Predicting Inpatient Length of Stay After Brain Tumor Surgery: Developing Machine Learning Ensembles to Improve Predictive Performance

Early detection of pancreatic cancer by comprehensive serum miRNA sequencing with automated machine learning

BACKGROUND

Pancreatic cancer is often diagnosed at advanced stages, and early-stage diagnosis of pancreatic cancer is difficult because of nonspecific symptoms and lack of available biomarkers.

METHODS

We performed comprehensive serum miRNA sequencing of 212 pancreatic cancer patient samples from 14 hospitals and 213 non-cancerous healthy control samples. We randomly classified the pancreatic cancer and control samples into two cohorts: a training cohort (N = 185) and a validation cohort (N = 240). We created ensemble models that combined automated machine learning with 100 highly expressed miRNAs and their combination with CA19-9 and validated the performance of the models in the independent validation cohort.

RESULTS

The diagnostic model with the combination of the 100 highly expressed miRNAs and CA19-9 could discriminate pancreatic cancer from non-cancer healthy control with high accuracy (area under the curve (AUC), 0.99; sensitivity, 90%; specificity, 98%). We validated high diagnostic accuracy in an independent asymptomatic early-stage (stage 0-I) pancreatic cancer cohort (AUC:0.97; sensitivity, 67%; specificity, 98%).

CONCLUSIONS

We demonstrate that the 100 highly expressed miRNAs and their combination with CA19-9 could be biomarkers for the specific and early detection of pancreatic cancer.

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.

Natural language processing augments comorbidity documentation in neurosurgical inpatient admissions

OBJECTIVE

To establish whether or not a natural language processing technique could identify two common inpatient neurosurgical comorbidities using only text reports of inpatient head imaging.

MATERIALS AND METHODS

A training and testing dataset of reports of 979 CT or MRI scans of the brain for patients admitted to the neurosurgery service of a single hospital in June 2021 or to the Emergency Department between July 1-8, 2021, was identified. A variety of machine learning and deep learning algorithms utilizing natural language processing were trained on the training set (84% of the total cohort) and tested on the remaining images. A subset comparison cohort (n = 76) was then assessed to compare output of the best algorithm against real-life inpatient documentation.

RESULTS

For "brain compression", a random forest classifier outperformed other candidate algorithms with an accuracy of 0.81 and area under the curve of 0.90 in the testing dataset. For "brain edema", a random forest classifier again outperformed other candidate algorithms with an accuracy of 0.92 and AUC of 0.94 in the testing dataset. In the provider comparison dataset, for "brain compression," the random forest algorithm demonstrated better accuracy (0.76 vs 0.70) and sensitivity (0.73 vs 0.43) than provider documentation. For "brain edema," the algorithm again demonstrated better accuracy (0.92 vs 0.84) and AUC (0.45 vs 0.09) than provider documentation.

DISCUSSION

A natural language processing-based machine learning algorithm can reliably and reproducibly identify selected common neurosurgical comorbidities from radiology reports.

CONCLUSION

This result may justify the use of machine learning-based decision support to augment provider documentation.

PSO-XnB: a proposed model for predicting hospital stay of CAD patients

Coronary artery disease poses a significant challenge in decision-making when predicting the length of stay for a hospitalized patient. This study presents a predictive model-a Particle Swarm Optimized-Enhanced NeuroBoost-that combines the deep autoencoder with an eXtreme gradient boosting model optimized using particle swarm optimization. The model uses a fuzzy set of rules to categorize the length of stay into four distinct classes, followed by data preparation and preprocessing. In this study, the dimensionality of the data is reduced using deep neural autoencoders. The reconstructed data obtained from autoencoders is given as input to an eXtreme gradient boosting model. Finally, the model is tuned with particle swarm optimization to obtain optimal hyperparameters. With the proposed technique, the model achieved superior performance with an overall accuracy of 98.8% compared to traditional ensemble models and past research works. The model also scored highest in other metrics such as precision, recall, and particularly F1 scores for all categories of hospital stay. These scores validate the suitability of our proposed model in medical healthcare applications.

Multi-modal learning for inpatient length of stay prediction

Predicting inpatient length of stay (LoS) is important for hospitals aiming to improve service efficiency and enhance management capabilities. Patient medical records are strongly associated with LoS. However, due to diverse modalities, heterogeneity, and complexity of data, it becomes challenging to effectively leverage these heterogeneous data to put forth a predictive model that can accurately predict LoS. To address the challenge, this study aims to establish a novel data-fusion model, termed as DF-Mdl, to integrate heterogeneous clinical data for predicting the LoS of inpatients between hospital discharge and admission. Multi-modal data such as demographic data, clinical notes, laboratory test results, and medical images are utilized in our proposed methodology with individual "basic" sub-models separately applied to each different data modality. Specifically, a convolutional neural network (CNN) model, which we termed CRXMDL, is designed for chest X-ray (CXR) image data, two long short-term memory networks are used to extract features from long text data, and a novel attention-embedded 1D convolutional neural network is developed to extract useful information from numerical data. Finally, these basic models are integrated to form a new data-fusion model (DF-Mdl) for inpatient LoS prediction. The proposed method attains the best R2 and EVAR values of 0.6039 and 0.6042 among competitors for the LoS prediction on the Medical Information Mart for Intensive Care (MIMIC)-IV test dataset. Empirical evidence suggests better performance compared with other state-of-the-art (SOTA) methods, which demonstrates the effectiveness and feasibility of the proposed approach.

Personalized Prognosis with Machine Learning Models for Predicting In-Hospital Outcomes Following Intracranial Meningioma Resections

BACKGROUND

Meningiomas display diverse biological traits and clinical behaviors, complicating patient outcome prediction. This heterogeneity, along with varying prognoses, underscores the need for a precise, personalized evaluation of postoperative outcomes.

METHODS

Data from the American College of Surgeons National Surgical Quality Improvement Program database identified patients who underwent intracranial meningioma resections from 2014 to 2020. We focused on 5 outcomes: prolonged LOS, nonhome discharges, 30-day readmissions, unplanned reoperations, and major complications. Six machine learning algorithms, including TabPFN, TabNet, XGBoost, LightGBM, Random Forest, and Logistic Regression, coupled with the Optuna optimization library for hyperparameter tuning, were tested. Models with the highest area under the receiver operating characteristic (AUROC) values were included in the web application. SHapley Additive exPlanations were used to evaluate the importance of predictor variables.

RESULTS

Our analysis included 7000 patients. Of these patients, 1658 (23.7%) had prolonged LOS, 1266 (18.1%) had nonhome discharges, 573 (8.2%) had 30-day readmission, 253 (3.6%) had unplanned reoperation, and 888 (12.7%) had major complications. Performance evaluation indicated that the top-performing models for each outcome were the models built with LightGBM and Random Forest algorithms. The LightGBM models yielded AUROCs of 0.842 and 0.846 in predicting prolonged LOS and nonhome discharges, respectively. The Random Forest models yielded AUROCs of 0.717, 0.76, and 0.805 in predicting 30-day readmissions, unplanned reoperations, and major complications, respectively.

CONCLUSIONS

The study successfully demonstrated the potential of machine learning models in predicting short-term adverse postoperative outcomes after meningioma resections. This approach represents a significant step forward in personalizing the information provided to meningioma patients.

Application of machine learning models to animal health pharmacovigilance: A proof-of-concept study

Machine learning (ML) models were applied to pharmacovigilance (PV) data in a two-component proof-of-concept study. PV data were partitioned into Training, Validation, and Holdout datasets for model training and selection. During the first component ML models were challenged to identify factors in individual case safety reports (ICSRs) involving spinosad and neurological and ocular clinical signs. The target feature for the models were these clinical signs that were disproportionately reported for spinosad. The endpoints were normalized coefficient values representing the relationship between the target feature and ICSR free text fields. The deployed model accurately identified the risk factors "demodectic," "demodicosis," and "ivomec." In the second component, the ML models were trained to identify high quality and complete ICSRs free of confounders. The deployed model was presented with an external Test dataset of six ICSRs, one that was complete, of high quality, and devoid of confounders, and five that were not. The endpoints were model-generated probabilities for the ICSRs. The deployed ML model accurately identified the ICSR of interest with a greater than 10-fold higher probability score. Although narrow in scope, the study supports further investigation and potential application of ML models to animal health PV data.

Predictive Models Based on Molecular Images and Molecular Descriptors for Drug Screening

Various toxicity and pharmacokinetic evaluations as screening experiments are needed at the drug discovery stage. Currently, to reduce the use of animal experiments and developmental expenses, the development of high-performance predictive models based on quantitative structure-activity relationship analysis is desired. From these evaluation targets, we selected 50% lethal dose (LD50), blood-brain barrier penetration (BBBP), and the clearance (CL) pathway for this investigation and constructed predictive models for each target using 636-11,886 compounds. First, we constructed predictive models using the DeepSnap-deep learning (DL) method and images of compounds as features. The calculated area under the curve (AUC) and balanced accuracy (BAC) were, respectively, 0.887 and 0.818 for LD50, 0.893 and 0.824 for BBBP, and 0.883 and 0.763 for the CL pathway. Next, molecular descriptors (MDs) of compounds were calculated using Molecular Operating Environment, alvaDesc, and ADMET Predictor to construct predictive models using the MD-based method. Using these MDs, we constructed predictive models using DataRobot. The calculated AUC and BAC were, respectively, 0.931 and 0.805 for LD50, 0.919 and 0.849 for BBBP, and 0.900 and 0.807 for the CL pathway. In this investigation, we constructed predictive models combining the DeepSnap-DL and MD-based methods. In ensemble models using the mean predictive probability of the DeepSnap-DL and MD-based methods, the calculated AUC and BAC were, respectively, 0.942 and 0.842 for LD50, 0.936 and 0.853 for BBBP, and 0.908 and 0.832 for the CL pathway, with improved predictive performance observed for all variables compared with either single method alone. Moreover, in consensus models that adopted only compounds for which the results of the two methods agreed, the calculated BAC for LD50, BBBP, and the CL pathway were 0.916, 0.918, and 0.847, respectively, indicating higher predictive performance than the ensemble models for all three variables. The predictive models combining the DeepSnap-DL and MD-based methods displayed high predictive performance for LD50, BBBP, and the CL pathway. Therefore, the application of this approach to prediction targets in various drug discovery screenings is expected to accelerate drug discovery.

Association between preoperative serum sodium and postoperative 30-day mortality in adult patients with tumor craniotomy

BACKGROUND

Limited data exist regarding preoperative serum sodium (Na) and 30-day mortality in adult patients with tumor craniotomy. Therefore, this study investigates their relationship.

METHODS

A secondary retrospective analysis was performed using data from the ACS NSQIP database (2012-2015). The principal exposure was preoperative Na. The outcome measure was 30-day postoperative mortality. Binary logistic regression modeling was conducted to explore the link between them, and a generalized additive model and smooth curve fitting were applied to evaluate the potential association and its explicit curve shape. We also conducted sensitivity analyses and subgroup analyses.

RESULTS

A total of 17,844 patients (47.59% male) were included in our analysis. The mean preoperative Na was 138.63 ± 3.23 mmol/L. The 30-day mortality was 2.54% (455/17,844). After adjusting for covariates, we found that preoperative Na was negative associated with 30-day mortality. (OR = 0.967, 95% CI:0.941, 0.994). For patients with Na ≤ 140, each increase Na was related to a 7.1% decreased 30-day mortality (OR = 0.929, 95% CI:0.898, 0.961); for cases with Na > 140, each increased Na unit was related to a 8.8% increase 30-day mortality (OR = 1.088, 95% CI:1.019, 1.162). The sensitivity analysis and subgroup analysis indicated that the results were robust.

CONCLUSIONS

This study shows a positive and nonlinear association between preoperative Na and postoperative 30-day mortality in adult patients with tumor craniotomy. Appropriate preoperative Na management and maintenance of serum Na near the inflection point (140) may reduce 30-day mortality.

Machine Learning for Benchmarking Critical Care Outcomes

OBJECTIVES

Enhancing critical care efficacy involves evaluating and improving system functioning. Benchmarking, a retrospective comparison of results against standards, aids risk-adjusted assessment and helps healthcare providers identify areas for improvement based on observed and predicted outcomes. The last two decades have seen the development of several models using machine learning (ML) for clinical outcome prediction. ML is a field of artificial intelligence focused on creating algorithms that enable computers to learn from and make predictions or decisions based on data. This narrative review centers on key discoveries and outcomes to aid clinicians and researchers in selecting the optimal methodology for critical care benchmarking using ML.

METHODS

We used PubMed to search the literature from 2003 to 2023 regarding predictive models utilizing ML for mortality (592 articles), length of stay (143 articles), or mechanical ventilation (195 articles). We supplemented the PubMed search with Google Scholar, making sure relevant articles were included. Given the narrative style, papers in the cohort were manually curated for a comprehensive reader perspective.

RESULTS

Our report presents comparative results for benchmarked outcomes and emphasizes advancements in feature types, preprocessing, model selection, and validation. It showcases instances where ML effectively tackled critical care outcome-prediction challenges, including nonlinear relationships, class imbalances, missing data, and documentation variability, leading to enhanced results.

CONCLUSIONS

Although ML has provided novel tools to improve the benchmarking of critical care outcomes, areas that require further research include class imbalance, fairness, improved calibration, generalizability, and long-term validation of published models.

Enhancing length of stay prediction by learning similarity-aware representations for hospitalized patients

This paper focuses on predicting the length of stay for patients on the first day of admission and propose a predictive model named DGLoS. In order to capture the influence of various complex factors on the length of stay as well as the dependencies among various factors, DGLoS uses a deep neural network to model both the patient information and diagnostic information. Targeting at different attribution types, we utilize different coding methods to convert raw data to the input features. Besides, we find that similar patients have closer lengths of stay. Therefore, we further design a module based on graph representation learning to generate patients' similarity-aware representations, capturing the similarity between patients and therefore enhancing predictions. These similarity-aware representations are incorporated into the output of the deep neural network to jointly perform the prediction. We have conducted comprehensive experiments on a real-world hospitalization dataset. The performance comparison shows that our proposed DGLoS model improves predictive performance and the significance test demonstrates the improvement is significant. The ablation study verifies the effectiveness of each of the proposed components and the hyper-parameter investigation shows the robustness of the proposed model.

Developing Predictive Models to Anticipate Shunt Complications in 33,248 Pediatric Patients with Shunted Hydrocephalus Utilizing Machine Learning

INTRODUCTION

Hydrocephalus is a common pediatric neurosurgical pathology, typically treated with a ventricular shunt, yet approximately 30% of patients experience shunt failure within the first year after surgery. As a result, the objective of the present study was to validate a predictive model of pediatric shunt complications with data retrieved from the Healthcare Cost and Utilization Project (HCUP) National Readmissions Database (NRD).

METHODS

The HCUP NRD was queried from 2016 to 2017 for pediatric patients undergoing shunt placement using ICD-10 codes. Comorbidities present upon initial admission resulting in shunt placement, Johns Hopkins Adjusted Clinical Groups (JHACG) frailty-defining criteria, and Major Diagnostic Category (MDC) at admission classifications were obtained. The database was divided into training (n = 19,948), validation (n = 6,650), and testing (n = 6,650) datasets. Multivariable analysis was performed to identify significant predictors of shunt complications which were used to develop logistic regression models. Post hoc receiver operating characteristic (ROC) curves were created.

RESULTS

A total of 33,248 pediatric patients aged 6.9 ± 5.7 years were included. Number of diagnoses during primary admission (OR: 1.05, 95% CI: 1.04-1.07) and initial neurological admission diagnoses (OR: 3.83, 95% CI: 3.33-4.42) positively correlated with shunt complications. Female sex (OR: 0.87, 95% CI: 0.76-0.99) and elective admissions (OR: 0.62, 95% CI: 0.53-0.72) negatively correlated with shunt complications. ROC curve for the regression model utilizing all significant predictors of readmission demonstrated area under the curve of 0.733, suggesting these factors are possible predictors of shunt complications in pediatric hydrocephalus.

CONCLUSION

Efficacious and safe treatment of pediatric hydrocephalus is of paramount importance. Our machine learning algorithm delineated possible variables predictive of shunt complications with good predictive value.

Overinterpretation of findings in machine learning prediction model studies in oncology: a systematic review

OBJECTIVES

In biomedical research, spin is the overinterpretation of findings, and it is a growing concern. To date, the presence of spin has not been evaluated in prognostic model research in oncology, including studies developing and validating models for individualized risk prediction.

STUDY DESIGN AND SETTING

We conducted a systematic review, searching MEDLINE and EMBASE for oncology-related studies that developed and validated a prognostic model using machine learning published between 1st January, 2019, and 5th September, 2019. We used existing spin frameworks and described areas of highly suggestive spin practices.

RESULTS

We included 62 publications (including 152 developed models; 37 validated models). Reporting was inconsistent between methods and the results in 27% of studies due to additional analysis and selective reporting. Thirty-two studies (out of 36 applicable studies) reported comparisons between developed models in their discussion and predominantly used discrimination measures to support their claims (78%). Thirty-five studies (56%) used an overly strong or leading word in their title, abstract, results, discussion, or conclusion.

CONCLUSION

The potential for spin needs to be considered when reading, interpreting, and using studies that developed and validated prognostic models in oncology. Researchers should carefully report their prognostic model research using words that reflect their actual results and strength of evidence.

Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery

Acute kidney injury (AKI) is a common postoperative complication among patients in the neurological intensive care unit (NICU), often resulting in poor prognosis and high mortality. In this retrospective cohort study, we established a model for predicting AKI following brain surgery based on an ensemble machine learning algorithm using data from 582 postoperative patients admitted to the NICU at the Dongyang People's Hospital from March 1, 2017, to January 31, 2020. Demographic, clinical, and intraoperative data were collected. Four machine learning algorithms (C5.0, support vector machine, Bayes, and XGBoost) were used to develop the ensemble algorithm. The AKI incidence in critically ill patients after brain surgery was 20.8%. Intraoperative blood pressure; postoperative oxygenation index; oxygen saturation; and creatinine, albumin, urea, and calcium levels were associated with the postoperative AKI occurrence. The area under the curve value for the ensembled model was 0.85. The accuracy, precision, specificity, recall, and balanced accuracy values were 0.81, 0.86, 0.44, 0.91, and 0.68, respectively, indicating good predictive ability. Ultimately, the models using perioperative variables exhibited good discriminatory ability for early prediction of postoperative AKI risk in patients admitted to the NICU. Thus, the ensemble machine learning algorithm may be a valuable tool for forecasting AKI.

Intraoperative Predictor of Remission in Cushing Disease

BACKGROUND

Cushing disease represents a challenge for neurosurgeons, with high recurrence rates reported. Characteristics associated with remission are incompletely understood; thus, an intraoperative predictor for outcome would be valuable for assessing resection of adrenocorticotropic hormone (ACTH) secreting tissue.

OBJECTIVE

To evaluate whether intraoperative ACTH measurement could predict outcome after surgery for Cushing disease.

METHODS

Retrospective cohort study of 55 consecutive encounters with Cushing disease who had peripheral plasma ACTH levels measured intraoperatively before, during, and after tumor resection. The primary outcome measure was remission, defined by either 2 negative 24-hour urine free cortisol or 2 negative midnight salivary cortisol measurements. A logistic regression machine learning model was generated using recursive feature elimination.

RESULTS

Fifty-five operative encounters, comprising 49 unique patients, had a mean follow-up of 2.73 years (±2.11 years) and a median follow-up of 2.07 years. Remission was achieved in 69.1% (n = 38) of all operations and in 78.0% (n = 32) of those without cavernous sinus invasion. The final ACTH level measured intraoperatively correctly predicted outcome (area under the curve = 0.766; P value = .002). The odds ratio of remission in patients with the lowest quartile vs highest quartile final intraoperative ACTH was 23.4 ( P value = .002). Logistic regression machine learning model resulted in incorporating postoperative day 1 morning cortisol, final intraoperative ACTH that predicted outcome with an average area under the curve of 0.80 ( P = .0027).

CONCLUSION

Intraoperative ACTH may predict outcome after surgery in Cushing disease; furthermore, investigation is warranted.

Artificial Intelligence for Neurosurgery : Current State and Future Directions

Artificial intelligence (AI) is a field of computer science that equips machines with human-like intelligence and enables them to learn, reason, and solve problems when presented with data in various formats. Neurosurgery is often at the forefront of innovative and disruptive technologies, which have similarly altered the course of acute and chronic diseases. In diagnostic imaging, such as X-rays, computed tomography, and magnetic resonance imaging, AI is used to analyze images. The use of robots in the field of neurosurgery is also increasing. In neurointensive care units, AI is used to analyze data and provide care to critically ill patients. Moreover, AI can be used to predict a patient's prognosis. Several AI applications have already been introduced in the field of neurosurgery, and many more are expected in the near future. Ultimately, it is our responsibility to keep pace with this evolution to provide meaningful outcomes and personalize each patient's care. Rather than blindly relying on AI in the future, neurosurgeons should gain a thorough understanding of it and use it to enhance their patient care.

Predictors of extended length of stay related to craniotomy for tumor resection

Background

Hospital length of stay (LOS) related to craniotomy for tumor resection (CTR) is a marker of neurosurgical quality of care. Limiting LOS benefits both patients and hospitals. This study examined which factors contribute to extended LOS (eLOS) at our academic center.

Methods

Retrospective medical record review of 139 consecutive CTRs performed between July 2020 and July 2021. Univariate and multivariable analyses determined which factors were associated with an eLOS (≥8 days).

Results

Median LOS was 6 days (IQR 3-9 days). Fifty-one subjects (36.7%) experienced an eLOS. Upon univariate analysis, potentially modifiable factors associated with eLOS included days to occupational therapy (OT), physical therapy (PT), and case management clearance (p < .001); and discharge disposition (p < .001). Multivariable analysis revealed that pre-operative anti-coagulant use (OR 10.74, 95% CI 2.64-43.63, p = .001), Medicare (OR 4.80, 95% CI 1.07-21.52, p = .04), ED admission (OR 26.21, 95% CI 5.17-132.99, p < .001), transfer to another service post-surgery (OR 30.00, 95% CI 1.56-577.35, p = .02), and time to post-operative imaging (OR 2.91, 95% CI 1.27-6.65, p = .01) were associated with eLOS. Extended LOS was not significantly associated with ED visits (p = .45) or unplanned readmissions within 30 days of surgery (p = .35), and both (p = .04; p = .04) were less likely following a short LOS (<5 days).

Conclusion

While some factors driving LOS related to CTR are uncontrollable, expedient pre- and post-operative management may reduce LOS without compromising care.

Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm

The length of hospital stay (LOS) is a significant indicator of the quality of patient care, hospital efficiency, and operational resilience. Considering the importance of LOS in hospital resource management, this research aims to improve the accuracy of LOS prediction using hyperparameter optimization (HPO). Expert physicians and related studies were reviewed to determine the variables affecting LOS. The electronic medical records of 200 patients in the department of internal medicine of a hospital in Iran were collected randomly. As the performance of machine learning (ML) models can vary based on the characteristics of the features, several models were applied and evaluated in this study. In particular, k-nearest neighbors (KNN), multivariate regression, decision tree (DT), random forest (RF), artificial neural network (ANN), and XGBoost have been evaluated and improved. The genetic algorithm (GA) was applied to optimize the tree-based models. In addition, the dummy coding technique, sometimes called the One-Hot encoding, was used to encode categorical features to increase prediction accuracy. Compared with other algorithms, the XGBoost model optimized by GA (XGB_GA) achieved higher accuracy and better prediction performance. The mean and median of absolute errors in the test dataset for this model were 1.54 and 1.14 days, respectively. In other words, the XGB_GA model reduced the mean absolute error by 37%, which is beneficial in the reliable design of a clinical decision support system.

Association between Preoperative Medication Lists and Postoperative Hospital Length of Stay after Endoscopic Transsphenoidal Pituitary Surgery

Background: Endoscopic transsphenoidal surgery is the most common technique for the resection of pituitary adenoma. Data on factors associated with extended hospital stay after this surgery are limited. We aimed to characterize the relationship between preoperative medications and the risk of prolonged postoperative length of stay after this procedure. Methods: This single-center, retrospective cohort study included all adult patients scheduled for transsphenoidal pituitary surgery from 1 July 2016 to 31 December 2019. Anatomical Therapeutic Chemical codes were used to identify patients’ preoperative medications. The primary outcome was a prolonged postoperative hospital length of stay. Secondary outcomes included unplanned admission to the Intensive Care Unit, and in-hospital and one-year mortality. We developed a descriptive logistic model that included preoperative medications, obesity and age. Results: Median postoperative length of stay was 3 days for the 704 analyzed patients. Patients taking ATC-H drugs were at an increased risk of prolonged length of stay (OR 1.56, 95% CI 1.26−1.95, p < 0.001). No association was found between preoperative ATC-H medication and unplanned ICU admission or in-hospital mortality. Patients with multiple preoperative ATC-H medications had a significantly higher mean LOS (5.4 ± 7.6 days) and one-year mortality (p < 0.02). Conclusions: Clinicians should be aware of the possible vulnerability of patients taking systemic hormones preoperatively. Future studies should test this medication-based approach on endoscopic transsphenoidal pituitary surgery populations from different hospitals and countries.

Time-to-event modeling for hospital length of stay prediction for COVID-19 patients

Providing timely patient care while maintaining optimal resource utilization is one of the central operational challenges hospitals have been facing throughout the pandemic. Hospital length of stay (LOS) is an important indicator of hospital efficiency, quality of patient care, and operational resilience. Numerous researchers have developed regression or classification models to predict LOS. However, conventional models suffer from the lack of capability to make use of typically censored clinical data. We propose to use time-to-event modeling techniques, also known as survival analysis, to predict the LOS for patients based on individualized information collected from multiple sources. The performance of six proposed survival models is evaluated and compared based on clinical data from COVID-19 patients.

Could Machine Learning Better Predict Postoperative C5 Palsy of Cervical Ossification of the Posterior Longitudinal Ligament?

STUDY DESIGN

This was a retrospective cohort study.

OBJECTIVE

The objective of this study was to investigate whether machine learning (ML) can perform better than a conventional logistic regression in predicting postoperative C5 palsy of cervical ossification of the posterior longitudinal ligament (OPLL) patients.

SUMMARY OF BACKGROUND DATA

C5 palsy is one of the most common postoperative complications after surgical treatment of OPLL, with an incidence rate of 1.4%-18.4%. ML has recently been used to predict the outcomes of neurosurgery. To our knowledge there has not been a study to predict postoperative C5 palsy of cervical OPLL patient with ML.

METHODS

Four sampling methods were used for data balancing. Six ML algorithms and conventional logistic regression were used for model development. A total of 35 ML prediction model and 5 conventional logistic prediction models were generated. The performances of each model were compared with the area under the curve (AUC). Patients who underwent surgery for cervical OPLL at our institute from January 1998 to January 2012 were reviewed. Twenty-five variables of each patient were used to make a prediction model.

RESULTS

In total, 901 patients were included [651 male and 250 female, median age: 55 (49-63), mean±SD: 55.9±9.802]. Twenty-six (2.8%) patients developed postoperative C5 palsy. Age (P=0.043), surgical method (P=0.0112), involvement of OPLL at C1-3 (P=0.0359), and postoperative shoulder pain (P≤0.001) were significantly associated with C5 palsy. Among all ML models, a model using an adaptive reinforcement learning algorithm and downsampling showed the largest AUC (0.88; 95% confidence interval: 0.79-0.96), better than that of logistic regression (0.69; 95% confidence interval: 0.43-0.94).

CONCLUSIONS

The ML algorithm seems to be superior to logistic regression for predicting postoperative C5 palsy of OPLL patient after surgery with respect to AUC. Age, surgical method, and involvement of OPLL at C1-C3 were significantly associated with C5 palsy. This study demonstrates that shoulder pain immediately after surgery is closely associated with postoperative C5 palsy of OPLL patient.

Novel QSAR Approach for a Regression Model of Clearance That Combines DeepSnap-Deep Learning and Conventional Machine Learning

The toxicity, absorption, distribution, metabolism, and excretion properties of some targets are difficult to predict by quantitative structure-activity relationship analysis. Therefore, there is a need for a new prediction method that performs well for these targets. The aim of this study was to develop a new regression model of rat clearance (CL). We constructed a regression model using 1545 in-house compounds for which we had rat CL data. Molecular descriptors were calculated using molecular operating environment, alvaDesc, and ADMET Predictor software. The classification model of DeepSnap and Deep Learning (DeepSnap-DL) with images of the three-dimensional chemical structures of compounds as features was constructed, and the prediction probabilities for each compound were calculated. For molecular descriptor-based methods that use molecular descriptors and conventional machine learning algorithms selected by DataRobot, the correlation coefficient (R ²) and root mean square error (RMSE) were 0.625-0.669 and 0.295-0.318, respectively. We combined molecular descriptors and prediction probability of DeepSnap-DL as features and developed a novel regression method we called the combination model. In the combination model with these two types of features and conventional algorithms selected by DataRobot, R ² and RMSE were 0.710-0.769 and 0.247-0.278, respectively. This finding shows that the combination model performed better than molecular descriptor-based methods. Our combination model will contribute to the design of more rational compounds for drug discovery. This method may be applicable not only to rat CL but also to other pharmacokinetic and pharmacological activity and toxicity parameters; therefore, applying it to other parameters may help to accelerate drug discovery.

Methodological conduct of prognostic prediction models developed using machine learning in oncology: a systematic review

BACKGROUND

Describe and evaluate the methodological conduct of prognostic prediction models developed using machine learning methods in oncology.

METHODS

We conducted a systematic review in MEDLINE and Embase between 01/01/2019 and 05/09/2019, for studies developing a prognostic prediction model using machine learning methods in oncology. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement, Prediction model Risk Of Bias ASsessment Tool (PROBAST) and CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) to assess the methodological conduct of included publications. Results were summarised by modelling type: regression-, non-regression-based and ensemble machine learning models.

RESULTS

Sixty-two publications met inclusion criteria developing 152 models across all publications. Forty-two models were regression-based, 71 were non-regression-based and 39 were ensemble models. A median of 647 individuals (IQR: 203 to 4059) and 195 events (IQR: 38 to 1269) were used for model development, and 553 individuals (IQR: 69 to 3069) and 50 events (IQR: 17.5 to 326.5) for model validation. A higher number of events per predictor was used for developing regression-based models (median: 8, IQR: 7.1 to 23.5), compared to alternative machine learning (median: 3.4, IQR: 1.1 to 19.1) and ensemble models (median: 1.7, IQR: 1.1 to 6). Sample size was rarely justified (n = 5/62; 8%). Some or all continuous predictors were categorised before modelling in 24 studies (39%). 46% (n = 24/62) of models reporting predictor selection before modelling used univariable analyses, and common method across all modelling types. Ten out of 24 models for time-to-event outcomes accounted for censoring (42%). A split sample approach was the most popular method for internal validation (n = 25/62, 40%). Calibration was reported in 11 studies. Less than half of models were reported or made available.

CONCLUSIONS

The methodological conduct of machine learning based clinical prediction models is poor. Guidance is urgently needed, with increased awareness and education of minimum prediction modelling standards. Particular focus is needed on sample size estimation, development and validation analysis methods, and ensuring the model is available for independent validation, to improve quality of machine learning based clinical prediction models.

A systematic review of the prediction of hospital length of stay: Towards a unified framework

Hospital length of stay of patients is a crucial factor for the effective planning and management of hospital resources. There is considerable interest in predicting the LoS of patients in order to improve patient care, control hospital costs and increase service efficiency. This paper presents an extensive review of the literature, examining the approaches employed for the prediction of LoS in terms of their merits and shortcomings. In order to address some of these problems, a unified framework is proposed to better generalise the approaches that are being used to predict length of stay. This includes the investigation of the types of routinely collected data used in the problem as well as recommendations to ensure robust and meaningful knowledge modelling. This unified common framework enables the direct comparison of results between length of stay prediction approaches and will ensure that such approaches can be used across several hospital environments. A literature search was conducted in PubMed, Google Scholar and Web of Science from 1970 until 2019 to identify LoS surveys which review the literature. 32 Surveys were identified, from these 32 surveys, 220 papers were manually identified to be relevant to LoS prediction. After removing duplicates, and exploring the reference list of studies included for review, 93 studies remained. Despite the continuing efforts to predict and reduce the LoS of patients, current research in this domain remains ad-hoc; as such, the model tuning and data preprocessing steps are too specific and result in a large proportion of the current prediction mechanisms being restricted to the hospital that they were employed in. Adopting a unified framework for the prediction of LoS could yield a more reliable estimate of the LoS as a unified framework enables the direct comparison of length of stay methods. Additional research is also required to explore novel methods such as fuzzy systems which could build upon the success of current models as well as further exploration of black-box approaches and model interpretability.

The National Inpatient Sample: A Primer for Neurosurgical Big Data Research and Systematic Review

OBJECTIVE

The National Inpatient Sample - the largest all-payer inpatient database in the United States - is an important instrument for big data analysis of neurosurgical inquiries. However, earlier research has determined that many NIS studies are limited by common methodological pitfalls. In this study, we provide the first primer of NIS methodological procedures in the setting of neurosurgical research and review all published neurosurgical studies utilizing the NIS.

METHODS

We designed a protocol for neurosurgical big data research using the NIS, based on the authors' subject matter expertise, NIS documentation, and input and verification from the Healthcare Cost and Utilization Project. We subsequently used a comprehensive search strategy to identify all neurosurgical studies utilizing the NIS in the PubMed and MEDLINE, Embase, and Web of Science databases from inception to August 2021. Studies underwent qualitative categorization (years of the NIS studied, neurosurgical subspecialty, age group, and thematic focus of study objective) and analysis of longitudinal trends.

RESULTS

We identified a canonical, four-step protocol for NIS analysis: study population selection, defining additional clinical variables, identification and coding of outcomes, and statistical analysis. Methodological nuances discussed include identifying neurosurgery-specific admissions, addressing missing data, calculating additional severity and hospital-specific metrics, coding perioperative complications, and applying survey weights to make nationwide estimates. Inherent database limitations and common pitfalls of NIS studies discussed include lack of disease process-specific variables and data following the index admission, inability to calculate certain hospital-specific variables after 2011, performing state-level analyses, conflating hospitalization charges and costs, and not following proper statistical methodology for performing survey-weighted regression. In a systematic review, we identified 647 neurosurgical studies utilizing the NIS. While almost 60% of studies were published after 2015, <10% of studies analyzed NIS data after 2015. The average sample size of studies was 507,352 patients (standard deviation=2,739,900). Most studies analyzed cranial procedures (58.1%) and adults (68.1%). The most prevalent topic areas analyzed were surgical outcome trends (35.7%) and health policy and economics (17.8%), while patient disparities (9.4%) and surgeon or hospital volume (6.6%) were the least studied.

CONCLUSIONS

We present a standardized methodology to analyze the NIS, systematically review the state of the NIS neurosurgical literature, suggest potential future directions for neurosurgical big data inquiries, and outline recommendations to improve the design of future neurosurgical data instruments.

An explainable machine learning framework for lung cancer hospital length of stay prediction

This work introduces a predictive Length of Stay (LOS) framework for lung cancer patients using machine learning (ML) models. The framework proposed to deal with imbalanced datasets for classification-based approaches using electronic healthcare records (EHR). We have utilized supervised ML methods to predict lung cancer inpatients LOS during ICU hospitalization using the MIMIC-III dataset. Random Forest (RF) Model outperformed other models and achieved predicted results during the three framework phases. With clinical significance features selection, over-sampling methods (SMOTE and ADASYN) achieved the highest AUC results (98% with CI 95%: 95.3-100%, and 100% respectively). The combination of Over-sampling and under-sampling achieved the second-highest AUC results (98%, with CI 95%: 95.3-100%, and 97%, CI 95%: 93.7-100% SMOTE-Tomek, and SMOTE-ENN respectively). Under-sampling methods reported the least important AUC results (50%, with CI 95%: 40.2-59.8%) for both (ENN and Tomek- Links). Using ML explainable technique called SHAP, we explained the outcome of the predictive model (RF) with SMOTE class balancing technique to understand the most significant clinical features that contributed to predicting lung cancer LOS with the RF model. Our promising framework allows us to employ ML techniques in-hospital clinical information systems to predict lung cancer admissions into ICU.

Machine Learning in Neuro-Oncology, Epilepsy, Alzheimer's Disease, and Schizophrenia

Applications of machine learning (ML) in translational medicine include therapeutic drug creation, diagnostic development, surgical planning, outcome prediction, and intraoperative assistance. Opportunities in the neurosciences are rich given advancement in our understanding of the brain, expanding indications for intervention, and diagnostic challenges often characterized by multiple clinical and environmental factors. We present a review of ML in neuro-oncology, epilepsy, Alzheimer's disease, and schizophrenia to highlight recent progression in these field, optimizing machine learning capabilities in their current forms. Supervised learning models appear to be the most commonly incorporated algorithm models for machine learning across the reviewed neuroscience disciplines with primary aim of diagnosis. Accuracy ranges are high from 63% to 99% across all algorithms investigated. Machine learning contributions to neurosurgery, neurology, psychiatry, and the clinical and basic science neurosciences may enhance current medical best practices while also broadening our understanding of dynamic neural networks and the brain.

Deployment of Clinical Prediction Models: A Practical Guide to Nomograms and Online Calculators

The use of predictive models within neurosurgery is increasing and many models described in published journal articles are made available to readers in formats such as nomograms and online calculators. The present chapter details a step-by-step methodology with accompanying R code that may be used to implement models both in the form of traditional nomograms and as open-access, online calculators through RStudio's Shinyapps. The chapter assumes a basic understanding of predictive modeling in R and utilizes open-access files created by the Machine Intelligence in Clinical Neuroscience (MICN) Lab (Department of Neurosurgery and the Clinical Neuroscience Center of the University Hospital Zurich). When implemented correctly, tools such as nomograms and predictive calculators have the potential to improve user understanding of the underlying statistical models, facilitate broader adoption, and to streamline the eventual use of such models in clinical settings.

Predicting postoperative transfusion in elective total HIP and knee arthroplasty: Comparison of different machine learning models of a case-control study

BACKGROUND

Total joint arthroplasty (TJA) is a very successful orthopedics procedure but associates with a significantly high transfusion rate.

OBJECTIVE

In this study, we aimed to determine predictors of postoperative blood transfusion in patients undergoing elective hip and knee TJA patients and compare the accuracy of machine learning (ML) algorithms in predicting transfusion risk.

METHODS

We utilized data from 12,642 patients undergoing primary unilateral TJA. Risk factors and demographic information were extracted, and predictive models were developed using seven ML algorithms. The area under the receiver operating characteristic curve was used to measure the predictive accuracy of each algorithm.

RESULTS

The overall transfusion rate was 18.7%. Patient-related risk factors for transfusion included age 65-85 (Odds Ratio (OR): 1.175-1.222), female (OR: 1.246), American Society of Anesthesiologists grade Ⅱ or greater (OR: 1.264-2.758). Surgical factors included operation time (OR: 1.736), drain use (OR: 2.202) as well as intraoperative blood loss (OR: 7.895). Elevated preoperative Hb (OR: 0.615), Hct (OR: 0.800), BMI (≥24 kg/m2) (OR: 0.613-0.731) and tranexamic acid use (OR: 0.375) were associated with decreased risk of postoperative transfusion. The long short-term memory networks (LSTM) and random forest (RF) models achieved the highest predictive accuracy (p < 0.001).

CONCLUSION

The risk factors identified in the current study can provide specific, personalized postoperative transfusion risk assessment for a patient considering lower limb TJA. Furthermore, the predictive accuracies of LSTM and RF algorithms were significantly higher than the others, making them potential tools for future personalized preoperative prediction of risk for postoperative transfusion.

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.

Predicting in-hospital length of stay for very-low-birth-weight preterm infants using machine learning techniques

BACKGROUND/PURPOSE

The in-hospital length of stay (LOS) among very-low-birth-weight (VLBW, BW < 1500 g) infants is an index for care quality and affects medical resource allocation. We aimed to analyze the LOS among VLBW infants in Taiwan, and to develop and compare the performance of different LOS prediction models using machine learning (ML) techniques.

METHODS

This retrospective study illustrated LOS data from VLBW infants born between 2016 and 2018 registered in the Taiwan Neonatal Network. Among infants discharged alive, continuous variables (LOS or postmenstrual age, PMA) and categorical variables (late and non-late discharge group) were used as outcome variables to build prediction models. We used 21 early neonatal variables and six algorithms. The performance was compared using the coefficient of determination (R²) for continuous variables and area under the curve (AUC) for categorical variables.

RESULTS

A total of 3519 VLBW infants were included to illustrate the profile of LOS. We found 59% of mortalities occurred within the first 7 days after birth. The median of LOS among surviving and deceased infants was 62 days and 5 days. For the ML prediction models, 2940 infants were enrolled. Prediction of LOS or PMA had R² values less than 0.6. Among the prediction models for prolonged LOS, the logistic regression (ROC: 0.724) and random forest (ROC: 0.712) approach had better performance.

CONCLUSION

We provide a benchmark of LOS among VLBW infants in each gestational age group in Taiwan. ML technique can improve the accuracy of the prediction model of prolonged LOS of VLBW.

Prediction Model of Clearance by a Novel Quantitative Structure-Activity Relationship Approach, Combination DeepSnap-Deep Learning and Conventional Machine Learning

Some targets predicted by machine learning (ML) in drug discovery remain a challenge because of poor prediction. In this study, a new prediction model was developed and rat clearance (CL) was selected as a target because it is difficult to predict. A classification model was constructed using 1545 in-house compounds with rat CL data. The molecular descriptors calculated by Molecular Operating Environment (MOE), alvaDesc, and ADMET Predictor software were used to construct the prediction model. In conventional ML using 100 descriptors and random forest selected by DataRobot, the area under the curve (AUC) and accuracy (ACC) were 0.883 and 0.825, respectively. Conversely, the prediction model using DeepSnap and Deep Learning (DeepSnap-DL) with compound features as images had AUC and ACC of 0.905 and 0.832, respectively. We combined the two models (conventional ML and DeepSnap-DL) to develop a novel prediction model. Using the ensemble model with the mean of the predicted probabilities from each model improved the evaluation metrics (AUC = 0.943 and ACC = 0.874). In addition, a consensus model using the results of the agreement between classifications had an increased ACC (0.959). These combination models with a high level of predictive performance can be applied to rat CL as well as other pharmacokinetic parameters, pharmacological activity, and toxicity prediction. Therefore, these models will aid in the design of more rational compounds for the development of drugs.

Big data, machine learning, and artificial intelligence: a field guide for neurosurgeons

Big data has transformed into a trend phrase in healthcare and neurosurgery, becoming a pervasive and inescapable phrase in everyday life. The upsurge in big data applications is a direct consequence of the drastic boom in information technology as well as the growing number of internet-connected devices called the Internet of Things in healthcare. Compared with business, marketing, and other sectors, healthcare applications are lagging due to a lack of technical knowledge among healthcare workers, technological limitations in acquiring and analyzing the data, and improper governance of healthcare big data. Despite these limitations, the medical literature is flooded with big data-related articles, and most of these are filled with abstruse terminologies such as machine learning, artificial intelligence, artificial neural network, and algorithm. Many of the recent articles are restricted to neurosurgical registries, creating a false impression that big data is synonymous with registries. Others advocate that the utilization of big data will be the panacea to all healthcare problems and research in the future. Without a proper understanding of these principles, it becomes easy to get lost without the ability to differentiate hype from reality. To that end, the authors give a brief narrative of big data analysis in neurosurgery and review its applications, limitations, and the challenges it presents for neurosurgeons and healthcare professionals naive to this field. Awareness of these basic concepts will allow neurosurgeons to understand the literature regarding big data, enabling them to make better decisions and deliver personalized care.

Machine learning in patient flow: a review

This work is a review of the ways in which machine learning has been used in order to plan, improve or aid the problem of moving patients through healthcare services. We decompose the patient flow problem into four subcategories: prediction of demand on a healthcare institution, prediction of the demand and resource required to transfer patients from the emergency department to the hospital, prediction of potential resource required for the treatment and movement of inpatients and prediction of length-of-stay and discharge timing. We argue that there are benefits to both approaches of considering the healthcare institution as a whole as well as the patient by patient case and that ideally a combination of these would be best for improving patient flow through hospitals. We also argue that it is essential for there to be a shared dataset that will allow researchers to benchmark their algorithms on and thereby allow future researchers to build on that which has already been done. We conclude that machine learning for the improvement of patient flow is still a young field with very few papers tailor-making machine learning methods for the problem being considered. Future works should consider the need to transfer algorithms trained on a dataset to multiple hospitals and allowing for dynamic algorithms which will allow real-time decision-making to help clinical staff on the shop floor.

Pre-operative headaches and obstructive hydrocephalus predict an extended length of stay following suboccipital decompression for pediatric Chiari I malformation

PURPOSE

For young children and adolescents with Chiari malformation type I (CM-I), the determinants of extended length of hospital stay (LOS) after neurosurgical suboccipital decompression are obscure. Here, we investigate the impact of patient- and hospital-level risk factors on extended LOS following surgical decompression for CM-I in young children to adolescents.

METHODS

The Kids' Inpatient Database year 2012 was queried. Pediatric CM-I patients (6-18 years) undergoing surgical decompression were identified. Weighted patient demographics, comorbidities, complications, LOS, disposition, and total cost were recorded. A multivariate logistic regression was used to determine the odds ratio for risk-adjusted LOS. The primary outcome was the degree patient comorbidities or post-operative complications correlated with extended LOS.

RESULTS

A total of 1592 pediatric CM-I patients were identified for which 328 (20.6%) patients had extended LOS (normal LOS, 1264; extended LOS, 328). Age, gender, race, median household income quartile, and healthcare coverage distributions were similar between the two cohorts. Patients with extended LOS had significantly greater admission comorbidities including headache symptoms, nausea and vomiting, obstructive hydrocephalus, lack of coordination, deficiency anemias, and fluid and electrolyte disorders. On multivariate logistic regression, several risk factors were associated with extended LOS, including headache symptoms, obstructive hydrocephalus, and fluid and electrolyte disorders.

CONCLUSIONS

Our study using the Kids' Inpatient Database demonstrates that presenting symptoms and signs, including headaches and obstructive hydrocephalus, respectively, are significantly associated with extended LOS following decompression for pediatric CM-I.

Machine learning models to predict length of stay and discharge destination in complex head and neck surgery

BACKGROUND

This study develops machine learning (ML) algorithms that use preoperative-only features to predict discharge-to-nonhome-facility (DNHF) and length-of-stay (LOS) following complex head and neck surgeries.

METHODS

Patients undergoing laryngectomy or composite tissue excision followed by free tissue transfer were extracted from the 2005 to 2017 NSQIP database.

RESULTS

Among the 2786 included patients, DNHF and mean LOS were 421 (15.1%) and 11.7 ± 8.8 days. Four classification models for predicting DNHF with high specificities (range, 0.80-0.84) were developed. The generalized linear and gradient boosting machine models performed best with receiver operating characteristic (ROC), accuracy, and negative predictive value (NPV) of 0.72-0.73, 0.75-0.76, and 0.88-0.89. Four regression models for predicting LOS in days were developed, where all performed similarly with mean absolute error and root mean-squared errors of 3.95-3.98 and 5.14-5.16. Both models were developed into an encrypted web-based interface: https://uci-ent.shinyapps.io/head-neck/.

CONCLUSION

Novel and proof-of-concept ML models to predict DNHF and LOS were developed and published as web-based interfaces.

Artificial intelligence for brain diseases: A systematic review

Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.

Prediction of general medical admission length of stay with natural language processing and deep learning: a pilot study

Length of stay (LOS) and discharge destination predictions are key parts of the discharge planning process for general medical hospital inpatients. It is possible that machine learning, using natural language processing, may be able to assist with accurate LOS and discharge destination prediction for this patient group. Emergency department triage and doctor notes were retrospectively collected on consecutive general medical and acute medical unit admissions to a single tertiary hospital from a 2-month period in 2019. These data were used to assess the feasibility of predicting LOS and discharge destination using natural language processing and a variety of machine learning models. 313 patients were included in the study. The artificial neural network achieved the highest accuracy on the primary outcome of predicting whether a patient would remain in hospital for > 2 days (accuracy 0.82, area under the received operator curve 0.75, sensitivity 0.47 and specificity 0.97). When predicting LOS as an exact number of days, the artificial neural network achieved a mean absolute error of 2.9 and a mean squared error of 16.8 on the test set. For the prediction of home as a discharge destination (vs any non-home alternative), all models performed similarly with an accuracy of approximately 0.74. This study supports the feasibility of using natural language processing to predict general medical inpatient LOS and discharge destination. Further research is indicated with larger, more detailed, datasets from multiple centres to optimise and examine the accuracy that may be achieved with such predictions.

Machine Learning Classification of Cerebral Aneurysm Rupture Status with Morphologic Variables and Hemodynamic Parameters

Purpose

To construct a classification model of rupture status and to clarify the importance of morphologic variables and hemodynamic parameters on rupture status by applying a machine learning (ML) algorithm to morphologic and hemodynamic data of cerebral aneurysms.

Materials and Methods

Between 2011 and 2019, 226 (112 ruptured and 114 unruptured) cerebral aneurysms in 188 consecutive patients were retrospectively analyzed with computational fluid dynamics (CFD). A random forest ML algorithm was applied to the results to create three classification models consisting of only morphologic variables (model 1), only hemodynamic parameters (model 2), and both morphologic variables and hemodynamic parameters (model 3). The accuracy of rupture status classification and the importance of each variable or parameter in the models were computed.

Results

The accuracy was 77.0% in model 1, 71.2% in model 2, and 78.3% in model 3. The three most important features were projection ratio, size ratio, and aspect ratio in model 1; low shear area ratio, oscillatory shear index, and oscillatory velocity index in model 2; and projection ratio, irregular shape, and size ratio in model 3.

Conclusion

Classification models of rupture status of cerebral aneurysms were constructed by applying an ML algorithm to morphologic variables and hemodynamic parameters. The model worked with relatively high accuracy, in which projection ratio, irregular shape, and size ratio were important for the discrimination of ruptured aneurysms.Supplemental material is available for this article.© RSNA, 2020.

Big Data Defined: A Practical Review for Neurosurgeons

BACKGROUND

Modern science and healthcare generate vast amounts of data, and, coupled with the increasingly inexpensive and accessible computing, a tremendous opportunity exists to use these data to improve care. A better understanding of data science and its relationship to neurosurgical practice will be increasingly important as we transition into this modern "big data" era.

METHODS

A review of the literature was performed for key articles referencing big data for neurosurgical care or related topics.

RESULTS

In the present report, we first defined the nature and scope of data science from a technical perspective. We then discussed its relationship to the modern neurosurgical practice, highlighting key references, which might form a useful introductory reading list.

CONCLUSIONS

Numerous challenges exist going forward; however, organized neurosurgery has an important role in fostering and facilitating these efforts to merge data science with neurosurgical practice.

Machine Learning Analysis of Matricellular Proteins and Clinical Variables for Early Prediction of Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage

Although delayed cerebral ischemia (DCI) is a well-known complication after subarachnoid hemorrhage (SAH), there are no reliable biomarkers to predict DCI development. Matricellular proteins (MCPs) have been reported relevant to DCI and expected to become biomarkers. As machine learning (ML) enables the classification of various input data and the result prediction, the aim of this study was to construct early prediction models of DCI development with clinical variables and MCPs using ML analyses. Early-stage clinical data of 95 SAH patients in a prospective cohort were analyzed and applied to a ML algorithm, random forest, to construct three prediction models: (1) a model with only clinical variables on admission, (2) a model with only plasma levels of MCP (periostin, osteopontin, and galectin-3) at post-onset days 1-3, and (3) a model with both clinical variables on admission and MCP values at days 1-3. The prediction accuracy of the development of DCI, angiographic vasospasm, or cerebral infarction and the importance of each feature were computed. The prediction accuracy of DCI development was 93.9% in model 1, 87.2% in model 2, and 95.1% in model 3, but that of angiographic vasospasm or cerebral infarction was lower. The three most important features in model 3 for DCI were periostin, osteopontin, and galectin-3, followed by aneurysm location. All of the early-stage prediction models of DCI development constructed by ML worked with high accuracy and sensitivity. One-time early-stage measurement of plasma MCPs served for reliable prediction of DCI development, suggesting their potential utility as biomarkers.

Decision Support Software for Forecasting Patient’s Length of Stay

Length of stay of hospitalized patients is generally considered to be a significant and critical factor for healthcare policy planning which consequently affects the hospital management plan and resources. Its reliable prediction in the preadmission stage could further assist in identifying abnormality or potential medical risks to trigger additional attention for individual cases. Recently, data mining and machine learning constitute significant tools in the healthcare domain. In this work, we introduce a new decision support software for the accurate prediction of hospitalized patients’ length of stay which incorporates a novel two-level classification algorithm. Our numerical experiments indicate that the proposed algorithm exhibits better classification performance than any examined single learning algorithm. The proposed software was developed to provide assistance to the hospital management and strengthen the service system by offering customized assistance according to patients’ predicted hospitalization time.