and observed probabilities to measure calibration. The Brier score was evaluated as an overall performance metric. We included 11,863 consecutive patients who underwent surgery with general anesthesia between December 2017 and February 2022. The patients were divided into a derivation cohort before the COVID-19 pandemic and a validation cohort during the COVID-19 pandemic. Postoperative delirium was diagnosed according to the confusion assessment method.

RESULTS

A total of 6497 patients (68.5, SD 14.4 years, women n=2627, 40.4%) were included in the derivation cohort, and 5366 patients (67.8, SD 14.6 years, women n=2105, 39.2%) were included in the validation cohort. Regarding discrimination, the XGBoost model (AUROC 0.87-0.90 and MCC 0.34-0.44) did not significantly outperform the LASSO model (AUROC 0.86-0.89 and MCC 0.34-0.41). The logistic regression model (AUROC 0.84-0.88, MCC 0.33-0.40, slope 1.01-1.19, intercept -0.16 to 0.06, and Brier score 0.06-0.07), with 8 predictors (age, intensive care unit, neurosurgery, emergency admission, anesthesia time, BMI, blood loss during surgery, and use of an ambulance) achieved good predictive performance.

CONCLUSIONS

The XGBoost model did not significantly outperform the LASSO model in predicting postoperative delirium. Furthermore, a parsimonious logistic model with a few important predictors achieved comparable performance to machine learning models in predicting postoperative delirium.

Individualized treatment decision model for inoperable elderly esophageal squamous cell carcinoma based on multi-modal data fusion

BACKGROUND

This research aimed to develop a model for individualized treatment decision-making in inoperable elderly patients with esophageal squamous cell carcinoma (ESCC) using machine learning methods and multi-modal data.

METHODS

A total of 189 inoperable elderly ESCC patients aged 65 or older who underwent concurrent chemoradiotherapy (CCRT) or radiotherapy (RT) were included. Multi-task learning models were created using machine learning techniques to analyze multi-modal data, including pre-treatment CT images, clinical information, and blood test results. Nomograms were constructed to predict the objective response rate (ORR) and progression-free survival (PFS) for different treatment strategies. Optimal treatment plans were recommended based on the nomograms. Patients were stratified into high-risk and low-risk groups using the nomograms, and survival analysis was performed using Kaplan-Meier curves.

RESULTS

The identified risk factors influencing ORR were histologic grade (HG), T stage and three radiomic features including original shape elongation, first-order skewness and original shape flatness, while risk factors influencing PFS included BMI, HG and three radiomic features including high gray-level run emphasis, first-order minimum and first-order skewness. These risk factors were incorporated into the nomograms as independent predictive factors. PFS was substantially different between the low-risk group (total score ≤ 110) and the high-risk group (total score > 110) according to Kaplan-Meier curves (P < 0.05).

CONCLUSIONS

The developed predictive models for ORR and PFS in inoperable elderly ESCC patients provide valuable insights for predicting treatment efficacy and prognosis. The nomograms enable personalized treatment decision-making and can guide optimal treatment plans for inoperable elderly ESCC patients.

Artificial intelligence in vascular surgical decision making

Despite advances in prevention, detection, and treatment, cardiovascular disease is a leading cause of mortality and represents a major health problem worldwide. Artificial intelligence and machine learning have brought new insights to the management of vascular diseases by allowing analysis of huge and complex datasets and by offering new techniques to develop advanced imaging analysis. Artificial intelligence-based applications have the potential to improve prognostic evaluation and evidence-based decision making and contribute to vascular therapeutic decision making. In this scoping review, we provide an overview on how artificial intelligence could help in vascular surgical clinical decision making, highlighting potential benefits, current limitations, and future challenges.

A Comprehensive Analysis and Review of Artificial Intelligence in Anaesthesia

In the field of anaesthesia, artificial intelligence (AI) has become a game-changing technology. Applications of AI include keeping records, monitoring patients, calculating and administering drugs, and carrying out mechanical procedures. This article explores the current uses, challenges, and prospective applications of AI in anaesthesia practices. This review discusses AI-supported systems like anaesthesia information management systems (AIMS), mechanical robots for carrying out procedures, and pharmacological models for drug delivery. AIMS has helped in automated record-keeping, predicting bad events, and monitoring the vital signs of the patient. Their application has a vital role in improving the efficacy of anaesthesia management and patient safety. The application of AI in anaesthesia comes with its own unique difficulties. Noteworthy obstacles include issues with data quantity and quality, technical limitations, and moral and legal dilemmas. The key to overcoming these barriers is to set guidelines for the ethical use of AI in healthcare, improve the reliability and comprehension of AI systems, and certify the health data precision and security. AI has very bright potential. Exciting future directions include developments in AI and machine learning thus development of new applications, and the possible enhancement in training and education. Potential research areas include the application of AI to chronic disease management, pain management, and the reinforcement of anaesthesiologists' education. AI could be used to design authentic lifelike training simulations and individualized student feedback systems, hence transforming anaesthesia education and training methodology. For this review, we conducted a PubMed, Google Scholar, and Cochrane Database search in 2022-2023 and retrieved articles on AI and its uses in anaesthesia. Recommendations for future research and development include strengthening the safety and reliability of health data, building a better understanding of AI systems, and looking into new areas of use. The power of AI can be used to innovate anaesthesia practices by concentrating on these areas.

Machine Learning in Spinal Cord Stimulation for Chronic Pain

Spinal cord stimulation (SCS) is an effective treatment for chronic neuropathic pain. The success of SCS is dependent on candidate selection, response to trialing, and programming optimization. Owing to the subjective nature of these variables, machine learning (ML) offers a powerful tool to augment these processes. Here we explore what work has been done using data analytics and applications of ML in SCS. In addition, we discuss aspects of SCS which have narrowly been influenced by ML and propose the need for further exploration. ML has demonstrated a potential to complement SCS to an extent ranging from assistance with candidate selection to replacing invasive and costly aspects of the surgery. The clinical application of ML in SCS shows promise for improving patient outcomes, reducing costs of treatment, limiting invasiveness, and resulting in a better quality of life for the patient.

Development and Validation of a Machine Learning Model to Identify Patients Before Surgery at High Risk for Postoperative Adverse Events

Importance

Identifying patients at high risk of adverse outcomes prior to surgery may allow for interventions associated with improved postoperative outcomes; however, few tools exist for automated prediction.

Objective

To evaluate the accuracy of an automated machine-learning model in the identification of patients at high risk of adverse outcomes from surgery using only data in the electronic health record.

Design, Setting, and Participants

This prognostic study was conducted among 1 477 561 patients undergoing surgery at 20 community and tertiary care hospitals in the University of Pittsburgh Medical Center (UPMC) health network. The study included 3 phases: (1) building and validating a model on a retrospective population, (2) testing model accuracy on a retrospective population, and (3) validating the model prospectively in clinical care. A gradient-boosted decision tree machine learning method was used for developing a preoperative surgical risk prediction tool. The Shapley additive explanations method was used for model interpretability and further validation. Accuracy was compared between the UPMC model and National Surgical Quality Improvement Program (NSQIP) surgical risk calculator for predicting mortality. Data were analyzed from September through December 2021.

Exposure

Undergoing any type of surgical procedure.

Main Outcomes and Measures

Postoperative mortality and major adverse cardiac and cerebrovascular events (MACCEs) at 30 days were evaluated.

Results

Among 1 477 561 patients included in model development (806 148 females [54.5%; mean [SD] age, 56.8 [17.9] years), 1 016 966 patient encounters were used for training and 254 242 separate encounters were used for testing the model. After deployment in clinical use, another 206 353 patients were prospectively evaluated; an additional 902 patients were selected for comparing the accuracy of the UPMC model and NSQIP tool for predicting mortality. The area under the receiver operating characteristic curve (AUROC) for mortality was 0.972 (95% CI, 0.971-0.973) for the training set and 0.946 (95% CI, 0.943-0.948) for the test set. The AUROC for MACCE and mortality was 0.923 (95% CI, 0.922-0.924) on the training and 0.899 (95% CI, 0.896-0.902) on the test set. In prospective evaluation, the AUROC for mortality was 0.956 (95% CI, 0.953-0.959), sensitivity was 2148 of 2517 patients (85.3%), specificity was 186 286 of 203 836 patients (91.4%), and negative predictive value was 186 286 of 186 655 patients (99.8%). The model outperformed the NSQIP tool as measured by AUROC (0.945 [95% CI, 0.914-0.977] vs 0.897 [95% CI, 0.854-0.941], for a difference of 0.048), specificity (0.87 [95% CI, 0.83-0.89] vs 0.68 [95% CI, 0.65-0.69]), and accuracy (0.85 [95% CI, 0.82-0.87] vs 0.69 [95% CI, 0.66, 0.72]).

Conclusions and Relevance

This study found that an automated machine learning model was accurate in identifying patients undergoing surgery who were at high risk of adverse outcomes using only preoperative variables within the electronic health record, with superior performance compared with the NSQIP calculator. These findings suggest that using this model to identify patients at increased risk of adverse outcomes prior to surgery may allow for individualized perioperative care, which may be associated with improved outcomes.

Development of a machine learning algorithm to predict complications of total laparoscopic anterior resection and natural orifice specimen extraction surgery in rectal cancer

BACKGROUND

Total laparoscopic anterior resection (tLAR) and natural orifice specimen extraction surgery (NOSES) has been widely adopted in the treatment of rectal cancer (RC). However, no study has been performed to predict the short-term outcomes of tLAR using machine learning algorithms to analyze a national cohort.

METHODS

Data from consecutive RC patients who underwent tLAR were collected from the China NOSES Database (CNDB). The random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), deep neural network (DNN), logistic regression (LR) and K-nearest neighbor (KNN) algorithms were used to develop risk models to predict short-term complications of tLAR. The area under the receiver operating characteristic curve (AUROC), Gini coefficient, specificity and sensitivity were calculated to assess the performance of each risk model. The selected factors from the models were evaluated by relative importance.

RESULTS

A total of 4313 RC patients were identified, and 667 patients (15.5%) developed postoperative complications. The machine learning model of XGBoost showed more promising results in the prediction of complication than other models (AUROC 0.90, P < 0.001). The performance was similar when internal and external validation was used. In the XGBoost model, the top four influential factors were the distance from the lower edge of the tumor to the anus, age at diagnosis, surgical time and comorbidities. In risk stratification analysis, the rate of postoperative complications in the high-risk group was significantly higher than in the medium- and low-risk groups (P < 0.001).

CONCLUSION

The machine learning model shows potential benefits in predicting the risk of complications in RC patients after tLAR. This novel approach can provide reliable individual information for surgical treatment recommendations.

Assessment of the prognostic value of preoperative high-sensitive troponin T for myocardial injury and long-term mortality for groups at high risk for cardiovascular events following noncardiac surgery: a retrospective cohort study

Background

Few studies explored the association between high-sensitive cardiac troponin T (hs-cTnT) and long-term mortality for patients after surgery. This study was conducted to assess the association of hs-cTnT with long-term mortality and to investigate the extent to which this association is mediated via myocardial injury after noncardiac surgery (MINS).

Methods

This retrospective cohort study included all patients with hs-cTnT measurements who underwent non-cardiac surgery at Sichuan University West China Hospital. Data were collected from February 2018 and November 2020, with follow-up through February 2022. The primary outcome was all-cause mortality within 1 year. As secondary outcomes, MINS, length of hospital stay (LOS), and ICU admission were analyzed.

Results

The cohort included 7,156 patients (4,299 [60.1%] men; 61.0 [49.0-71.0] years). Among 7,156 patients, there were 2,151 (30.05%) with elevated hs-cTnT(>14 ng/L). After more than 1 year of follow-up, more than 91.8% of mortality information was available. During one-year follow-up after surgery, there were 308 deaths (14.8%) with a preoperative hs-cTnT >14 ng/L, compared with 192 deaths (3.9%) with a preoperative hs-cTnT <=14 ng/L(adjusted hazard ratio [aHR] 1.93, 95% CI 1.58-2.36; p < 0.001). Elevated preoperative hs-cTnT was also associated with several other adverse outcomes (MINS: adjusted odds ratio [aOR] 3.01; 95% CI, 2.46-3.69; p < 0.001; LOS: aOR 1.48, 95%CI 1.34-1.641; p < 0.001; ICU admission: aOR 1.52, 95%CI 1.31-1.76; p < 0.001). MINS explained approximately 33.6% of the variance in mortality due to preoperative hs-cTnT levels.

Conclusion

Preoperative elevated hs-cTnT concentrations have a significant association with long-term mortality after noncardiac surgery, one-third of which may by accounted for by MINS.

The digital transformation of surgery

Rapid advances in digital technology and artificial intelligence in recent years have already begun to transform many industries, and are beginning to make headway into healthcare. There is tremendous potential for new digital technologies to improve the care of surgical patients. In this piece, we highlight work being done to advance surgical care using machine learning, computer vision, wearable devices, remote patient monitoring, and virtual and augmented reality. We describe ways these technologies can be used to improve the practice of surgery, and discuss opportunities and challenges to their widespread adoption and use in operating rooms and at the bedside.

Exploring Artificial Intelligence in Anesthesia: A Primer on Ethics, and Clinical Applications

The field of anesthesia has always been at the forefront of innovation and technology, and the integration of Artificial Intelligence (AI) represents the next frontier in anesthesia care. The use of AI and its subtypes, such as machine learning, has the potential to improve efficiency, reduce costs, and ameliorate patient outcomes. AI can assist with decision making, but its primary advantage lies in empowering anesthesiologists to adopt a proactive approach to address clinical issues. The potential uses of AI in anesthesia can be schematically grouped into clinical decision support and pharmacologic and mechanical robotic applications. Tele-anesthesia includes strategies of telemedicine, as well as device networking, for improving logistics in the operating room, and augmented reality approaches for training and assistance. Despite the growing scientific interest, further research and validation are needed to fully understand the benefits and limitations of these applications in clinical practice. Moreover, the ethical implications of AI in anesthesia must also be considered to ensure that patient safety and privacy are not compromised. This paper aims to provide a comprehensive overview of AI in anesthesia, including its current and potential applications, and the ethical considerations that must be considered to ensure the safe and effective use of the technology.

Patient Embeddings From Diagnosis Codes for Health Care Prediction Tasks: Pat2Vec Machine Learning Framework

BACKGROUND

In health care, diagnosis codes in claims data and electronic health records (EHRs) play an important role in data-driven decision making. Any analysis that uses a patient's diagnosis codes to predict future outcomes or describe morbidity requires a numerical representation of this diagnosis profile made up of string-based diagnosis codes. These numerical representations are especially important for machine learning models. Most commonly, binary-encoded representations have been used, usually for a subset of diagnoses. In real-world health care applications, several issues arise: patient profiles show high variability even when the underlying diseases are the same, they may have gaps and not contain all available information, and a large number of appropriate diagnoses must be considered.

OBJECTIVE

We herein present Pat2Vec, a self-supervised machine learning framework inspired by neural network-based natural language processing that embeds complete diagnosis profiles into a small real-valued numerical vector.

METHODS

Based on German outpatient claims data with diagnosis codes according to the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10), we discovered an optimal vectorization embedding model for patient diagnosis profiles with Bayesian optimization for the hyperparameters. The calibration process ensured a robust embedding model for health care-relevant tasks by aggregating the metrics of different regression and classification tasks using different machine learning algorithms (linear and logistic regression as well as gradient-boosted trees). The models were tested against a baseline model that binary encodes the most common diagnoses. The study used diagnosis profiles and supplementary data from more than 10 million patients from 2016 to 2019 and was based on the largest German ambulatory claims data set. To describe subpopulations in health care, we identified clusters (via density-based clustering) and visualized patient vectors in 2D (via dimensionality reduction with uniform manifold approximation). Furthermore, we applied our vectorization model to predict prospective drug prescription costs based on patients' diagnoses.

RESULTS

Our final models outperform the baseline model (binary encoding) with equal dimensions. They are more robust to missing data and show large performance gains, particularly in lower dimensions, demonstrating the embedding model's compression of nonlinear information. In the future, other sources of health care data can be integrated into the current diagnosis-based framework. Other researchers can apply our publicly shared embedding model to their own diagnosis data.

CONCLUSIONS

We envision a wide range of applications for Pat2Vec that will improve health care quality, including personalized prevention and signal detection in patient surveillance as well as health care resource planning based on subcohorts identified by our data-driven machine learning framework.

Association between hospital surgical case volume and postoperative mortality in patients undergoing gastrectomy for gastric cancer: a systematic review and meta-analysis

BACKGROUND

Postoperative mortality is an important indicator for evaluating surgical safety. Postoperative mortality is influenced by hospital volume; however, this association is not fully understood. This study aimed to investigate the volume-outcome association between the hospital surgical case volume for gastrectomies per year (hospital volume) and the risk of postoperative mortality in patients undergoing a gastrectomy for gastric cancer.

METHODS

Studies assessing the association between hospital volume and the postoperative mortality in patients who underwent gastrectomy for gastric cancer were searched for eligibility. Odds ratios were pooled for the highest versus lowest categories of hospital volume using a random-effects model. The volume-outcome association between hospital volume and the risk of postoperative mortality was analyzed. The study protocol was registered with Prospective Register of Systematic Reviews (PROSPERO).

RESULTS

Thirty studies including 586 993 participants were included. The risk of postgastrectomy mortality in patients with gastric cancer was 35% lower in hospitals with higher surgical case volumes than in their lower-volume counterparts (odds ratio: 0.65; 95% CI: 0.56-0.76; P <0.001). This relationship was consistent and robust in most subgroup analyses. Volume-outcome analysis found that the postgastrectomy mortality rate remained stable or was reduced after the hospital volume reached a plateau of 100 gastrectomy cases per year.

CONCLUSIONS

The current findings suggest that a higher-volume hospital can reduce the risk of postgastrectomy mortality in patients with gastric cancer, and that greater than or equal to 100 gastrectomies for gastric cancer per year may be defined as a high hospital surgical case volume.

Cognitive Bias and Dissonance in Surgical Practice: A Narrative Review

A cognitive bias describes "shortcuts" subconsciously applied to new scenarios to simplify decision-making. Unintentional introduction of cognitive bias in surgery may result in surgical diagnostic error that leads to delayed surgical care, unnecessary procedures, intraoperative complications, and delayed recognition of postoperative complications. Data suggest that surgical error secondary to the introduction of cognitive bias results in significant harm. Thus, debiasing is a growing area of research which urges practitioners to deliberately slow decision-making to reduce the effects of cognitive bias.

Machine Learning and Artificial Intelligence in Surgical Research

Machine learning, a subtype of artificial intelligence, is an emerging field of surgical research dedicated to predictive modeling. From its inception, machine learning has been of interest in medical and surgical research. Built on traditional research metrics for optimal success, avenues of research include diagnostics, prognosis, operative timing, and surgical education, in a variety of surgical subspecialties. Machine learning represents an exciting and developing future in the world of surgical research that will not only allow for more personalized and comprehensive medical care.

How do serum lipid levels change and influence progression-free survival in epithelial ovarian cancer patients receiving bevacizumab treatment?

Background

This study aimed to investigate how serum lipid levels affect epithelial ovarian cancer (EOC) patients receiving bevacizumab treatment and to develop a model for predicting the patients’ prognosis.

Methods

A total of 139 EOC patients receiving bevacizumab treatment were involved in this study. Statistical analysis was used to compare the median and average values of serum lipid level variables between the baseline and final follow-up. Additionally, a method based on machine learning was proposed to identify independent risk factors for estimating progression-free survival (PFS) in EOC patients receiving bevacizumab treatment. A PFS nomogram dividing the patients into low- and high-risk categories was created based on these independent prognostic variables. Finally, Kaplan–Meier curves and log-rank tests were utilized to perform survival analysis.

Results

Among EOC patients involved in this study, statistical analysis of serum lipid level variables revealed a substantial increase in total cholesterol, triglycerides, apolipoprotein A1, and free fatty acids, and a significant decrease in apolipoprotein B from baseline to final follow-up. Our method identified FIGO stage, combined chemotherapy regimen, activated partial thromboplastin time, globulin, direct bilirubin, free fatty acids, blood urea nitrogen, high-density lipoprotein cholesterol, and triglycerides as risk factors. These risk factors were then included in our nomogram as independent predictors for EOC patients. PFS was substantially different between the low-risk group (total score &lt; 298) and the high-risk group (total score ≥ 298) according to Kaplan–Meier curves (P &lt; 0.05).

Conclusion

Serum lipid levels changed variously in EOC patients receiving bevacizumab treatment. A prediction model for PFS of EOC patients receiving bevacizumab treatment was constructed, and it can be beneficial in determining the prognosis, selecting a treatment plan, and monitoring these patients’ long-term care.

A Predictive Model for Chronic Hydrocephalus After Clipping Aneurysmal Subarachnoid Hemorrhage

Chronic hydrocephalus after clipping aneurysmal subarachnoid hemorrhage (aSAH) often results in poor outcomes. This study was to establish and validate model to predict chronic hydrocephalus after aSAH by least absolute shrinkage and selection operator logistic regression. The model was constructed from a retrospectively analyzed. Two hundred forty-eight patients of aSAH were analyzed retrospectively in our hospital from January 2019 to December 2021, and the patients were divided into chronic hydrocephalus (CH) group (n=55) and non-CH group (n=193) according to whether occurred CH within 3 months. In summary, 16 candidate risk factors related to chronic hydrocephalus after aSAH were analyzed. Univariate analysis was performed to judging the risk factors for CH. The least absolute shrinkage and selection operator regression was used to filter risk factors. Subsequently, the nomogram was designed by the above variables. And area under the curve and calibration chart were used to detect the discrimination and goodness of fit of the nomogram, respectively. Finally, decision curve analysis was constructed to assess the practicability of the risk of chronic hydrocephalus by calculating the net benefits. Univariate analysis showed that age (60 y or older), aneurysm location, modified Fisher grade, Hunt-Hess grade, and the method for cerebrospinal fluid drainage, intracranial infections, and decompressive craniectomy were significantly related to CH ( P <0.05). Whereas 5 variables [age (60 y or older), posterior aneurysm, modified Fisher grade, Hunt-Hess grade, decompression craniectomy] from 16 candidate factors were filtered by LASSO logistic regression for further research. Area under the curve of this model was 0.892 (95% confidence interval: 0.799-0.981), indicating a good discrimination ability. Meanwhile, the result of calibration indicated a good fitting between the prediction probability and the actual probability. Finally, decision curve analysis showed a good clinical efficacy. In summary, this model could conveniently predict the occurrence of chronic hydrocephalus after aSAH. Meanwhile, it could help physicians to develop personalized treatment and close follow-up for these patients.

Prediction of Prednisolone Dose Correction Using Machine Learning

Wrong dose, a common prescription error, can cause serious patient harm, especially in the case of high-risk drugs like oral corticosteroids. This study aims to build a machine learning model to predict dose-related prescription modifications for oral prednisolone tablets (i.e., highly imbalanced data with very few positive cases). Prescription data were obtained from the electronic medical records at a single institute. Cluster analysis classified the clinical departments into six clusters with similar patterns of prednisolone prescription. Two patterns of training datasets were created with/without preprocessing by the SMOTE method. Five ML models (SVM, KNN, GB, RF, and BRF) and logistic regression (LR) models were constructed by Python. The model was internally validated by five-fold stratified cross-validation and was validated with a 30% holdout test dataset. Eighty-two thousand five hundred fifty-three prescribing data for prednisolone tablets containing 135 dose-corrected positive cases were obtained. In the original dataset (without SMOTE), only the BRF model showed a good performance (in test dataset, ROC-AUC:0.917, recall: 0.951). In the training dataset preprocessed by SMOTE, performance was improved on all models. The highest performance models with SMOTE were SVM (in test dataset, ROC-AUC: 0.820, recall: 0.659) and BRF (ROC-AUC: 0.814, recall: 0.634). Although the prescribing data for dose-related collection are highly imbalanced, various techniques such as the following have allowed us to build high-performance prediction models: data preprocessing by SMOTE, stratified cross-validation, and BRF classifier corresponding to imbalanced data. ML is useful in complicated dose audits such as oral prednisolone.

Supplementary Information

The online version contains supplementary material available at 10.1007/s41666-023-00128-3.

Performance and usability of pre-operative prediction models for 30-day peri-operative mortality risk: a systematic review

Estimating pre-operative mortality risk may inform clinical decision-making for peri-operative care. However, pre-operative mortality risk prediction models are rarely implemented in routine clinical practice. High predictive accuracy and clinical usability are essential for acceptance and clinical implementation. In this systematic review, we identified and appraised prediction models for 30-day postoperative mortality in non-cardiac surgical cohorts. PubMed and Embase were searched up to December 2022 for studies investigating pre-operative prediction models for 30-day mortality. We assessed predictive performance in terms of discrimination and calibration. Risk of bias was evaluated using a tool to assess the risk of bias and applicability of prediction model studies. To further inform potential adoption, we also assessed clinical usability for selected models. In all, 15 studies evaluating 10 prediction models were included. Discrimination ranged from a c-statistic of 0.82 (MySurgeryRisk) to 0.96 (extreme gradient boosting machine learning model). Calibration was reported in only six studies. Model performance was highest for the surgical outcome risk tool (SORT) and its external validations. Clinical usability was highest for the surgical risk pre-operative assessment system. The SORT and risk quantification index also scored high on clinical usability. We found unclear or high risk of bias in the development of all models. The SORT showed the best combination of predictive performance and clinical usability and has been externally validated in several heterogeneous cohorts. To improve clinical uptake, full integration of reliable models with sufficient face validity within the electronic health record is imperative.

Necessity and Importance of Developing AI in Anesthesia from the Perspective of Clinical Safety and Information Security

The rapid development of artificial intelligence (AI) technology is due to the significant progress in big data, databases, algorithms, and computing power, and medical research is a vital application direction of AI. The integrated development of AI and medicine has improved medical technology, and the efficiency of medical services and equipment has enabled doctors to better serve patients. The tasks and characteristics of the anesthesia discipline also make AI necessary for its development, and AI has also been initially applied in different fields of anesthesia. Our review aims to clarify the current situation and challenges of AI application in anesthesiology to provide clinical references and guide the future development of AI in anesthesiology. This review summarizes progress in the application of AI in perioperative risk assessment and prediction, deep monitoring and regulation of anesthesia, essential anesthesia skills operation, automatic drug administration systems, and teaching and training in anesthesia. Also discussed herein are the accompanying risks and challenges of applying AI in anesthesia: patient privacy and information security, data sources, and ethical issues, lack of capital and talent, and the "black box" phenomenon.

Building an automated, machine learning-enabled platform for predicting post-operative complications

Objective. In 2019, the University of Florida College of Medicine launched theMySurgeryRiskalgorithm to predict eight major post-operative complications using automatically extracted data from the electronic health record.Approach. This project was developed in parallel with our Intelligent Critical Care Center and represents a culmination of efforts to build an efficient and accurate model for data processing and predictive analytics.Main Results and Significance. This paper discusses how our model was constructed and improved upon. We highlight the consolidation of the database, processing of fixed and time-series physiologic measurements, development and training of predictive models, and expansion of those models into different aspects of patient assessment and treatment. We end by discussing future directions of the model.

Development of a Human Immunodeficiency Virus Risk Prediction Model Using Electronic Health Record Data From an Academic Health System in the Southern United States

BACKGROUND

Human immunodeficiency virus (HIV) pre-exposure prophylaxis (PrEP) is underutilized in the southern United States. Rapid identification of individuals vulnerable to diagnosis of HIV using electronic health record (EHR)-based tools may augment PrEP uptake in the region.

METHODS

Using machine learning, we developed EHR-based models to predict incident HIV diagnosis as a surrogate for PrEP candidacy. We included patients from a southern medical system with encounters between October 2014 and August 2016, training the model to predict incident HIV diagnosis between September 2016 and August 2018. We obtained 74 EHR variables as potential predictors. We compared Extreme Gradient Boosting (XGBoost) versus least absolute shrinkage selection operator (LASSO) logistic regression models, and assessed performance, overall and among women, using area under the receiver operating characteristic curve (AUROC) and area under precision recall curve (AUPRC).

RESULTS

Of 998 787 eligible patients, 162 had an incident HIV diagnosis, of whom 49 were women. The XGBoost model outperformed the LASSO model for the total cohort, achieving an AUROC of 0.89 and AUPRC of 0.01. The female-only cohort XGBoost model resulted in an AUROC of 0.78 and AUPRC of 0.00025. The most predictive variables for the overall cohort were race, sex, and male partner. The strongest positive predictors for the female-only cohort were history of pelvic inflammatory disease, drug use, and tobacco use.

CONCLUSIONS

Our machine-learning models were able to effectively predict incident HIV diagnoses including among women. This study establishes feasibility of using these models to identify persons most suitable for PrEP in the South.

Implementing machine learning methods with complex survey data: Lessons learned on the impacts of accounting sampling weights in gradient boosting

Despite the prominent use of complex survey data and the growing popularity of machine learning methods in epidemiologic research, few machine learning software implementations offer options for handling complex samples. A major challenge impeding the broader incorporation of machine learning into epidemiologic research is incomplete guidance for analyzing complex survey data, including the importance of sampling weights for valid prediction in target populations. Using data from 15, 820 participants in the 1988-1994 National Health and Nutrition Examination Survey cohort, we determined whether ignoring weights in gradient boosting models of all-cause mortality affected prediction, as measured by the F1 score and corresponding 95% confidence intervals. In simulations, we additionally assessed the impact of sample size, weight variability, predictor strength, and model dimensionality. In the National Health and Nutrition Examination Survey data, unweighted model performance was inflated compared to the weighted model (F1 score 81.9% [95% confidence interval: 81.2%, 82.7%] vs 77.4% [95% confidence interval: 76.1%, 78.6%]). However, the error was mitigated if the F1 score was subsequently recalculated with observed outcomes from the weighted dataset (F1: 77.0%; 95% confidence interval: 75.7%, 78.4%). In simulations, this finding held in the largest sample size (N = 10,000) under all analytic conditions assessed. For sample sizes <5,000, sampling weights had little impact in simulations that more closely resembled a simple random sample (low weight variability) or in models with strong predictors, but findings were inconsistent under other analytic scenarios. Failing to account for sampling weights in gradient boosting models may limit generalizability for data from complex surveys, dependent on sample size and other analytic properties. In the absence of software for configuring weighted algorithms, post-hoc re-calculations of unweighted model performance using weighted observed outcomes may more accurately reflect model prediction in target populations than ignoring weights entirely.

Effect of Present at Time of Surgery on Unadjusted and Risk-Adjusted Postoperative Complication Rate

BACKGROUND

Present at the time of surgery (PATOS) is an important measure to collect in postoperative complication surveillance systems because it may affect a patient's risk of a subsequent complication and the estimation of postoperative complication rates attributed to the healthcare system. The American College of Surgeons (ACS) NSQIP started collecting PATOS data for 8 postoperative complications in 2011, but no one has used these data to quantify how this may affect unadjusted and risk-adjusted postoperative complication rates.

STUDY DESIGN

This study was a retrospective observational study of the ACS NSQIP database from 2012 to 2018. PATOS data were analyzed for the 8 postoperative complications of superficial, deep, and organ space surgical site infection; pneumonia; urinary tract infection; ventilator dependence; sepsis; and septic shock. Unadjusted postoperative complication rates were compared ignoring PATOS vs taking PATOS into account. Observed to expected ratios over time were also compared by calculating expected values using multiple logistic regression analyses with complication as the dependent variable and the 28 nonlaboratory preoperative variables in the ACS NSQIP database as the independent variables.

RESULTS

In 5,777,108 patients, observed event rates for each outcome were reduced by between 6.1% (superficial surgical site infection) and 52.5% (sepsis) when PATOS was taken into account. The observed to expected ratios were similar each year for all outcomes, except for sepsis and septic shock in the early years.

CONCLUSIONS

Taking PATOS into account is important for reporting unadjusted event rates. The effect varied by type of complication-lowest for superficial surgical site infection and highest for sepsis and septic shock. Taking PATOS into account was less important for risk-adjusted outcomes (observed to expected ratios), except for sepsis and septic shock.