Dynamic multi-outcome prediction after injury: Applying adaptive machine learning for precision medicine in trauma

Machine Learning-Based Predictive Models for Patients with Venous Thromboembolism: A Systematic Review

BACKGROUND

 Venous thromboembolism (VTE) is a chronic disorder with a significant health and economic burden. Several VTE-specific clinical prediction models (CPMs) have been used to assist physicians in decision-making but have several limitations. This systematic review explores if machine learning (ML) can enhance CPMs by analyzing extensive patient data derived from electronic health records. We aimed to explore ML-CPMs' applications in VTE for risk stratification, outcome prediction, diagnosis, and treatment.

METHODS

 Three databases were searched: PubMed, Google Scholar, and IEEE electronic library. Inclusion criteria focused on studies using structured data, excluding non-English publications, studies on non-humans, and certain data types such as natural language processing and image processing. Studies involving pregnant women, cancer patients, and children were also excluded. After excluding irrelevant studies, a total of 77 studies were included.

RESULTS

 Most studies report that ML-CPMs outperformed traditional CPMs in terms of receiver operating area under the curve in the four clinical domains that were explored. However, the majority of the studies were retrospective, monocentric, and lacked detailed model architecture description and external validation, which are essential for quality audit. This review identified research gaps and highlighted challenges related to standardized reporting, reproducibility, and model comparison.

CONCLUSION

 ML-CPMs show promise in improving risk assessment and individualized treatment recommendations in VTE. Apparently, there is an urgent need for standardized reporting and methodology for ML models, external validation, prospective and real-world data studies, as well as interventional studies to evaluate the impact of artificial intelligence in VTE.

Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma

Purpose

Earlier research has identified several potentially predictive features including biomarkers associated with trauma, which can be used to assess the risk for harmful outcomes of polytraumatized patients. These features encompass various aspects such as the nature and severity of the injury, accompanying health conditions, immune and inflammatory markers, and blood parameters linked to organ functioning, however their applicability is limited. Numerous indicators relevant to the patients` outcome are routinely gathered in the intensive care unit (ICU) and recorded in electronic medical records, rendering them suitable predictors for risk assessment of polytraumatized patients.

Methods

317 polytraumatized patients were included, and the influence of 29 clinical and biological features on the complication patterns for systemic inflammatory response syndrome (SIRS), pneumonia and sepsis were analyzed with a machine learning workflow including clustering, classification and explainability using SHapley Additive exPlanations (SHAP) values. The predictive ability of the analyzed features within three days after admission to the hospital were compared based on patient-specific outcomes using receiver-operating characteristics.

Results

A correlation and clustering analysis revealed that distinct patterns of injury and biomarker patterns were observed for the major complication classes. A k-means clustering suggested four different clusters based on the major complications SIRS, pneumonia and sepsis as well as a patient subgroup that developed no complications. For classification of the outcome groups with no complications, pneumonia and sepsis based on boosting ensemble classification, 90% were correctly classified as low-risk group (no complications). For the high-risk groups associated with development of pneumonia and sepsis, 80% of the patients were correctly identified. The explainability analysis with SHAP values identified the top-ranking features that had the largest impact on the development of adverse outcome patterns. For both investigated risk scenarios (infectious complications and long ICU stay) the most important features are SOFA score, Glasgow Coma Scale, lactate, GGT and hemoglobin blood concentration.

Conclusion

The machine learning-based identification of prognostic feature patterns in patients with traumatic injuries may improve tailoring personalized treatment modalities to mitigate the adverse outcomes in high-risk patient clusters.

Comparison of Machine Learning Methods in the Study of Cancer Survivors' Return to Work: An Example of Breast Cancer Survivors with Work-Related Factors in the CONSTANCES Cohort

PURPOSE

Machine learning (ML) methods showed a higher accuracy in identifying individuals without cancer who were unable to return to work (RTW) compared to the classical methods (e.g. logistic regression models). We therefore aim to discuss the value of these methods in relation to RTW for cancer survivors.

METHODS

Breast cancer (BC) survivors who were working at diagnosis within the CONSTANCES cohort were included in the study. RTW was assessed five years after the BC diagnosis (early retirement was considered as non-RTW). Age and occupation at diagnosis, and physical occupational job exposures assessed using the Job Exposure Matrix, JEM-CONSTANCES, were evaluated as predictors of RTW five years after BC diagnosis. The following four ML methods were used: (i) k-nearest neighbors; (ii) random forest; (iii) neural network; and (iv) elastic net.

RESULTS

The training sample included 683 BC survivors (RTW: 85.7%), and the test sample 171 (RTW: 85.4%). The elastic net method had the best results despite low sensitivity (accuracy = 76.6%; sensitivity = 31.7%; specificity = 90.8%), and the random forest model was the most accurate (= 79.5%) but also the least sensitive (= 14.3%).

CONCLUSION

This study takes a first step towards opening up new possibilities for identifying the occupational determinants of cancer survivors' RTW. Further work, including a larger sample size, and more predictor variables, is now needed.

Artificial intelligence assistance in deciding management strategies for polytrauma and trauma patients

<b><br>Introduction:</b> Artificial intelligence (AI) is an emerging technology with vast potential for use in several fields of medicine. However, little is known about the application of AI in treatment decisions for patients with polytrauma. In this systematic review, we investigated the benefits and performance of AI in predicting the management of patients with polytrauma and trauma.</br> <b><br>Methods:</b> This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies were extracted from the PubMed and Google Scholar databases from their inception until November 2022, using the search terms "Artificial intelligence," "polytrauma," and "decision." Seventeen articles were identified and screened for eligibility. Animal studies, review articles, systematic reviews, meta-analyses, and studies that did not involve polytrauma or severe trauma management decisions were excluded. Eight studies were eligible for final review.</br> <b><br>Results:</b> Eight studies focusing on patients with trauma, including two on military trauma, were included. The AI applications were mainly implemented for predictions and/or decisions on shock, bleeding, and blood transfusion. Few studies predicted death/survival. The identification of trauma patients using AI was proposed in a previous study. The overall performance of AI was good (six studies), excellent (one study), and acceptable (one study).</br> <b><br>Discussion:</b> AI demonstrated satisfactory performance in decision-making and management prediction in patients with polytrauma/severe trauma, especially in situations of shock/bleeding.</br> <b><br>Importance:</b> The present study serves as a basis for further research to develop practical AI applications for the management of patients with trauma.</br>.

Exploring alternative approaches to precision medicine through genomics and artificial intelligence - a systematic review

The core idea behind precision medicine is to pinpoint the subpopulations that differ from one another in terms of disease risk, drug responsiveness, and treatment outcomes due to differences in biology and other traits. Biomarkers are found through genomic sequencing. Multi-dimensional clinical and biological data are created using these biomarkers. Better analytic methods are needed for these multidimensional data, which can be accomplished by using artificial intelligence (AI). An updated review of 80 latest original publications is presented on four main fronts-preventive medicine, medication development, treatment outcomes, and diagnostic medicine-All these studies effectively illustrated the significance of AI in precision medicine. Artificial intelligence (AI) has revolutionized precision medicine by swiftly analyzing vast amounts of data to provide tailored treatments and predictive diagnostics. Through machine learning algorithms and high-resolution imaging, AI assists in precise diagnoses and early disease detection. AI's ability to decode complex biological factors aids in identifying novel therapeutic targets, allowing personalized interventions and optimizing treatment outcomes. Furthermore, AI accelerates drug discovery by navigating chemical structures and predicting drug-target interactions, expediting the development of life-saving medications. With its unrivaled capacity to comprehend and interpret data, AI stands as an invaluable tool in the pursuit of enhanced patient care and improved health outcomes. It's evident that AI can open a new horizon for precision medicine by translating complex data into actionable information. To get better results in this regard and to fully exploit the great potential of AI, further research is required on this pressing subject.

Trans-Omics analysis of post injury thrombo-inflammation identifies endotypes and trajectories in trauma patients

Understanding and managing the complexity of trauma-induced thrombo-inflammation necessitates an innovative, data-driven approach. This study leveraged a trans-omics analysis of longitudinal samples from trauma patients to illuminate molecular endotypes and trajectories that underpin patient outcomes, transcending traditional demographic and physiological characterizations. We hypothesize that trans-omics profiling reveals underlying clinical differences in severely injured patients that may present with similar clinical characteristics but ultimately have very different responses to treatment and clinical outcomes. Here we used proteomics and metabolomics to profile 759 of longitudinal plasma samples from 118 patients at 11 time points and 97 control subjects. Results were used to define distinct patient states through data reduction techniques. The patient groups were stratified based on their shock severity and injury severity score, revealing a spectrum of responses to trauma and treatment that are fundamentally tied to their unique underlying biology. Ensemble models were then employed, demonstrating the predictive power of these molecular signatures with area under the receiver operating curves of 80 to 94% for key outcomes such as INR, ICU-free days, ventilator-free days, acute lung injury, massive transfusion, and death. The molecularly defined endotypes and trajectories provide an unprecedented lens to understand and potentially guide trauma patient management, opening a path towards precision medicine. This strategy presents a transformative framework that aligns with our understanding that trauma patients, despite similar clinical presentations, might harbor vastly different biological responses and outcomes.

Adaptive Bayesian learning for making risk-aware decisions: A case of trauma survival prediction

Decision tree (DT) models provide a transparent approach to prediction of patient's outcomes within a probabilistic framework. Averaging over DT models under certain conditions can deliver reliable estimates of predictive posterior probability distributions, which is of critical importance in the case of predicting an individual patient's outcome. Reliable estimations of the distribution can be achieved within the Bayesian framework using Markov chain Monte Carlo (MCMC) and its Reversible Jump extension enabling DT models to grow to a reasonable size. Existing MCMC strategies however have limited ability to control DT structures and tend to sample overgrown DT models, making unreasonably small partitions, thus deteriorating the uncertainty calibration. This happens because the MCMC explores a DT model parameter space within a limited knowledge of the distribution of data partitions. We propose a new adaptive strategy which overcomes this limitation, and show that in the case of predicting trauma outcomes the number of data partitions can be significantly reduced, so that the unnecessary uncertainty of estimating the predictive posterior density is avoided. The proposed and existing strategies are compared in terms of entropy which, being calculated for predicted posterior distributions, represents the uncertainty in decisions. In this framework, the proposed method has outperformed the existing sampling strategies, so that the unnecessary uncertainty in decisions is efficiently avoided.

Assessing the utility of a sliding-windows deep neural network approach for risk prediction of trauma patients

The risks of post trauma complications are regulated by the injury, comorbidities, and the clinical trajectories, yet prediction models are often limited to single time-point data. We hypothesize that deep learning prediction models can be used for risk prediction using additive data after trauma using a sliding windows approach. Using the American College of Surgeons Trauma Quality Improvement Program (ACS TQIP) database, we developed three deep neural network models, for sliding-windows risk prediction. Output variables included early- and late mortality and any of 17 complications. As patients moved through the treatment trajectories, performance metrics increased. Models predicted early- and late mortality with ROC AUCs ranging from 0.980 to 0.994 and 0.910 to 0.972, respectively. For the remaining 17 complications, the mean performance ranged from 0.829 to 0.912. In summary, the deep neural networks achieved excellent performance in the sliding windows risk stratification of trauma patients.

Science fiction or clinical reality: a review of the applications of artificial intelligence along the continuum of trauma care

Artificial intelligence (AI) and machine learning describe a broad range of algorithm types that can be trained based on datasets to make predictions. The increasing sophistication of AI has created new opportunities to apply these algorithms within within trauma care. Our paper overviews the current uses of AI along the continuum of trauma care, including injury prediction, triage, emergency department volume, assessment, and outcomes. Starting at the point of injury, algorithms are being used to predict severity of motor vehicle crashes, which can help inform emergency responses. Once on the scene, AI can be used to help emergency services triage patients remotely in order to inform transfer location and urgency. For the receiving hospital, these tools can be used to predict trauma volumes in the emergency department to help allocate appropriate staffing. After patient arrival to hospital, these algorithms not only can help to predict injury severity, which can inform decision-making, but also predict patient outcomes to help trauma teams anticipate patient trajectory. Overall, these tools have the capability to transform trauma care. AI is still nascent within the trauma surgery sphere, but this body of the literature shows that this technology has vast potential. AI-based predictive tools in trauma need to be explored further through prospective trials and clinical validation of algorithms.

Artificial intelligence and machine learning for hemorrhagic trauma care

Artificial intelligence (AI), a branch of machine learning (ML) has been increasingly employed in the research of trauma in various aspects. Hemorrhage is the most common cause of trauma-related death. To better elucidate the current role of AI and contribute to future development of ML in trauma care, we conducted a review focused on the use of ML in the diagnosis or treatment strategy of traumatic hemorrhage. A literature search was carried out on PubMed and Google scholar. Titles and abstracts were screened and, if deemed appropriate, the full articles were reviewed. We included 89 studies in the review. These studies could be grouped into five areas: (1) prediction of outcomes; (2) risk assessment and injury severity for triage; (3) prediction of transfusions; (4) detection of hemorrhage; and (5) prediction of coagulopathy. Performance analysis of ML in comparison with current standards for trauma care showed that most studies demonstrated the benefits of ML models. However, most studies were retrospective, focused on prediction of mortality, and development of patient outcome scoring systems. Few studies performed model assessment via test datasets obtained from different sources. Prediction models for transfusions and coagulopathy have been developed, but none is in widespread use. AI-enabled ML-driven technology is becoming integral part of the whole course of trauma care. Comparison and application of ML algorithms using different datasets from initial training, testing and validation in prospective and randomized controlled trials are warranted for provision of decision support for individualized patient care as far forward as possible.

Using machine learning on clinical data to identify unexpected patterns in groups of COVID-19 patients

As clinicians are faced with a deluge of clinical data, data science can play an important role in highlighting key features driving patient outcomes, aiding in the development of new clinical hypotheses. Insight derived from machine learning can serve as a clinical support tool by connecting care providers with reliable results from big data analysis that identify previously undetected clinical patterns. In this work, we show an example of collaboration between clinicians and data scientists during the COVID-19 pandemic, identifying sub-groups of COVID-19 patients with unanticipated outcomes or who are high-risk for severe disease or death. We apply a random forest classifier model to predict adverse patient outcomes early in the disease course, and we connect our classification results to unsupervised clustering of patient features that may underpin patient risk. The paradigm for using data science for hypothesis generation and clinical decision support, as well as our triaged classification approach and unsupervised clustering methods to determine patient cohorts, are applicable to driving rapid hypothesis generation and iteration in a variety of clinical challenges, including future public health crises.

Clustering of trauma patients based on longitudinal data and the application of machine learning to predict recovery

Predicting recovery after trauma is important to provide patients a perspective on their estimated future health, to engage in shared decision making and target interventions to relevant patient groups. In the present study, several unsupervised techniques are employed to cluster patients based on longitudinal recovery profiles. Subsequently, these data-driven clusters were assessed on clinical validity by experts and used as targets in supervised machine learning models. We present a formalised analysis of the obtained clusters that incorporates evaluation of (i) statistical and machine learning metrics, (ii) clusters clinical validity with descriptive statistics and medical expertise. Clusters quality assessment revealed that clusters obtained through a Bayesian method (High Dimensional Supervised Classification and Clustering) and a Deep Gaussian Mixture model, in combination with oversampling and a Random Forest for supervised learning of the cluster assignments provided among the most clinically sensible partitioning of patients. Other methods that obtained higher classification accuracy suffered from cluster solutions with large majority classes or clinically less sensible classes. Models that used just physical or a mix of physical and psychological outcomes proved to be among the most sensible, suggesting that clustering on psychological outcomes alone yields recovery profiles that do not conform to known risk factors.

Decision support by machine learning systems for acute management of severely injured patients: A systematic review

Introduction

Treating severely injured patients requires numerous critical decisions within short intervals in a highly complex situation. The coordination of a trauma team in this setting has been shown to be associated with multiple procedural errors, even of experienced care teams. Machine learning (ML) is an approach that estimates outcomes based on past experiences and data patterns using a computer-generated algorithm. This systematic review aimed to summarize the existing literature on the value of ML for the initial management of severely injured patients.

Methods

We conducted a systematic review of the literature with the goal of finding all articles describing the use of ML systems in the context of acute management of severely injured patients. MESH search of Pubmed/Medline and Web of Science was conducted. Studies including fewer than 10 patients were excluded. Studies were divided into the following main prediction groups: (1) injury pattern, (2) hemorrhage/need for transfusion, (3) emergency intervention, (4) ICU/length of hospital stay, and (5) mortality.

Results

Thirty-six articles met the inclusion criteria; among these were two prospective and thirty-four retrospective case series. Publication dates ranged from 2000 to 2020 and included 32 different first authors. A total of 18,586,929 patients were included in the prediction models. Mortality was the most represented main prediction group (n = 19). ML models used were artificial neural network ( n = 15), singular vector machine (n = 3), Bayesian network (n = 7), random forest (n = 6), natural language processing (n = 2), stacked ensemble classifier [SuperLearner (SL), n = 3], k-nearest neighbor (n = 1), belief system (n = 1), and sequential minimal optimization (n = 2) models. Thirty articles assessed results as positive, five showed moderate results, and one article described negative results to their implementation of the respective prediction model.

Conclusions

While the majority of articles show a generally positive result with high accuracy and precision, there are several requirements that need to be met to make the implementation of such models in daily clinical work possible. Furthermore, experience in dealing with on-site implementation and more clinical trials are necessary before the implementation of ML techniques in clinical care can become a reality.

Prediction of Prognosis in Patients with Trauma by Using Machine Learning

Background and Objectives: We developed a machine learning algorithm to analyze trauma-related data and predict the mortality and chronic care needs of patients with trauma. Materials and Methods: We recruited admitted patients with trauma during 2015 and 2016 and collected their clinical data. Then, we subjected this database to different machine learning techniques and chose the one with the highest accuracy by using cross-validation. The primary endpoint was mortality, and the secondary endpoint was requirement for chronic care. Results: Data of 5871 patients were collected. We then used the eXtreme Gradient Boosting (xGBT) machine learning model to create two algorithms: a complete model and a short-term model. The complete model exhibited an 86% recall for recovery, 30% for chronic care, 67% for mortality, and 80% for complications; the short-term model fitted for ED displayed an 89% recall for recovery, 25% for chronic care, and 41% for mortality. Conclusions: We developed a machine learning algorithm that displayed good recall for the healthy recovery group but unsatisfactory results for those requiring chronic care or having a risk of mortality. The prediction power of this algorithm may be improved by implementing features such as age group classification, severity selection, and score calibration of trauma-related variables.

Machine Learning in the Prediction of Trauma Outcomes: A Systematic Review

STUDY OBJECTIVE

Machine learning models carry unique potential as decision-making aids and prediction tools for improving patient care. Traumatically injured patients provide a uniquely heterogeneous population with severe injuries that can be difficult to predict. Given the relative infancy of machine learning applications in medicine, this systematic review aimed to better understand the current state of machine learning development and implementation to help create a basis for future research.

METHODS

We conducted a systematic review from inception to May 2021, using Embase, MEDLINE through Ovid, Web of Science, Google Scholar, and relevant gray literature, for uses of machine learning in predicting the outcomes of trauma patients. The screening and data extraction were performed by 2 independent reviewers.

RESULTS

Of the 14,694 identified articles screened, 67 were included for data extraction. Artificial neural networks comprised the most commonly used model, and mortality was the most prevalent outcome of interest. In terms of machine learning model development, there was a lack of studies that employed external validation, feature selection methods, and performed formal calibration testing. Significant heterogeneity in reporting was also observed between the machine learning models employed, patient populations, performance metrics, and features employed.

CONCLUSION

This review highlights the heterogeneity in the development and reporting of machine learning models for the prediction of trauma outcomes. While these models present an area of opportunity as an ancillary to clinical decision-making, we recommend more standardization and rigorous guidelines for the development of future models.

Predicting outcomes after trauma: Prognostic model development based on admission features through machine learning

In an overcrowded emergency department (ED), trauma surgeons and emergency physicians need an accurate prognostic predictor for critical decision-making involving patients with severe trauma. We aimed to develope a machine learning-based early prognostic model based on admission features and initial ED management.We only recruited patients with severe trauma (defined as an injury severity score >15) as the study cohort and excluded children (defined as patients <16 years old) from a 4-years database (Chi-Mei Medical Center, from January 2015, to December 2018) recording the clinical features of all admitted trauma patients. We considered only patient features that could be determined within the first 2 hours after arrival to the ED. These variables included Glasgow Coma Scale (GCS) score; heart rate; respiratory rate; mean arterial pressure (MAP); prehospital cardiac arrest; abbreviated injury scales (AIS) of head and neck, thorax, and abdomen; and ED interventions (tracheal intubation/tracheostomy, blood product transfusion, thoracostomy, and cardiopulmonary resuscitation). The endpoint for prognostic analyses was mortality within 7 days of admission.We divided the study cohort into the early death group (149 patients who died within 7 days of admission) and non-early death group (2083 patients who survived at >7 days of admission). The extreme Gradient Boosting (XGBoost) machine learning model provided mortality prediction with higher accuracy (94.0%), higher sensitivity (98.0%), moderate specificity (54.8%), higher positive predict value (PPV) (95.4%), and moderate negative predictive value (NPV) (74.2%).We developed a machine learning-based prognostic model that showed high accuracy, high sensitivity, and high PPV for predicting the mortality of patients with severe trauma.

Personalized modulation of coagulation factors using a thrombin dynamics model to treat trauma-induced coagulopathy

Current trauma-induced coagulopathy resuscitation protocols use slow laboratory measurements, rules-of-thumb, and clinician gestalt to administer large volumes of uncharacterized, non-tailored blood products. These one-size-fits-all treatment approaches have high mortality. Here, we provide significant evidence that trauma patient survival 24 h after hospital admission occurs if and only if blood protein coagulation factor concentrations equilibrate at a normal value, either from inadvertent plasma-based modulation or from innate compensation. This result motivates quantitatively guiding trauma patient coagulation factor levels while accounting for protein interactions. Toward such treatment, we develop a Goal-oriented Coagulation Management (GCM) algorithm, a personalized and automated ordered sequence of operations to compute and specify coagulation factor concentrations that rectify clotting. This novel GCM algorithm also integrates new control-oriented advancements that we make in this work: an improvement of a prior thrombin dynamics model that captures the coagulation process to control, a use of rapidly-measurable concentrations to help predict patient state, and an accounting of patient-specific effects and limitations when adding coagulation factors to remedy coagulopathy. Validation of the GCM algorithm's guidance shows superior performance over clinical practice in attaining normal coagulation factor concentrations and normal clotting profiles simultaneously.

Predicting correlated outcomes from molecular data

MOTIVATION

Multivariate (multi-target) regression has the potential to outperform univariate (single-target) regression at predicting correlated outcomes, which frequently occur in biomedical and clinical research. Here we implement multivariate lasso and ridge regression using stacked generalisation.

RESULTS

Our flexible approach leads to predictive and interpretable models in high-dimensional settings, with a single estimate for each input-output effect. In the simulation, we compare the predictive performance of several state-of-the-art methods for multivariate regression. In the application, we use clinical and genomic data to predict multiple motor and non-motor symptoms in Parkinson's disease patients. We conclude that stacked multivariate regression, with our adaptations, is a competitive method for predicting correlated outcomes.

AVAILABILITY AND IMPLEMENTATION

The R package joinet is available on GitHub (https://github.com/rauschenberger/joinet) and cran (https://cran.r-project.org/package=joinet).

SUPPLEMENTARY INFORMATION

Supplementary tables and figures are available at Bioinformatics online.

Predicting Readmission After Anterior, Posterior, and Posterior Interbody Lumbar Spinal Fusion: A Neural Network Machine Learning Approach

BACKGROUND

Readmission after spine surgery is costly and a relatively common occurrence. Previous research identified several risk factors for readmission; however, the conclusions remain equivocal. Machine learning algorithms offer a unique perspective in analysis of risk factors for readmission and can help predict the likelihood of this occurrence. This study evaluated a neural network (NN), a supervised machine learning technique, to determine whether it could predict readmission after 3 lumbar fusion procedures.

METHODS

The American College of Surgeons National Surgical Quality Improvement Program database was queried between 2009 and 2018. Patients who had undergone anterior, lateral, and/or posterior lumbar fusion were included in the study. The Python scikit Learn package was used to run the NN algorithm. A multivariate regression was performed to determine risk factors for readmission.

RESULTS

There were 63,533 patients analyzed (12,915 anterior lumbar interbody fusion, 27,212 posterior lumbar interbody fusion, and 23,406 posterior spinal fusion cases). The NN algorithm was able to successfully predict 30-day readmission for 94.6% of anterior lumbar interbody fusion, 94.0% of posterior lumbar interbody fusion, and 92.6% of posterior spinal fusion cases with area under the curve values of 0.64-0.65. Multivariate regression indicated that age >65 years and American Society of Anesthesiologists class >II were linked to increased risk for readmission for all 3 procedures.

CONCLUSIONS

The accurate metrics presented indicate the capability for NN algorithms to predict readmission after lumbar arthrodesis. Moreover, the results of this study serve as a catalyst for further research into the utility of machine learning in spine surgery.

Clinician involvement in research on machine learning-based predictive clinical decision support for the hospital setting: A scoping review

OBJECTIVE

The study sought to describe the prevalence and nature of clinical expert involvement in the development, evaluation, and implementation of clinical decision support systems (CDSSs) that utilize machine learning to analyze electronic health record data to assist nurses and physicians in prognostic and treatment decision making (ie, predictive CDSSs) in the hospital.

MATERIALS AND METHODS

A systematic search of PubMed, CINAHL, and IEEE Xplore and hand-searching of relevant conference proceedings were conducted to identify eligible articles. Empirical studies of predictive CDSSs using electronic health record data for nurses or physicians in the hospital setting published in the last 5 years in peer-reviewed journals or conference proceedings were eligible for synthesis. Data from eligible studies regarding clinician involvement, stage in system design, predictive CDSS intention, and target clinician were charted and summarized.

RESULTS

Eighty studies met eligibility criteria. Clinical expert involvement was most prevalent at the beginning and late stages of system design. Most articles (95%) described developing and evaluating machine learning models, 28% of which described involving clinical experts, with nearly half functioning to verify the clinical correctness or relevance of the model (47%).

DISCUSSION

Involvement of clinical experts in predictive CDSS design should be explicitly reported in publications and evaluated for the potential to overcome predictive CDSS adoption challenges.

CONCLUSIONS

If present, clinical expert involvement is most prevalent when predictive CDSS specifications are made or when system implementations are evaluated. However, clinical experts are less prevalent in developmental stages to verify clinical correctness, select model features, preprocess data, or serve as a gold standard.

Can Big Data and Machine Learning Improve Our Understanding of Acute Respiratory Distress Syndrome?

Acute respiratory distress syndrome (ARDS) accounts for 10% of all diagnoses in the Intensive Care Unit, and about 40% of the patients succumb to the disease. Clinical methods alone can result in the under-recognition of this heterogeneous syndrome. The purpose of this study is to evaluate the role that big data and machine learning (ML) have played in understanding the heterogeneity of the disease and the development of various prediction algorithms. Most of the work in the field of ML in ARDS has been in the development of prediction models that have comparable efficacies to that of traditional models. Prediction algorithms have been useful in identifying new variables that may be important to consider in the future, supplementing the unknown information with the help of available noninvasive parameters, as well as predicting mortality. Phenotype identification using an unsupervised ML algorithm has been pivotal in classifying the heterogeneous population into more homogenous classes. Big data generated from ventilators in the form of ventilator waveform analysis and images in the form of radiomics have also been leveraged for the identification of the syndrome and can be incorporated into a clinical decision support system. Although the results are promising, lack of generalizability, "black box" nature of algorithms and concerns about "alarm fatigue" should be addressed for more mainstream adoption of these models.

Use of Machine Learning to Re-Assess Patterns of Multivariate Functional Recovery after Fluid Percussion Injury: Operation Brain Trauma Therapy

Traumatic brain injury (TBI) is a leading cause of death and disability. Yet, despite immense research efforts, treatment options remain elusive. Translational failures in TBI are often attributed to the heterogeneity of the TBI population and limited methods to capture these individual variabilities. Advances in machine learning (ML) have the potential to further personalized treatment strategies and better inform translational research. However, the use of ML has yet to be widely assessed in pre-clinical neurotrauma research, where data are strictly limited in subject number. To better establish ML's feasibility, we utilized the fluid percussion injury (FPI) portion of the rich, rat data set collected by Operation Brain Trauma Therapy (OBTT), which tested multiple pharmacological treatments. Previous work has provided confidence that both unsupervised and supervised ML techniques can uncover useful insights from this OBTT pre-clinical research data set. As a proof-of-concept, we aimed to better evaluate the multi-variate recovery profiles afforded by the administration of nine different experimental therapies. We assessed supervised pairwise classifiers trained on a pre-processed data set that incorporated metrics from four feature groups to determine their ability to correctly identify specific drug treatments. In all but one of the possible pairwise combinations of minocycline, levetiracetam, erythropoietin, nicotinamide, and amantadine, the baseline was outperformed by one or more supervised classifiers, the exception being nicotinamide versus amantadine. Further, when the same methods were employed to assess different doses of the same treatment, the ML classifiers had greater difficulty in understanding which treatment each sample received. Our data serve as a critical first step toward identifying optimal treatments for specific subgroups of samples that are dependent on factors such as types and severity of traumatic injuries, as well as informing the prediction of therapeutic combinations that may lead to greater treatment effects than individual therapies.

Severity Trajectories of Pediatric Inpatients Using the Criticality Index

OBJECTIVES

To assess severity of illness trajectories described by the Criticality Index for survivors and deaths in five patient groups defined by the sequence of patient care in ICU and routine patient care locations.

DESIGN

The Criticality Index developed using a calibrated, deep neural network, measures severity of illness using physiology, therapies, and therapeutic intensity. Criticality Index values in sequential 6-hour time periods described severity trajectories.

SETTING

Hospitals with pediatric inpatient and ICU care.

PATIENTS

Pediatric patients never cared for in an ICU (n = 20,091), patients only cared for in the ICU (n = 2,096) and patients cared for in both ICU and non-ICU care locations (n = 17,023) from 2009 to 2016 Health Facts database (Cerner Corporation, Kansas City, MO).

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Criticality Index values were consistent with clinical experience. The median (25-75th percentile) ICU Criticality Index values (0.878 [0.696-0.966]) were more than 80-fold higher than the non-ICU values (0.010 [0.002-0.099]). Non-ICU Criticality Index values for patients transferred to the ICU were 40-fold higher than those never transferred to the ICU (0.164 vs 0.004). The median for ICU deaths was higher than ICU survivors (0.983 vs 0.875) (p < 0.001). The severity trajectories for the five groups met expectations based on clinical experience. Survivors had increasing Criticality Index values in non-ICU locations prior to ICU admission, decreasing Criticality Index values in the ICU, and decreasing Criticality Index values until hospital discharge. Deaths had higher Criticality Index values than survivors, steeper increases prior to the ICU, and worsening values in the ICU. Deaths had a variable course, especially those who died in non-ICU care locations, consistent with deaths associated with both active therapies and withdrawals/limitations of care.

CONCLUSIONS

Severity trajectories measured by the Criticality Index showed strong validity, reflecting the expected clinical course for five diverse patient groups.

Risk Factors Associated With Early and Late Posttraumatic Multiorgan Failure: An Analysis From RETRAUCI

OBJECTIVE

To analyze factors associated with the development of early and late multiorgan failure (MOF) in trauma patients admitted to the intensive care unit (ICU).

METHODS

Spanish Trauma ICU Registry (RETRAUCI). Data collected from 52 trauma ICU between March 2015 and December 2019. We analyzed the incidence, outcomes, and the risk factors associated with early (< 72 h) or late (beyond 72 h) MOF in trauma ICU patients. Multiple logistic regression analysis was performed to analyze associated factors.

RESULTS

After excluding patients with incomplete data, 9,598 trauma ICU patients constituted the study population. Up to 965 patients (10.1%) presented with MOF, distributed by early MOF in 780 patients (8.1%) and late MOF in 185 patients (1.9%). The multivariate analysis showed that early MOF was associated with: ISS ≥ 16 (OR 2.80), hemodynamic instability (OR from 2.03 to 43.05), trauma-associated coagulopathy (OR 2.32), and acute kidney injury (OR 4.10). Late MOF was associated with: age > 65 years (OR 1.52), hemodynamic instability (OR from 1.92 to 9.94), acute kidney injury (OR 4.22), and nosocomial infection (OR 17.23). MOF was closely related to mortality (crude OR (95% CI) 4.77 (4.22-5.40)).

CONCLUSIONS

Multiorgan failure was recorded in 10% of trauma ICU patients, with early MOF being the predominant form. Early and late MOF forms were associated with different risk factors, suggesting different pathophysiological pathways. Early MOF was associated with higher severity of injury and severe bleeding-related complications and late MOF with advanced age and nosocomial infection.

Identifying bladder rupture following traumatic pelvic fracture: A machine learning approach

INTRODUCTION

Bladder rupture following blunt pelvic trauma is rare though can have significant sequelae. We sought to determine whether machine learning could help predict the presence of bladder injury using certain factors at the time of presentation of blunt pelvic trauma.

MATERIALS AND METHODS

Adult patients at a Level I trauma center with blunt trauma pelvic fractures from January 1, 2005 to December 31, 2017 were identified. Patients with admission urinalysis data, fracture ICD 9 codes, and mechanism of injury available in the trauma registry were included. Patients with bladder rupture and pelvic fracture were compared to those with pelvic fracture alone. The classification of results was performed using the MATLAB Classification Learner Tool. The classification performances were tested by machine learning algorithms in the domains of Decision Tree, Logistic Regression, Naïve Bayes, Support Vector Machine (SVM), Nearest Neighbor (KNN), and Ensemble classifiers.

RESULTS

Of the 3063 eligible pelvic fracture patients identified, 208 (6.8%) had concomitant bladder ruptures. Twenty machine learning algorithms were then tested based on pelvic fracture ICD-9 code, admission urinalysis, and mechanism of injury. The best classification results were obtained using the Gaussian Naïve Bayes and Kernel Naïve Bayes classifiers, both with accuracy of 97.8%, specificity of 99%, sensitivity of 83%, and area under the curve (AUC) of the ROC curve of 0.99.

CONCLUSION

Machine learning algorithms can be used to help predict with a high level of accuracy the presence of bladder rupture with blunt pelvic trauma using readily available information at the time of presentation. This has the potential to improve selection of patients for additional imaging, while also more appropriately allocating hospital resources and reducing patient risks.

Early increase in anti-inflammatory biomarkers is associated with the development of multiple organ dysfunction syndrome in severely injured trauma patients

Background

As a result of improvements in the early resuscitation phase of trauma, mortality is largely driven by later mortality due to multiple organ dysfunction syndrome (MODS), which may be mediated by an early overdrive in the host immune response. If patients at risk for MODS could be identified early, preventive treatment measures could be taken. The aim of this study is to investigate whether specific biomarkers are associated with MODS.

Methods

Multiple trauma patients presenting to the Amsterdam University Medical Centers, location Academic Medical Center, between 2012 and 2018 with an Injury Severity Score of 16 or higher were sampled on arrival at the emergency department. A wide variety of inflammatory cytokines, endothelial and lung-specific markers were determined. Comparisons were made between patients with and without MODS. Univariate and multivariate logistic regression was used to determine associations between specific biomarkers and MODS. A p value of 0.05 was considered to be statistically significant.

Results

In total, 147 multiple trauma patients were included. Of these, 32 patients developed MODS (21.7%). Patients who developed MODS were more severely injured, had more traumatic brain injury and showed more deranged markers of coagulation when compared with patients without MODS. Overall, both proinflammatory and anti-inflammatory cytokines were higher in patients with MODS, indicative of a host immune reaction. In the multivariate analysis, the combination of anti-inflammatory proteins interleukin 1 receptor antagonist (IL-1RA) (OR 1.27 (1.07–1.51), p=0.002) and Clara cell protein 16 (CC-16) (1.06 (1.01–1.05), p=0.031) was most strongly associated with the development MODS.

Conclusions

In trauma, anti-inflammatory proteins IL-1RA and CC-16 have the potential to early identify patients at risk for development of MODS. Further research is warranted to prospectively validate these results.

Level of evidence

Prognostic study, level III.