Development and Validation of a Machine Learning Model to Aid Discharge Processes for Inpatient Surgical Care

A systematic literature review of predicting patient discharges using statistical methods and machine learning

Discharge planning is integral to patient flow as delays can lead to hospital-wide congestion. Because a structured discharge plan can reduce hospital length of stay while enhancing patient satisfaction, this topic has caught the interest of many healthcare professionals and researchers. Predicting discharge outcomes, such as destination and time, is crucial in discharge planning by helping healthcare providers anticipate patient needs and resource requirements. This article examines the literature on the prediction of various discharge outcomes. Our review discovered papers that explore the use of prediction models to forecast the time, volume, and destination of discharged patients. Of the 101 reviewed papers, 49.5% looked at the prediction with machine learning tools, and 50.5% focused on prediction with statistical methods. The fact that knowing discharge outcomes in advance affects operational, tactical, medical, and administrative aspects is a frequent theme in the papers studied. Furthermore, conducting system-wide optimization, predicting the time and destination of patients after discharge, and addressing the primary causes of discharge delay in the process are among the recommendations for further research in this field.

Nursing workload: use of artificial intelligence to develop a classifier model

OBJECTIVE

to describe the development of a predictive nursing workload classifier model, using artificial intelligence.

METHOD

retrospective observational study, using secondary sources of electronic patient records, using machine learning. The convenience sample consisted of 43,871 assessments carried out by clinical nurses using the Perroca Patient Classification System, which served as the gold standard, and clinical data from the electronic medical records of 11,774 patients, which constituted the variables. In order to organize the data and carry out the analysis, the Dataiku® data science platform was used. Data analysis occurred in an exploratory, descriptive and predictive manner. The study was approved by the Ethics and Research Committee of the institution where the study was carried out.

RESULTS

the use of artificial intelligence enabled the development of the nursing workload assessment classifier model, identifying the variables that most contributed to its prediction. The algorithm correctly classified 72% of the variables and the area under the Receiver Operating Characteristic curve was 82%.

CONCLUSION

a predictive model was developed, demonstrating that it is possible to train algorithms with data from the patient's electronic medical record to predict the nursing workload and that artificial intelligence tools can be effective in automating this activity.

Artificial intelligence in surgery

Artificial intelligence (AI) is rapidly emerging in healthcare, yet applications in surgery remain relatively nascent. Here we review the integration of AI in the field of surgery, centering our discussion on multifaceted improvements in surgical care in the preoperative, intraoperative and postoperative space. The emergence of foundation model architectures, wearable technologies and improving surgical data infrastructures is enabling rapid advances in AI interventions and utility. We discuss how maturing AI methods hold the potential to improve patient outcomes, facilitate surgical education and optimize surgical care. We review the current applications of deep learning approaches and outline a vision for future advances through multimodal foundation models.

First deployment of artificial intelligence recommendations in orthopedic surgery

Scant research has delved into the non-clinical facets of artificial intelligence (AI), concentrating on leveraging data to enhance the efficiency of healthcare systems and operating rooms. Notably, there is a gap in the literature regarding the implementation and outcomes of AI solutions. The absence of published results demonstrating the practical application and effectiveness of AI in domains beyond clinical settings, particularly in the field of surgery, served as the impetus for our undertaking in this area. Within the realm of non-clinical strategies aimed at enhancing operating room efficiency, we characterize OR efficiency as the capacity to successfully perform four uncomplicated arthroplasty surgeries within an 8-h timeframe. This Community Case Study addresses this gap by presenting the results of incorporating AI recommendations at our clinical institute on 228 patient arthroplasty surgeries. The implementation of a prescriptive analytics system (PAS), utilizing supervised machine learning techniques, led to a significant improvement in the overall efficiency of the operating room, increasing it from 39 to 93%. This noteworthy achievement highlights the impact of AI in optimizing surgery workflows.

Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study

Background

Nursing narratives are an intriguing feature in the prediction of short-term clinical outcomes. However, it is unclear which nursing narratives significantly impact the prediction of postoperative length of stay (LOS) in deep learning models.

Objective

Therefore, we applied the Reverse Time Attention (RETAIN) model to predict LOS, entering nursing narratives as the main input.

Methods

A total of 354 patients who underwent ovarian cancer surgery at the Seoul National University Bundang Hospital from 2014 to 2020 were retrospectively enrolled. Nursing narratives collected within 3 postoperative days were used to predict prolonged LOS (≥10 days). The physician's assessment was conducted based on a retrospective review of the physician's note within the same period of the data model used.

Results

The model performed better than the physician's assessment (area under the receiver operating curve of 0.81 vs 0.58; P=.02). Nursing narratives entered on the first day were the most influential predictors in prolonged LOS. The likelihood of prolonged LOS increased if the physician had to check the patient often and if the patient received intravenous fluids or intravenous patient-controlled analgesia late.

Conclusions

The use of the RETAIN model on nursing narratives predicted postoperative LOS effectively for patients who underwent ovarian cancer surgery. These findings suggest that accurate and interpretable deep learning information obtained shortly after surgery may accurately predict prolonged LOS.

On the Horizon: Specific Applications of Automation and Artificial Intelligence in Anesthesiology

Purpose of Review

The purpose of this review is to summarize the current research and critically examine artificial intelligence (AI) technologies and their applicability to the daily practice of anesthesiologists.

Recent Findings

Novel AI tools are developed using data from electronic health records, imaging, waveforms, clinical notes, and wearables. These tools can accurately predict the perioperative risk for adverse outcomes, the need for blood transfusion, and the risk of difficult intubation. Intraoperatively, AI models can assist with technical skill augmentation, patient monitoring, and management. Postoperatively, AI technology can aid in preventing complications and discharge planning. While further prospective validation is needed, these early applications demonstrate promise in every area of perioperative care.

Summary

The practice of anesthesiology is at a precipice fueled by technological innovation. The clinical AI implementation would enable personalized and safer patient care by offering actionable insights from the wealth of perioperative data.

Early Expected Discharge Date Accuracy During Hospitalization: A Multivariable Analysis

INTRODUCTION

Accurate estimation of an expected discharge date (EDD) early during hospitalization impacts clinical operations and discharge planning.

METHODS

We conducted a retrospective study of patients discharged from six general medicine units at an academic medical center in Boston, MA from January 2017 to June 2018. We retrieved all EDD entries and patient, encounter, unit, and provider data from the electronic health record (EHR), and public weather data. We excluded patients who expired, discharged against medical advice, or lacked an EDD within the first 24 h of hospitalization. We used generalized estimating equations in a multivariable logistic regression analysis to model early EDD accuracy (an accurate EDD entered within 24 h of admission), adjusting for all covariates and clustering by patient. We similarly constructed a secondary multivariable model using covariates present upon admission alone.

RESULTS

Of 3917 eligible hospitalizations, 890 (22.7%) had at least one accurate early EDD entry. Factors significantly positively associated (OR > 1) with an accurate early EDD included clinician-entered EDD, admit day and discharge day during the work week, and teaching clinical units. Factors significantly negatively associated (OR < 1) with an accurate early EDD included Elixhauser Comorbidity Index ≥ 11 and length of stay of two or more days. C-statistics for the primary and secondary multivariable models were 0.75 and 0.60, respectively.

CONCLUSIONS

EDDs entered within the first 24 h of admission were often inaccurate. While several variables from the EHR were associated with accurate early EDD entries, few would be useful for prospective prediction.

Implementing a discharge process for patients undergoing elective surgery: Rapid review

BACKGROUND

Hospital discharge is a 'vulnerable stage' in care. A delayed, inappropriate or poorly planned discharge increases hazards and costs, inhibiting recovery, and often leading to unplanned readmission. New discharge processes could boost practice, reduce the length of stay, and, consequently, reduce costs and improve patients' quality of life.

AIM

To identify technology based interventions that have been implemented to facilitate a safe and timely discharge procedure after elective surgery, and to describe implementation barriers and facilitators and patient satisfaction.

METHOD

This rapid review followed a restricted systematic review framework, searching Medline, EMBASE, CINAHL, PsychINFO, and ClinicalTrials.gov. for relevant studies published from 2015 to 2021 in English.

RESULTS

Eleven studies were included. Most interventions were machine-learning-based, and only one study reported patient involvement. Effective leadership, team work and communication were stated as implementation facilitators. The main barriers to implementation were: lack of support from leaders, poor clinical documentation, resistance to change, and financial and logistical concerns. None of the studies evaluated patient satisfaction.

CONCLUSIONS

Findings highlight factors that support the implementation of technology based interventions aimed at a safe and timely discharge process following elective surgery. Nurses play an important role in the provision of information, and in the development and implementation of discharge processes.

A Synopsis of Artificial Intelligence and its Applications in Surgery

Artificial intelligence (AI) has made steady in-roads into the healthcare scenario over the last decade. While widespread adoption into clinical practice remains elusive, the outreach of this discipline has progressed beyond the physician scientist, and different facets of this technology have been incorporated into the care of surgical patients. New AI applications are developing at rapid pace, and it is imperative that the general surgeon be aware of the broad utility of AI as applicable in his or her day-to-day practice, so that healthcare continues to remain up-to-date and evidence based. This review provides a broad account of the tip of the AI iceberg and highlights it potential for positively impacting surgical care.

Planning with care complexity: Factors related to discharge delays of hospitalised people with disability

Planning for discharge and supports beyond hospital for people with disability in Australia involves negotiation of complex care systems. The aims of this study were to examine how the individualised support pathway of the National Disability Insurance Scheme (NDIS) functioned for admitted people with disability who required funded support to leave hospital; and to explore the factors indicative of increased care complexity associated with delays. Retrospective chart reviews of people with disability were conducted. Data on 198 eligible patients were extracted, including NDIS plan approval and plan implementation timeframes and discharge delay. Participants' median age was 52 years (interquartile range = 41-59). The most common disability type was spinal cord injury (41%). The median NDIS plan approval and implementation timeframes were 89 days (63-123) and 39 days (8-131), respectively, and most participants (72%) experienced a delayed discharge. A longer plan implementation timeframe was associated with higher odds of a delay in discharge (OR = 3.41, 95% credible interval = 1.56, 7.11). We did not find any evidence that plan approval timeframe, or any other variable indicative of increased care complexity, was associated with discharge delays. Our findings suggest that a delayed discharge will likely be the reality for people with disability who require funded supports to leave hospital. They also suggest that NDIS plan implementation is a major challenge and a focus for policy and practice improvements. To target solutions, further research should focus on the interactions and negotiations of the multiple intermediaries involved and resource and structural impediments to plan implementation.

Early prediction of patient discharge disposition in acute neurological care using machine learning

BACKGROUND

Acute neurological complications are some of the leading causes of death and disability in the U.S. The medical professionals that treat patients in this setting are tasked with deciding where (e.g., home or facility), how, and when to discharge these patients. It is important to be able to predict potential patient discharge outcomes as early as possible during the patient's hospital stay and to know what factors influence the development of discharge planning. This study carried out two parallel experiments: A multi-class outcome (patient discharge targets of 'home', 'nursing facility', 'rehab', 'death') and binary class outcome ('home' vs. 'non-home'). The goal of this study is to develop early predictive models for each experiment exploring which patient characteristics and clinical variables significantly influence discharge planning of patients based on the data that are available only within 24 h of their hospital admission.  METHOD: Our methodology centers around building and training five different machine learning models followed by testing and tuning those models to find the best-suited predictor for each experiment with a dataset of 5,245 adult patients with neurological conditions taken from the eICU-CRD database.

RESULTS

The results of this study show XGBoost to be the most effective model for predicting between four common discharge outcomes of 'home', 'nursing facility', 'rehab', and 'death', with 71% average c-statistic. The XGBoost model was also the best-performer in the binary outcome experiment with a c-statistic of 76%. This article also explores the accuracy, reliability, and interpretability of the best performing models in each experiment by identifying and analyzing the features that are most impactful to the predictions.

CONCLUSIONS

The acceptable accuracy and interpretability of the predictive models based on early admission data suggests that the models can be used in a suggestive context to help guide healthcare providers in efforts of planning effective and equitable discharge recommendations.

Artificial intelligence assisted acute patient journey

Artificial intelligence is taking the world by storm and soon will be aiding patients in their journey at the hospital. The trials and tribulations of the healthcare system during the COVID-19 pandemic have set the stage for shifting healthcare from a physical to a cyber-physical space. A physician can now remotely monitor a patient, admitting them only if they meet certain thresholds, thereby reducing the total number of admissions at the hospital. Coordination, communication, and resource management have been core issues for any industry. However, it is most accurate in healthcare. Both systems and providers are exhausted under the burden of increasing data and complexity of care delivery, increasing costs, and financial burden. Simultaneously, there is a digital transformation of healthcare in the making. This transformation provides an opportunity to create systems of care that are artificial intelligence-enabled. Healthcare resources can be utilized more justly. The wastage of financial and intellectual resources in an overcrowded healthcare system can be avoided by implementing IoT, telehealth, and AI/ML-based algorithms. It is imperative to consider the design principles of the patient's journey while simultaneously prioritizing a better user experience to alleviate physician concerns. This paper discusses the entire blueprint of the AI/ML-assisted patient journey and its impact on healthcare provision.

Development of artificial neural networks for early prediction of intestinal perforation in preterm infants

Intestinal perforation (IP) in preterm infants is a life-threatening condition that may result in serious complications and increased mortality. Early Prediction of IP in infants is important, but challenging due to its multifactorial and complex nature of the disease. Thus, there are no reliable tools to predict IP in infants. In this study, we developed new machine learning (ML) models for predicting IP in very low birth weight (VLBW) infants and compared their performance to that of classic ML methods. We developed artificial neural networks (ANNs) using VLBW infant data from a nationwide cohort and prospective web-based registry. The new ANN models, which outperformed all other classic ML methods, showed an area under the receiver operating characteristic curve (AUROC) of 0.8832 for predicting IP associated with necrotizing enterocolitis (NEC-IP) and 0.8797 for spontaneous IP (SIP). We tested these algorithms using patient data from our institution, which were not included in the training dataset, and obtained an AUROC of 1.0000 for NEC-IP and 0.9364 for SIP. NEC-IP and SIP in VLBW infants can be predicted at an excellent performance level with these newly developed ML models. https://github.com/kdhRick2222/Early-Prediction-of-Intestinal-Perforation-in-Preterm-Infants.

Optimizing discharge after major surgery using an artificial intelligence-based decision support tool (DESIRE): An external validation study

BACKGROUND

In the DESIRE study (Discharge aftEr Surgery usIng aRtificial intElligence), we have previously developed and validated a machine learning concept in 1,677 gastrointestinal and oncology surgery patients that can predict safe hospital discharge after the second postoperative day. Despite strong model performance (area under the receiver operating characteristics curve of 0.88) in an academic surgical population, it remains unknown whether these findings can be translated to other hospitals and surgical populations. We therefore aimed to determine the generalizability of the previously developed machine learning concept.

METHODS

We externally validated the machine learning concept in gastrointestinal and oncology surgery patients admitted to 3 nonacademic hospitals in The Netherlands between January 2017 and June 2021, who remained admitted 2 days after surgery. Primary outcome was the ability to predict hospital interventions after the second postoperative day, which were defined as unplanned reoperations, radiological interventions, and/or intravenous antibiotics administration. Four forest models were locally trained and evaluated with respect to area under the receiver operating characteristics curve, sensitivity, specificity, positive predictive value, and negative predictive value.

RESULTS

All models were trained on 1,693 epsiodes, of which 731 (29.9%) required a hospital intervention and demonstrated strong performance (area under the receiver operating characteristics curve only varied 4%). The best model achieved an area under the receiver operating characteristics curve of 0.83 (95% confidence interval [0.81-0.85]), sensitivity of 77.9% (0.67-0.87), specificity of 79.2% (0.72-0.85), positive predictive value of 61.6% (0.54-0.69), and negative predictive value of 89.3% (0.85-0.93).

CONCLUSION

This study showed that a previously developed machine learning concept can predict safe discharge in different surgical populations and hospital settings (academic versus nonacademic) by training a model on local patient data. Given its high accuracy, integration of the machine learning concept into the clinical workflow could expedite surgical discharge and aid hospitals in addressing capacity challenges by reducing avoidable bed-days.

A scoping review of artificial intelligence applications in thoracic surgery

OBJECTIVES

Machine learning (ML) has great potential, but there are few examples of its implementation improving outcomes. The thoracic surgeon must be aware of pertinent ML literature and how to evaluate this field for the safe translation to patient care. This scoping review provides an introduction to ML applications specific to the thoracic surgeon. We review current applications, limitations and future directions.

METHODS

A search of the PubMed database was conducted with inclusion requirements being the use of an ML algorithm to analyse patient information relevant to a thoracic surgeon and contain sufficient details on the data used, ML methods and results. Twenty-two papers met the criteria and were reviewed using a methodological quality rubric.

RESULTS

ML demonstrated enhanced preoperative test accuracy, earlier pathological diagnosis, therapies to maximize survival and predictions of adverse events and survival after surgery. However, only 4 performed external validation. One demonstrated improved patient outcomes, nearly all failed to perform model calibration and one addressed fairness and bias with most not generalizable to different populations. There was a considerable variation to allow for reproducibility.

CONCLUSIONS

There is promise but also challenges for ML in thoracic surgery. The transparency of data and algorithm design and the systemic bias on which models are dependent remain issues to be addressed. Although there has yet to be widespread use in thoracic surgery, it is essential thoracic surgeons be at the forefront of the eventual safe introduction of ML to the clinic and operating room.

Opal: an implementation science tool for machine learning clinical decision support in anesthesia

Opal is the first published example of a full-stack platform infrastructure for an implementation science designed for ML in anesthesia that solves the problem of leveraging ML for clinical decision support. Users interact with a secure online Opal web application to select a desired operating room (OR) case cohort for data extraction, visualize datasets with built-in graphing techniques, and run in-client ML or extract data for external use. Opal was used to obtain data from 29,004 unique OR cases from a single academic institution for pre-operative prediction of post-operative acute kidney injury (AKI) based on creatinine KDIGO criteria using predictors which included pre-operative demographic, past medical history, medications, and flowsheet information. To demonstrate utility with unsupervised learning, Opal was also used to extract intra-operative flowsheet data from 2995 unique OR cases and patients were clustered using PCA analysis and k-means clustering. A gradient boosting machine model was developed using an 80/20 train to test ratio and yielded an area under the receiver operating curve (ROC-AUC) of 0.85 with 95% CI [0.80–0.90]. At the default probability decision threshold of 0.5, the model sensitivity was 0.9 and the specificity was 0.8. K-means clustering was performed to partition the cases into two clusters and for hypothesis generation of potential groups of outcomes related to intraoperative vitals. Opal’s design has created streamlined ML functionality for researchers and clinicians in the perioperative setting and opens the door for many future clinical applications, including data mining, clinical simulation, high-frequency prediction, and quality improvement.

Predicting next-day discharge via electronic health record access logs

OBJECTIVE

Hospital capacity management depends on accurate real-time estimates of hospital-wide discharges. Estimation by a clinician requires an excessively large amount of effort and, even when attempted, accuracy in forecasting next-day patient-level discharge is poor. This study aims to support next-day discharge predictions with machine learning by incorporating electronic health record (EHR) audit log data, a resource that captures EHR users' granular interactions with patients' records by communicating various semantics and has been neglected in outcome predictions.

MATERIALS AND METHODS

This study focused on the EHR data for all adults admitted to Vanderbilt University Medical Center in 2019. We learned multiple advanced models to assess the value that EHR audit log data adds to the daily prediction of discharge likelihood within 24 h and to compare different representation strategies. We applied Shapley additive explanations to identify the most influential types of user-EHR interactions for discharge prediction.

RESULTS

The data include 26 283 inpatient stays, 133 398 patient-day observations, and 819 types of user-EHR interactions. The model using the count of each type of interaction in the recent 24 h and other commonly used features, including demographics and admission diagnoses, achieved the highest area under the receiver operating characteristics (AUROC) curve of 0.921 (95% CI: 0.919-0.923). By contrast, the model lacking user-EHR interactions achieved a worse AUROC of 0.862 (0.860-0.865). In addition, 10 of the 20 (50%) most influential factors were user-EHR interaction features.

CONCLUSION

EHR audit log data contain rich information such that it can improve hospital-wide discharge predictions.

Improving patient flow during infectious disease outbreaks using machine learning for real-time prediction of patient readiness for discharge

BACKGROUND

Delays in patient flow and a shortage of hospital beds are commonplace in hospitals during periods of increased infection incidence, such as seasonal influenza and the COVID-19 pandemic. The objective of this study was to develop and evaluate the efficacy of machine learning methods at identifying and ranking the real-time readiness of individual patients for discharge, with the goal of improving patient flow within hospitals during periods of crisis.

METHODS AND PERFORMANCE

Electronic Health Record data from Oxford University Hospitals was used to train independent models to classify and rank patients' real-time readiness for discharge within 24 hours, for patient subsets according to the nature of their admission (planned or emergency) and the number of days elapsed since their admission. A strategy for the use of the models' inference is proposed, by which the model makes predictions for all patients in hospital and ranks them in order of likelihood of discharge within the following 24 hours. The 20% of patients with the highest ranking are considered as candidates for discharge and would therefore expect to have a further screening by a clinician to confirm whether they are ready for discharge or not. Performance was evaluated in terms of positive predictive value (PPV), i.e., the proportion of these patients who would have been correctly deemed as 'ready for discharge' after having the second screening by a clinician. Performance was high for patients on their first day of admission (PPV = 0.96/0.94 for planned/emergency patients respectively) but dropped for patients further into a longer admission (PPV = 0.66/0.71 for planned/emergency patients still in hospital after 7 days).

CONCLUSION

We demonstrate the efficacy of machine learning methods at making operationally focused, next-day discharge readiness predictions for all individual patients in hospital at any given moment and propose a strategy for their use within a decision-support tool during crisis periods.

Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort

Despite the many comorbidities and high mortality rate in preterm infants with patent ductus arteriosus (PDA), therapeutic strategies vary depending on the clinical setting, and most studies of the related risk factors are based on small sample populations. We aimed to compare the performance of artificial intelligence (AI) analysis with that of conventional analysis to identify risk factors associated with symptomatic PDA (sPDA) in very low birth weight infants. This nationwide cohort study included 8369 very low birth weight (VLBW) infants. The participants were divided into an sPDA group and an asymptomatic PDA or spontaneously close PDA (nPDA) group. The sPDA group was further divided into treated and untreated subgroups. A total of 47 perinatal risk factors were collected and analyzed. Multiple logistic regression was used as a standard analytic tool, and five AI algorithms were used to identify the factors associated with sPDA. Combining a large database of risk factors from nationwide registries and AI techniques achieved higher accuracy and better performance of the PDA prediction tasks, and the ensemble methods showed the best performances.

Novel Dynamic Prediction of Daily Patient Discharge in Acute and Critical Care

Determining when a patient can be discharged from a care setting is critical to optimize the utilization and delivery of timely care. Furthermore, timely discharge can lead to better clinical outcomes by effectively mitigating the prolonged length of stay in a care environment. This paper presents a novel algorithm for the prediction of likelihood of patient discharge within the next 24 or 48 hours from acute or critical care environments on a daily basis. Continuous patient monitoring and health data obtained from acute hospital at home environment (n=303 patients) and a critical care unit environment (n=9,520 patients) are retrospectively used to train, validate and test numerous machine learning models for dynamic daily predictions of patients discharge. In the acute hospital at home environment, the area under the receiver operating characteristic (AUROC) curve performance of a top XGBoost model was 0.816 ± 0.025 and 0.758 ± 0.029 for daily discharge prediction within 24 hours and 48 hours respectively. Similar independent prediction models from the critical care environment resulted in relatively a lower AUROC for likewise predicting daily patient discharge. Overall, the results demonstrate the efficacy and utility of our novel algorithm for dynamic predictions of daily patient discharge in both acute- and critical care healthcare settings.

Machine learning in gastrointestinal surgery

Machine learning (ML) is a collection of algorithms allowing computers to learn directly from data without predetermined equations. It is used widely to analyze "big data". In gastrointestinal surgery, surgeons deal with various data such as clinical parameters, surgical videos, and pathological images, to stratify surgical risk, perform safe surgery and predict patient prognosis. In the current "big data" era, the accelerating accumulation of a large amount of data drives studies using ML algorithms. Three subfields of ML are supervised learning, unsupervised learning, and reinforcement learning. In this review, we summarize applications of ML to surgical practice in the preoperative, intraoperative, and postoperative phases of care. Prediction and stratification using ML is promising; however, the current overarching concern is the availability of ML models. Information systems that can manage "big data" and integrate ML models into electronic health records are essential to incorporate ML into daily practice. ML is fundamental technology to meaningfully process data that exceeds the capacity of the human mind to comprehend. The accelerating accumulation of a large amount of data is changing the nature of surgical practice fundamentally. Artificial intelligence (AI), represented by ML, is being incorporated into daily surgical practice.

The application of machine learning algorithms in predicting the length of stay following femoral neck fracture

PURPOSE

Femoral neck fracture is a frequent cause of hospitalization, and length of stay is an important marker of hospital cost and quality of care provided. As an extension of traditional statistical methods, machine learning provides the possibility of accurately predicting the length of hospital stay. The aim of this paper is to retrospectively identify predictive factors of the length of hospital stay (LOS) and predict the postoperative LOS by using machine learning algorithms.

METHOD

Based on the admission and perioperative data of the patients, linear regression was used to analyze the predictive factors of the LOS. Multiple machine learning models were developed, and the performance of different models was compared.

RESULT

Stepwise linear regression showed that preoperative calcium level (P = 0.017) and preoperative lymphocyte percentage (P = 0.007), in addition to intraoperative bleeding (p = 0.041), glucose and sodium chloride infusion after surgery (P = 0.019), Charlson Comorbidity Index (p = 0.007) and BMI (P = 0.031), were significant predictors of LOS. The best performing model was the principal component regression (PCR) with an optimal MAE (1.525) and a proportion of prediction error within 3 days of 90.91%.

CONCLUSION

Excessive intravenous glucose and sodium chloride infusion after surgery, preoperative hypocalcemia, preoperative high percentages of lymphocytes, excessive intraoperative bleeding, lower BMI and higher CCI scores were related to prolonged LOS by using linear regression. Machine learning could accurately predict the postoperative LOS. This information allows hospital administrators to plan reasonable resource allocation to fulfill demand, leading to direct care quality improvement and more reasonable use of scarce resources.

Artificial neural network prediction of same-day discharge following primary total knee arthroplasty based on preoperative and intraoperative variables

AIMS

This study used an artificial neural network (ANN) model to determine the most important pre- and perioperative variables to predict same-day discharge in patients undergoing total knee arthroplasty (TKA).

METHODS

Data for this study were collected from the National Surgery Quality Improvement Program (NSQIP) database from the year 2018. Patients who received a primary, elective, unilateral TKA with a diagnosis of primary osteoarthritis were included. Demographic, preoperative, and intraoperative variables were analyzed. The ANN model was compared to a logistic regression model, which is a conventional machine-learning algorithm. Variables collected from 28,742 patients were analyzed based on their contribution to hospital length of stay.

RESULTS

The predictability of the ANN model, area under the curve (AUC) = 0.801, was similar to the logistic regression model (AUC = 0.796) and identified certain variables as important factors to predict same-day discharge. The ten most important factors favouring same-day discharge in the ANN model include preoperative sodium, preoperative international normalized ratio, BMI, age, anaesthesia type, operating time, dyspnoea status, functional status, race, anaemia status, and chronic obstructive pulmonary disease (COPD). Six of these variables were also found to be significant on logistic regression analysis.

CONCLUSION

Both ANN modelling and logistic regression analysis revealed clinically important factors in predicting patients who can undergo safely undergo same-day discharge from an outpatient TKA. The ANN model provides a beneficial approach to help determine which perioperative factors can predict same-day discharge as of 2018 perioperative recovery protocols. Cite this article: Bone Joint J 2021;103-B(8):1358-1366.

Requirement of artificial intelligence technology awareness for thoracic surgeons

Background

We have recently witnessed incredible interest in computer-based, internet web-dependent mechanisms and artificial intelligence (AI)-dependent technique emergence in our day-to-day lives. In the recent era of COVID-19 pandemic, this nonhuman, machine-based technology has gained a lot of momentum.

Main body of the abstract

The supercomputers and robotics with AI technology have shown the potential to equal or even surpass human experts' accuracy in some tasks in the future. Artificial intelligence (AI) is prompting massive data interweaving with elements from many digital sources such as medical imaging sorting, electronic health records, and transforming healthcare delivery. But in thoracic surgical and our counterpart pulmonary medical field, AI's main applications are still for interpretation of thoracic imaging, lung histopathological slide evaluation, physiological data interpretation, and biosignal testing only. The query arises whether AI-enabled technology-based or autonomous robots could ever do or provide better thoracic surgical procedures than current surgeons but it seems like an impossibility now.

Short conclusion

This review article aims to provide information pertinent to the use of AI to thoracic surgical specialists. In this review article, we described AI and related terminologies, current utilisation, challenges, potential, and current need for awareness of this technology.

Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit

PURPOSE

Due to the increasing demand for intensive care unit (ICU) treatment, and to improve quality and efficiency of care, there is a need for adequate and efficient clinical decision-making. The advancement of artificial intelligence (AI) technologies has resulted in the development of prediction models, which might aid clinical decision-making. This systematic review seeks to give a contemporary overview of the current maturity of AI in the ICU, the research methods behind these studies, and the risk of bias in these studies.

METHODS

A systematic search was conducted in Embase, Medline, Web of Science Core Collection and Cochrane Central Register of Controlled Trials databases to identify eligible studies. Studies using AI to analyze ICU data were considered eligible. Specifically, the study design, study aim, dataset size, level of validation, level of readiness, and the outcomes of clinical trials were extracted. Risk of bias in individual studies was evaluated by the Prediction model Risk Of Bias ASsessment Tool (PROBAST).

RESULTS

Out of 6455 studies identified through literature search, 494 were included. The most common study design was retrospective [476 studies (96.4% of all studies)] followed by prospective observational [8 (1.6%)] and clinical [10 (2%)] trials. 378 (80.9%) retrospective studies were classified as high risk of bias. No studies were identified that reported on the outcome evaluation of an AI model integrated in routine clinical practice.

CONCLUSION

The vast majority of developed ICU-AI models remain within the testing and prototyping environment; only a handful were actually evaluated in clinical practice. A uniform and structured approach can support the development, safe delivery, and implementation of AI to determine clinical benefit in the ICU.

Predicting need for hospital-specific interventional care after surgery using electronic health record data

BACKGROUND

A significant proportion of surgical inpatients is often admitted longer than necessary. Early identification of patients who do not need care that is strictly provided within hospitals would allow timely discharge of patients to a postoperative nursing home for further recovery. We aimed to develop a model to predict whether a patient needs hospital-specific interventional care beyond the second postoperative day.

METHODS

This study included all adult patients discharged from surgical care in the surgical oncology department from June 2017 to February 2020. The primary outcome was to predict whether a patient still needs hospital-specific interventional care beyond the second postoperative day. Hospital-specific care was defined as unplanned reoperations, radiological interventions, and intravenous antibiotics administration. Different analytical methods were compared with respect to the area under the receiver-operating characteristics curve, sensitivity, specificity, positive predictive value, and negative predictive value.

RESULTS

Each model was trained on 1,174 episodes. In total, 847 (50.5%) patients required an intervention during postoperative admission. A random forest model performed best with an area under the receiver-operating characteristics curve of 0.88 (95% confidence interval 0.83-0.93), sensitivity of 79.1% (95% confidence interval 0.67-0.92), specificity of 80.0% (0.73-0.87), positive predictive value of 57.6% (0.45-0.70) and negative predictive value of 91.7% (0.87-0.97).

CONCLUSION

This proof-of-concept study found that a random forest model could successfully predict whether a patient could be safely discharged to a nursing home and does not need hospital care anymore. Such a model could aid hospitals in addressing capacity challenges and improve patient flow, allowing for timely surgical care.

Safe and effective protocol for discharge 3 days after cardiac surgery

The Enhanced Recovery After Surgery (ERAS) protocol affected traditional cardiac surgery processes and COVID-19 is expected to accelerate its scalability. The aim of this study was to assess the impact of an ERAS-based protocol on the length of hospital stay after cardiac surgery. From January 2019 to June 2020, 664 patients underwent consecutive cardiac surgery at a Latin American center. Here, 46 patients were prepared for a rapid recovery through a multidisciplinary institutional protocol based on the ERAS concept, the "TotalCor protocol". After the propensity score matching, 46 patients from the entire population were adjusted for 12 variables. Patients operated on the TotalCor protocol had reduced intensive care unit time (P < 0.025), postoperative stay (P ≤ 0.001) and length of hospital stay (P ≤ 0.001). In addition, there were no significant differences in the occurrence of complications and death between the two groups. Of the 10-central metrics of TotalCor protocol, 6 had > 70% adherences. In conclusion, the TotalCor protocol was safe and effective for a 3-day discharge after cardiac surgery. Postoperative atrial fibrillation and renal failure were predictors of postoperative stay > 5 days.

2021 ISHNE/HRS/EHRA/APHRS collaborative statement on mHealth in Arrhythmia Management: Digital Medical Tools for Heart Rhythm Professionals: From the International Society for Holter and Noninvasive Electrocardiology/Heart Rhythm Society/European Heart Rhythm Association/Asia Pacific Heart Rhythm Society

This collaborative statement from the International Society for Holter and Noninvasive Electrocardiology/Heart Rhythm Society/European Heart Rhythm Association/Asia Pacific Heart Rhythm Society describes the current status of mobile health ("mHealth") technologies in arrhythmia management. The range of digital medical tools and heart rhythm disorders that they may be applied to and clinical decisions that may be enabled are discussed. The facilitation of comorbidity and lifestyle management (increasingly recognized to play a role in heart rhythm disorders) and patient self-management are novel aspects of mHealth. The promises of predictive analytics but also operational challenges in embedding mHealth into routine clinical care are explored.

2021 ISHNE/ HRS/ EHRA/ APHRS collaborative statement on mHealth in Arrhythmia Management: Digital Medical Tools for Heart Rhythm Professionals: From the International Society for Holter and Noninvasive Electrocardiology/Heart Rhythm Society/European Heart Rhythm Association/Asia Pacific Heart Rhythm Society

This collaborative statement from the International Society for Holter and Noninvasive Electrocardiology/ Heart Rhythm Society/ European Heart Rhythm Association/ Asia Pacific Heart Rhythm Society describes the current status of mobile health ("mHealth") technologies in arrhythmia management. The range of digital medical tools and heart rhythm disorders that they may be applied to and clinical decisions that may be enabled are discussed. The facilitation of comorbidity and lifestyle management (increasingly recognized to play a role in heart rhythm disorders) and patient self-management are novel aspects of mHealth. The promises of predictive analytics but also operational challenges in embedding mHealth into routine clinical care are explored.

The Power of Modeling in Emergency Preparedness for COVID-19: A Moonshot Moment for Hospitals

Before coronavirus disease 2019 (COVID-19), few hospitals had fully tested emergency surge plans. Uncertainty in the timing and degree of surge complicates planning efforts, putting hospitals at risk of being overwhelmed. Many lack access to hospital-specific, data-driven projections of future patient demand to guide operational planning. Our hospital experienced one of the largest surges in New England. We developed statistical models to project hospitalizations during the first wave of the pandemic. We describe how we used these models to meet key planning objectives. To build the models successfully, we emphasize the criticality of having a team that combines data scientists with frontline operational and clinical leadership. While modeling was a cornerstone of our response, models currently available to most hospitals are built outside of their institution and are difficult to translate to their environment for operational planning. Creating data-driven, hospital-specific, and operationally relevant surge targets and activation triggers should be a major objective of all health systems.

2021 ISHNE/HRS/EHRA/APHRS Expert Collaborative Statement on mHealth in Arrhythmia Management: Digital Medical Tools for Heart Rhythm Professionals: From the International Society for Holter and Noninvasive Electrocardiology/Heart Rhythm Society/European Heart Rhythm Association/Asia-Pacific Heart Rhythm Society

This collaborative statement from the International Society for Holter and Noninvasive Electrocardiology/Heart Rhythm Society/European Heart Rhythm Association/Asia-Pacific Heart Rhythm Society describes the current status of mobile health technologies in arrhythmia management. The range of digital medical tools and heart rhythm disorders that they may be applied to and clinical decisions that may be enabled are discussed. The facilitation of comorbidity and lifestyle management (increasingly recognized to play a role in heart rhythm disorders) and patient self-management are novel aspects of mobile health. The promises of predictive analytics but also operational challenges in embedding mobile health into routine clinical care are explored.

Machine Learning Models for Predicting Neonatal Mortality: A Systematic Review

INTRODUCTION

Approximately 7,000 newborns die every day, accounting for almost half of child deaths under 5 years of age. Deciphering which neonates are at increased risk for mortality can have an important global impact. As such, integrating high computational technology (e.g., artificial intelligence [AI]) may help identify the early and potentially modifiable predictors of neonatal mortality. Therefore, the objective of this study was to collate, critically appraise, and analyze neonatal prediction studies that included AI.

METHODS

A literature search was performed in PubMed, Cochrane, OVID, and Google Scholar. We included studies that used AI (e.g., machine learning (ML) and deep learning) to formulate prediction models for neonatal death. We excluded small studies (n < 500 individuals) and studies using only antenatal factors to predict mortality. Two independent investigators screened all articles for inclusion. The data collection consisted of study design, number of models, features used per model, feature importance, internal and/or external validation, and calibration analysis. Our primary outcome was the average area under the receiving characteristic curve (AUC) or sensitivity and specificity for all models included in each study.

RESULTS

Of 434 articles, 11 studies were included. The total number of participants was 1.26 M with gestational ages ranging from 22 weeks to term. Number of features ranged from 3 to 66 with timing of prediction as early as 5 min of life to a maximum of 7 days of age. The average number of models per study was 4, with neural network, random forest, and logistic regression comprising the most used models (58.3%). Five studies (45.5%) reported calibration plots and 2 (18.2%) conducted external validation. Eight studies reported results by AUC and 5 studies reported the sensitivity and specificity. The AUC varied from 58.3% to 97.0%. The mean sensitivities ranged from 63% to 80% and specificities from 78% to 99%. The best overall model was linear discriminant analysis, but it also had a high number of features (n = 17).

DISCUSSION/CONCLUSION

ML models can accurately predict death in neonates. This analysis demonstrates the most commonly used predictors and metrics for AI prediction models for neonatal mortality. Future studies should focus on external validation, calibration, as well as deployment of applications that can be readily accessible to health-care providers.

Predicting Length of Stay and Discharge Destination for Surgical Patients: A Cohort Study

Discharge planning is important to prevent surgical site infections, reduce costs, and improve the hospitalization experience. The identification of early variables that can predict a longer-than-expected length of stay or the need for a discharge with additional needs can improve this process. A cohort study was conducted in the largest hospital of Northern Italy, collecting discharge records from January 2017 to January 2020 and pre-admission visits in the last three months. Socio-demographic and clinical data were collected. Linear and logistic regression models were fitted. The main outcomes were the length of stay (LOS) and discharge destination. The main predictors of a longer LOS were the need for additional care at discharge (+10.76 days), hospitalization from the emergency department (ED) (+5.21 days), and age (+0.04 days per year), accounting for clinical variables (p < 0.001 for all variables). Each year of age and hospitalization from the ED were associated with a higher probability of needing additional care at discharge (OR 1.02 and 1.77, respectively, p < 0.001). No additional findings came from pre-admission forms. Discharge difficulties seem to be related mainly to age and hospitalization procedures: those factors are probably masking underlying social risk factors that do not show up in patients with planned admissions.

Getting Unstuck: Challenges and Opportunities in Caring for Patients Experiencing Prolonged Hospitalization While Stable for Discharge

Many physicians care for patients who remain in the hospital for prolonged periods despite being "medically ready" or stable for discharge. However, this phenomenon is not well-defined, and optimal strategies to address the problem are not known. A prolonged hospitalization past the point of medical necessity can harm patients, frustrate care teams, and is costly for the health care system. In this perspective, we describe opportunities to improve value of care for these patients through the lens of the Quadruple Aim, a common framework used to guide health care transformation efforts. We then offer recommendations, including some employed by our hospitals, for clinicians, researchers, and health care systems to improve the care for patients who are "stuck" in the hospital.

Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology

Artificial intelligence (AI) uses data and algorithms to aim to draw conclusions that are as good as, or even better than, those drawn by humans. AI is already part of our daily life; it is behind face recognition technology, speech recognition in virtual assistants (such as Amazon Alexa, Apple's Siri, Google Assistant and Microsoft Cortana) and self-driving cars. AI software has been able to beat world champions in chess, Go and recently even Poker. Relevant to our community, it is a prominent source of innovation in healthcare, already helping to develop new drugs, support clinical decisions and provide quality assurance in radiology. The list of medical image-analysis AI applications with USA Food and Drug Administration or European Union (soon to fall under European Union Medical Device Regulation) approval is growing rapidly and covers diverse clinical needs, such as detection of arrhythmia using a smartwatch or automatic triage of critical imaging studies to the top of the radiologist's worklist. Deep learning, a leading tool of AI, performs particularly well in image pattern recognition and, therefore, can be of great benefit to doctors who rely heavily on images, such as sonologists, radiographers and pathologists. Although obstetric and gynecological ultrasound are two of the most commonly performed imaging studies, AI has had little impact on this field so far. Nevertheless, there is huge potential for AI to assist in repetitive ultrasound tasks, such as automatically identifying good-quality acquisitions and providing instant quality assurance. For this potential to thrive, interdisciplinary communication between AI developers and ultrasound professionals is necessary. In this article, we explore the fundamentals of medical imaging AI, from theory to applicability, and introduce some key terms to medical professionals in the field of ultrasound. We believe that wider knowledge of AI will help accelerate its integration into healthcare. © 2020 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of the International Society of Ultrasound in Obstetrics and Gynecology.

Artificial intelligence in thoracic surgery: past, present, perspective and limits

Artificial intelligence (AI) technology is becoming prevalent in many areas of everyday life. The healthcare industry is concerned by it even though its widespread use is still limited. Thoracic surgeons should be aware of the new opportunities that could affect their daily practice, by direct use of AI technology or indirect use via related medical fields (radiology, pathology and respiratory medicine). The objective of this article is to review applications of AI related to thoracic surgery and discuss the limits of its application in the European Union. Key aspects of AI will be developed through clinical pathways, beginning with diagnostics for lung cancer, a prognostic-aided programme for decision making, then robotic surgery, and finishing with the limitations of AI, the legal and ethical issues relevant to medicine. It is important for physicians and surgeons to have a basic knowledge of AI to understand how it impacts healthcare, and to consider ways in which they may interact with this technology. Indeed, synergy across related medical specialties and synergistic relationships between machines and surgeons will likely accelerate the capabilities of AI in augmenting surgical care.