Machine learning algorithms performed no better than regression models for prognostication in traumatic brain injury

Usefulness of Artificial Intelligence in Traumatic Brain Injury: A Bibliometric Analysis and Mini-review

BACKGROUND

Traumatic brain injury (TBI) has become a major source of disability worldwide, increasing the interest in algorithms that use artificial intelligence (AI) to optimize the interpretation of imaging studies, prognosis estimation, and critical care issues. In this study we present a bibliometric analysis and mini-review on the main uses that have been developed for TBI in AI.

METHODS

The results informing this review come from a Scopus database search as of April 15, 2023. The bibliometric analysis was carried out via the mapping bibliographic metrics method. Knowledge mapping was made in the VOSviewer software (V1.6.18), analyzing the "link strength" of networks based on co-occurrence of key words, countries co-authorship, and co-cited authors. In the mini-review section, we highlight the main findings and contributions of the studies.

RESULTS

A total of 495 scientific publications were identified from 2000 to 2023, with 9262 citations published since 2013. Among the 160 journals identified, The Journal of Neurotrauma, Frontiers in Neurology, and PLOS ONE were those with the greatest number of publications. The most frequently co-occurring key words were: "machine learning", "deep learning", "magnetic resonance imaging", and "intracranial pressure". The United States accounted for more collaborations than any other country, followed by United Kingdom and China. Four co-citation author clusters were found, and the top 20 papers were divided into reviews and original articles.

CONCLUSIONS

AI has become a relevant research field in TBI during the last 20 years, demonstrating great potential in imaging, but a more modest performance for prognostic estimation and neuromonitoring.

Machine Learning Algorithms Versus Classical Regression Models in Pre-Eclampsia Prediction: A Systematic Review

PURPOSE OF REVIEW

Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthesise the literature on ML and classical regression studies exploring potential prognostic factors and to compare prediction performance for pre-eclampsia.

RECENT FINDINGS

From 9382 studies retrieved, 82 were included. Sixty-six publications exclusively reported eighty-four classical regression models to predict variable timing of onset of pre-eclampsia. Another six publications reported purely ML algorithms, whilst another 10 publications reported ML algorithms and classical regression models in the same sample with 8 of 10 findings that ML algorithms outperformed classical regression models. The most frequent prognostic factors were age, pre-pregnancy body mass index, chronic medical conditions, parity, prior history of pre-eclampsia, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and pregnancy-associated plasma protein A. Top performing ML algorithms were random forest (area under the curve (AUC) = 0.94, 95% confidence interval (CI) 0.91-0.96) and extreme gradient boosting (AUC = 0.92, 95% CI 0.90-0.94). The competing risk model had similar performance (AUC = 0.92, 95% CI 0.91-0.92) compared with a neural network. Calibration performance was not reported in the majority of publications. ML algorithms had better performance compared to classical regression models in pre-eclampsia prediction. Random forest and boosting-type algorithms had the best prediction performance. Further research should focus on comparing ML algorithms to classical regression models using the same samples and evaluation metrics to gain insight into their performance. External validation of ML algorithms is warranted to gain insights into their generalisability.

Assessing the predictive capability of machine learning models in determining clinical outcomes for patients with cervical spondylotic myelopathy treated with laminectomy and posterior spinal fusion

BACKGROUND

Cervical spondylotic myelopathy (CSM) is a prevalent degenerative condition resulting from spinal cord compression and injury. Laminectomy with posterior spinal fusion (LPSF) is a commonly employed treatment approach for CSM patients. This study aimed to assess the effectiveness of machine learning models (MLMs) in predicting clinical outcomes in CSM patients undergoing LPSF.

METHODS

A retrospective analysis was conducted on 329 CSM patients who underwent LPSF at our institution from Jul 2017 to Jul 2023. Neurological outcomes were evaluated using the modified Japanese Orthopaedic Association (mJOA) scale preoperatively and at the final follow-up. Patients were categorized into two groups based on clinical outcomes: the favorable group (recovery rates ≥ 52.8%) and the unfavorable group (recovery rates < 52.8%). Potential predictors for poor clinical outcomes were compared between the groups. Four MLMs-random forest (RF), logistic regression (LR), support vector machine (SVM), and k-nearest neighborhood (k-NN)-were utilized to predict clinical outcome. RF model was also employed to identify factors associated with poor clinical outcome.

RESULTS

Out of the 329 patients, 185 were male (56.2%) and 144 were female (43.4%), with an average follow-up period of 17.86 ± 1.74 months. Among them, 267 patients (81.2%) had favorable clinical outcomes, while 62 patients (18.8%) did not achieve favorable results. Analysis using binary logistic regression indicated that age, preoperative mJOA scale, and symptom duration (p < 0.05) were independent predictors of unfavorable clinical outcomes. All models performed satisfactorily, with RF achieving the highest accuracy of 0.922. RF also displayed superior sensitivity and specificity (sensitivity = 0.851, specificity = 0.944). The Area under the Curve (AUC) values for RF, Logistic LR, SVM, and k-NN were 0.905, 0.827, 0.851, and 0.883, respectively. The RF model identified preoperative mJOA scale, age, symptom duration, and MRI signal changes as the most significant variables associated with poor clinical outcomes in descending order.

CONCLUSIONS

This study highlighted the effectiveness of machine learning models in predicting the clinical outcomes of CSM patients undergoing LPSF. These models have the potential to forecast clinical outcomes in this patient population, providing valuable prognostic insights for preoperative counseling and postoperative management.

Prognostication in Neurocritical Care

OBJECTIVE

This article synthesizes the current literature on prognostication in neurocritical care, identifies existing challenges, and proposes future research directions to reduce variability and enhance scientific and patient-centered approaches to neuroprognostication.

LATEST DEVELOPMENTS

Patients with severe acute brain injury often lack the capacity to make their own medical decisions, leaving surrogate decision makers responsible for life-or-death choices. These decisions heavily rely on clinicians' prognostication, which is still considered an art because of the previous lack of specific guidelines. Consequently, there is significant variability in neuroprognostication practices. This article examines various aspects of neuroprognostication. It explores the cognitive approach to prognostication, highlights the use of statistical modeling such as Bayesian models and machine learning, emphasizes the importance of clinician-family communication during prognostic disclosures, and proposes shared decision making for more patient-centered care.

ESSENTIAL POINTS

This article identifies ongoing challenges in the field and emphasizes the need for future research to ameliorate variability in neuroprognostication. By focusing on scientific methodologies and patient-centered approaches, this research aims to provide guidance and tools that may enhance neuroprognostication in neurocritical care.

Predicting the risk of pancreatic cancer in adults with new-onset diabetes: development and internal-external validation of a clinical risk prediction model

BACKGROUND

The National Institute for Health and Care Excellence (NICE) recommends that people aged 60+ years with newly diagnosed diabetes and weight loss undergo abdominal imaging to assess for pancreatic cancer. More nuanced stratification could lead to enrichment of these referral pathways.

METHODS

Population-based cohort study of adults aged 30-85 years at type 2 diabetes diagnosis (2010-2021) using the QResearch primary care database in England linked to secondary care data, the national cancer registry and mortality registers. Clinical prediction models were developed to estimate risks of pancreatic cancer diagnosis within 2 years and evaluated using internal-external cross-validation.

RESULTS

Seven hundred and sixty-seven of 253,766 individuals were diagnosed with pancreatic cancer within 2 years. Models included age, sex, BMI, prior venous thromboembolism, digoxin prescription, HbA1c, ALT, creatinine, haemoglobin, platelet count; and the presence of abdominal pain, weight loss, jaundice, heartburn, indigestion or nausea (previous 6 months). The Cox model had the highest discrimination (Harrell's C-index 0.802 (95% CI: 0.797-0.817)), the highest clinical utility, and was well calibrated. The model's highest 1% of predicted risks captured 12.51% of pancreatic cancer cases. NICE guidance had 3.95% sensitivity.

DISCUSSION

A new prediction model could have clinical utility in identifying individuals with recent onset diabetes suitable for fast-track abdominal imaging.

Variables associated with owner perceptions of the health of their dog: Further analysis of data from a large international survey

In a recent study (doi: 10.1371/journal.pone.0265662), associations were identified between owner-reported dog health status and diet, whereby those fed a vegan diet were perceived to be healthier. However, the study was limited because it did not consider possible confounding from variables not included in the analysis. The aim of the current study was to extend these earlier findings, using different modelling techniques and including multiple variables, to identify the most important predictors of owner perceptions of dog health. From the original dataset, two binary outcome variables were created: the 'any health problem' distinguished dogs that owners perceived to be healthy ("no") from those perceived to have illness of any severity; the 'significant illness' variable distinguished dogs that owners perceived to be either healthy or having mild illness ("no") from those perceived to have significant or serious illness ("yes"). Associations between these health outcomes and both owner-animal metadata and healthcare variables were assessed using logistic regression and machine learning predictive modelling using XGBoost. For the any health problem outcome, best-fit models for both logistic regression (area under curve [AUC] 0.842) and XGBoost (AUC 0.836) contained the variables dog age, veterinary visits and received medication, whilst owner age and breed size category also featured. For the significant illness outcome, received medication, veterinary visits, dog age and were again the most important predictors for both logistic regression (AUC 0.903) and XGBoost (AUC 0.887), whilst breed size category, education and owner age also featured in the latter. Any contribution from the dog vegan diet variable was negligible. The results of the current study extend the previous research using the same dataset and suggest that diet has limited impact on owner-perceived dog health status; instead, dog age, frequency of veterinary visits and receiving medication are most important.

Identifying predictors of the tooth loss phenotype in a large periodontitis patient cohort using a machine learning approach

OBJECTIVES

This study aimed to identify predictors associated with the tooth loss phenotype in a large periodontitis patient cohort in the university setting.

METHODS

Information on periodontitis patients and nineteen factors identified at the initial visit was extracted from electronic health records. The primary outcome is tooth loss phenotype (presence or absence of tooth loss). Prediction models were built on significant factors (single or combinatory) selected by the RuleFit algorithm, and these factors were further adopted by regression models. Model performance was evaluated by Area Under the Receiver Operating Characteristic Curve (AUROC) and Area Under the Precision-Recall Curve (AUPRC). Associations between predictors and the tooth loss phenotype were also evaluated by classical statistical approaches to validate the performance of machine learning models.

RESULTS

In total, 7840 patients were included. The machine learning model predicting the tooth loss phenotype achieved AUROC of 0.71 and AUPRC of 0.66. Age, periodontal diagnosis, number of missing teeth at baseline, furcation involvement, and tooth mobility were associated with the tooth loss phenotype in both machine learning and classical statistical models.

CONCLUSIONS

The rule-based machine learning approach improves model explainability compared to classical statistical methods. However, the model's generalizability needs to be further validated by external datasets.

CLINICAL SIGNIFICANCE

Predictors identified by the current machine learning approach using the RuleFit algorithm had clinically relevant thresholds in predicting the tooth loss phenotype in a large and diverse periodontitis patient cohort. The results of this study will assist clinicians in performing risk assessment for periodontitis at the initial visit.

The Australian Traumatic Brain Injury Initiative: Single Data Dictionary to Predict Outcome for People With Moderate-Severe Traumatic Brain Injury

In this series of eight articles, the Australian Traumatic Brain Injury Initiative (AUS-TBI) consortium describes the Australian approach used to select the common data elements collected acutely that have been shown to predict outcome following moderate-severe traumatic brain injury (TBI) across the lifespan. This article presents the unified single data dictionary, together with additional measures chosen to facilitate comparative effectiveness research and data linkage. Consultations with the AUS-TBI Lived Experience Expert Group provided insights on the merits and considerations regarding data elements for some of the study areas, as well as more general principles to guide the collection of data and the selection of meaningful measures. These are presented as a series of guiding principles and themes. The AUS-TBI Aboriginal and Torres Strait Islander Advisory Group identified a number of key points and considerations for the project approach specific to Aboriginal and Torres Strait Islander peoples, including key issues of data sovereignty and community involvement. These are outlined in the form of principles to guide selection of appropriate methodologies, data management, and governance. Implementation of the AUS-TBI approach aims to maximize ongoing data collection and linkage, to facilitate personalization of care and improved outcomes for people who experience moderate-severe TBI.

Updating M6 pregnancy of unknown location risk-prediction model including evaluation of clinical factors

OBJECTIVES

Ectopic pregnancy (EP) is a major high-risk outcome following a pregnancy of unknown location (PUL) classification. Biochemical markers are used to triage PUL as high vs low risk to guide appropriate follow-up. The M6 model is currently the best risk-prediction model. We aimed to update the M6 model and evaluate whether performance can be improved by including clinical factors.

METHODS

This prospective cohort study recruited consecutive PUL between January 2015 and January 2017 at eight units (Phase 1), with two centers continuing recruitment between January 2017 and March 2021 (Phase 2). Serum samples were collected routinely and sent for β-human chorionic gonadotropin (β-hCG) and progesterone measurement. Clinical factors recorded were maternal age, pain score, bleeding score and history of EP. Based on transvaginal ultrasonography and/or biochemical confirmation during follow-up, PUL were classified subsequently as failed PUL (FPUL), intrauterine pregnancy (IUP) or EP (including persistent PUL (PPUL)). The M6 models with (M6P ) and without (M6NP ) progesterone were refitted and extended with clinical factors. Model validation was performed using internal-external cross-validation (IECV) (Phase 1) and temporal external validation (EV) (Phase 2). Missing values were handled using multiple imputation.

RESULTS

Overall, 5473 PUL were recruited over both phases. A total of 709 PUL were excluded because maternal age was < 16 years or initial β-hCG was ≤ 25 IU/L, leaving 4764 (87%) PUL for analysis (2894 in Phase 1 and 1870 in Phase 2). For the refitted M6P model, the area under the receiver-operating-characteristics curve (AUC) for EP/PPUL vs IUP/FPUL was 0.89 for IECV and 0.84-0.88 for EV, with respective sensitivities of 94% and 92-93%. For the refitted M6NP model, the AUCs were 0.85 for IECV and 0.82-0.86 for EV, with respective sensitivities of 92% and 93-94%. Calibration performance was good overall, but with heterogeneity between centers. Net Benefit confirmed clinical utility. The change in AUC when M6P was extended to include maternal age, bleeding score and history of EP was between -0.02 and 0.01, depending on center and phase. The corresponding change in AUC when M6NP was extended was between -0.01 and 0.03. At the 5% threshold to define high risk of EP/PPUL, extending M6P altered sensitivity by -0.02 to -0.01, specificity by 0.03 to 0.04 and Net Benefit by -0.005 to 0.006. Extending M6NP altered sensitivity by -0.03 to -0.01, specificity by 0.05 to 0.07 and Net Benefit by -0.005 to 0.006.

CONCLUSIONS

The updated M6 model offers accurate diagnostic performance, with excellent sensitivity for EP. Adding clinical factors to the model improved performance in some centers, especially when progesterone levels were not suitable or unavailable. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Machine Learning Models for Predicting Disability and Pain Following Lumbar Disc Herniation Surgery

Importance

Lumber disc herniation surgery can reduce pain and disability. However, a sizable minority of individuals experience minimal benefit, necessitating the development of accurate prediction models.

Objective

To develop and validate prediction models for disability and pain 12 months after lumbar disc herniation surgery.

Design, Setting, and Participants

A prospective, multicenter, registry-based prognostic study was conducted on a cohort of individuals undergoing lumbar disc herniation surgery from January 1, 2007, to May 31, 2021. Patients in the Norwegian Registry for Spine Surgery from all public and private hospitals in Norway performing spine surgery were included. Data analysis was performed from January to June 2023.

Exposures

Microdiscectomy or open discectomy.

Main Outcomes and Measures

Treatment success at 12 months, defined as improvement in Oswestry Disability Index (ODI) of 22 points or more; Numeric Rating Scale (NRS) back pain improvement of 2 or more points, and NRS leg pain improvement of 4 or more points. Machine learning models were trained for model development and internal-external cross-validation applied over geographic regions to validate the models. Model performance was assessed through discrimination (C statistic) and calibration (slope and intercept).

Results

Analysis included 22 707 surgical cases (21 161 patients) (ODI model) (mean [SD] age, 47.0 [14.0] years; 12 952 [57.0%] males). Treatment nonsuccess was experienced by 33% (ODI), 27% (NRS back pain), and 31% (NRS leg pain) of the patients. In internal-external cross-validation, the selected machine learning models showed consistent discrimination and calibration across all 5 regions. The C statistic ranged from 0.81 to 0.84 (pooled random-effects meta-analysis estimate, 0.82; 95% CI, 0.81-0.84) for the ODI model. Calibration slopes (point estimates, 0.94-1.03; pooled estimate, 0.99; 95% CI, 0.93-1.06) and calibration intercepts (point estimates, -0.05 to 0.11; pooled estimate, 0.01; 95% CI, -0.07 to 0.10) were also consistent across regions. For NRS back pain, the C statistic ranged from 0.75 to 0.80 (pooled estimate, 0.77; 95% CI, 0.75-0.79); for NRS leg pain, the C statistic ranged from 0.74 to 0.77 (pooled estimate, 0.75; 95% CI, 0.74-0.76). Only minor heterogeneity was found in calibration slopes and intercepts.

Conclusion

The findings of this study suggest that the models developed can inform patients and clinicians about individual prognosis and aid in surgical decision-making.

Predictive Performance of Machine Learning-Based Models for Poststroke Clinical Outcomes in Comparison With Conventional Prognostic Scores: Multicenter, Hospital-Based Observational Study

BACKGROUND

Although machine learning is a promising tool for making prognoses, the performance of machine learning in predicting outcomes after stroke remains to be examined.

OBJECTIVE

This study aims to examine how much data-driven models with machine learning improve predictive performance for poststroke outcomes compared with conventional stroke prognostic scores and to elucidate how explanatory variables in machine learning-based models differ from the items of the stroke prognostic scores.

METHODS

We used data from 10,513 patients who were registered in a multicenter prospective stroke registry in Japan between 2007 and 2017. The outcomes were poor functional outcome (modified Rankin Scale score >2) and death at 3 months after stroke. Machine learning-based models were developed using all variables with regularization methods, random forests, or boosted trees. We selected 3 stroke prognostic scores, namely, ASTRAL (Acute Stroke Registry and Analysis of Lausanne), PLAN (preadmission comorbidities, level of consciousness, age, neurologic deficit), and iScore (Ischemic Stroke Predictive Risk Score) for comparison. Item-based regression models were developed using the items of these 3 scores. The model performance was assessed in terms of discrimination and calibration. To compare the predictive performance of the data-driven model with that of the item-based model, we performed internal validation after random splits of identical populations into 80% of patients as a training set and 20% of patients as a test set; the models were developed in the training set and were validated in the test set. We evaluated the contribution of each variable to the models and compared the predictors used in the machine learning-based models with the items of the stroke prognostic scores.

RESULTS

The mean age of the study patients was 73.0 (SD 12.5) years, and 59.1% (6209/10,513) of them were men. The area under the receiver operating characteristic curves and the area under the precision-recall curves for predicting poststroke outcomes were higher for machine learning-based models than for item-based models in identical populations after random splits. Machine learning-based models also performed better than item-based models in terms of the Brier score. Machine learning-based models used different explanatory variables, such as laboratory data, from the items of the conventional stroke prognostic scores. Including these data in the machine learning-based models as explanatory variables improved performance in predicting outcomes after stroke, especially poststroke death.

CONCLUSIONS

Machine learning-based models performed better in predicting poststroke outcomes than regression models using the items of conventional stroke prognostic scores, although they required additional variables, such as laboratory data, to attain improved performance. Further studies are warranted to validate the usefulness of machine learning in clinical settings.

Development and internal validation of a prediction model for long-term opioid use-an analysis of insurance claims data

ABSTRACT

In the United States, a public-health crisis of opioid overuse has been observed, and in Europe, prescriptions of opioids are strongly increasing over time. The objective was to develop and validate a multivariable prognostic model to be used at the beginning of an opioid prescription episode, aiming to identify individual patients at high risk for long-term opioid use based on routinely collected data. Predictors including demographics, comorbid diseases, comedication, morphine dose at episode initiation, and prescription practice were collected. The primary outcome was long-term opioid use, defined as opioid use of either >90 days duration and ≥10 claims or >120 days, independent of the number of claims. Traditional generalized linear statistical regression models and machine learning approaches were applied. The area under the curve, calibration plots, and the scaled Brier score assessed model performance. More than four hundred thousand opioid episodes were included. The final risk prediction model had an area under the curve of 0.927 (95% confidence interval 0.924-0.931) in the validation set, and this model had a scaled Brier score of 48.5%. Using a threshold of 10% predicted probability to identify patients at high risk, the overall accuracy of this risk prediction model was 81.6% (95% confidence interval 81.2% to 82.0%). Our study demonstrated that long-term opioid use can be predicted at the initiation of an opioid prescription episode, with satisfactory accuracy using data routinely collected at a large health insurance company. Traditional statistical methods resulted in higher discriminative ability and similarly good calibration as compared with machine learning approaches.

Development and Validation of a Risk Prediction Model to Estimate the Risk of Stroke Among Hypertensive Patients in University of Gondar Comprehensive Specialized Hospital, Gondar, 2012 to 2022

Background

A risk prediction model to predict the risk of stroke has been developed for hypertensive patients. However, the discriminating power is poor, and the predictors are not easily accessible in low-income countries. Therefore, developing a validated risk prediction model to estimate the risk of stroke could help physicians to choose optimal treatment and precisely estimate the risk of stroke.

Objective

This study aims to develop and validate a risk prediction model to estimate the risk of stroke among hypertensive patients at the University of Gondar Comprehensive Specialized Hospital.

Methods

A retrospective follow-up study was conducted among 743 hypertensive patients between September 01/2012 and January 31/2022. The participants were selected using a simple random sampling technique. Model performance was evaluated using discrimination, calibration, and Brier scores. Internal validity and clinical utility were evaluated using bootstrapping and a decision curve analysis.

Results

Incidence of stroke was 31.4 per 1000 person-years (95% CI: 26.0, 37.7). Combinations of six predictors were selected for model development (sex, residence, baseline diastolic blood pressure, comorbidity, diabetes, and uncontrolled hypertension). In multivariable logistic regression, the discriminatory power of the model was 0.973 (95% CI: 0.959, 0.987). Calibration plot illustrated an overlap between the probabilities of the predicted and actual observed risks after 10,000 times bootstrap re-sampling, with a sensitivity of 92.79%, specificity 93.51%, and accuracy of 93.41%. The decision curve analysis demonstrated that the net benefit of the model was better than other intervention strategies, starting from the initial point.

Conclusion

An internally validated, accurate prediction model was developed and visualized in a nomogram. The model is then changed to an offline mobile web-based application to facilitate clinical applicability. The authors recommend that other researchers eternally validate the model.

Twenty-four-hour rhythmicities in disorders of consciousness are associated with a favourable outcome

Fluctuations of consciousness and their rhythmicities have been rarely studied in patients with a disorder of consciousness after acute brain injuries. 24-h assessment of brain (EEG), behaviour (eye-opening), and circadian (clock-controlled hormones secretion from urine) functions was performed in acute brain-injured patients. The distribution, long-term predictability, and rhythmicity (circadian/ultradian) of various EEG features were compared with the initial clinical status, the functional outcome, and the circadian rhythmicities of behaviour and clock-controlled hormones. Here we show that more physiological and favourable patterns of fluctuations are associated with a higher 24 h predictability and sharp up-and-down shape of EEG switches, reminiscent of the Flip-Flop model of sleep. Multimodal rhythmic analysis shows that patients with simultaneous circadian rhythmicity for brain, behaviour, and hormones had a favourable outcome. Finally, both re-emerging EEG fluctuations and homogeneous 24-h cycles for EEG, eye-opening, and hormones appeared as surrogates for preserved functionality in brainstem and basal forebrain, which are key prognostic factors for later improvement. While the recovery of consciousness has previously been related to a high short-term complexity, we suggest in this exploratory study the importance of the high predictability of the 24 h long-term generation of brain rhythms and highlight the importance of circadian body-brain rhythms in awakening.

Advances in neuroproteomics for neurotrauma: unraveling insights for personalized medicine and future prospects

Neuroproteomics, an emerging field at the intersection of neuroscience and proteomics, has garnered significant attention in the context of neurotrauma research. Neuroproteomics involves the quantitative and qualitative analysis of nervous system components, essential for understanding the dynamic events involved in the vast areas of neuroscience, including, but not limited to, neuropsychiatric disorders, neurodegenerative disorders, mental illness, traumatic brain injury, chronic traumatic encephalopathy, and other neurodegenerative diseases. With advancements in mass spectrometry coupled with bioinformatics and systems biology, neuroproteomics has led to the development of innovative techniques such as microproteomics, single-cell proteomics, and imaging mass spectrometry, which have significantly impacted neuronal biomarker research. By analyzing the complex protein interactions and alterations that occur in the injured brain, neuroproteomics provides valuable insights into the pathophysiological mechanisms underlying neurotrauma. This review explores how such insights can be harnessed to advance personalized medicine (PM) approaches, tailoring treatments based on individual patient profiles. Additionally, we highlight the potential future prospects of neuroproteomics, such as identifying novel biomarkers and developing targeted therapies by employing artificial intelligence (AI) and machine learning (ML). By shedding light on neurotrauma's current state and future directions, this review aims to stimulate further research and collaboration in this promising and transformative field.

Integrating unsupervised and supervised learning techniques to predict traumatic brain injury: A population-based study

This work aimed to identify pre-existing health conditions of patients with traumatic brain injury (TBI) and develop predictive models for the first TBI event and its external causes by employing a combination of unsupervised and supervised learning algorithms. We acquired up to five years of pre-injury diagnoses for 488,107 patients with TBI and 488,107 matched control patients who entered the emergency department or acute care hospitals between April 1st, 2002, and March 31st, 2020. Diagnoses were obtained from the Ontario Health Insurance Plan (OHIP) database which contains province-wide claims data by physicians in Ontario, Canada for inpatient and outpatient services. A screening process was conducted on the OHIP diagnostic codes to limit the subsequent analysis to codes that were predictive of TBI, which concluded that 314 codes were significantly associated with TBI. The Latent Dirichlet Allocation (LDA) model was applied to the diagnostic codes and generated an optimal number of 19 topics that concur with published literature but also suggest other unexplored areas. Estimated word-topic probabilities from the LDA model helped us detect pre-morbid conditions among patients with TBI by uncovering the underlying patterns of diagnoses, meanwhile estimated document-topic probabilities were utilized in variable creation as form of a dimension reduction. We created 19 topic scores for each patient in the cohort which were utilized along with socio-demographic factors for Random Forest binary classifier models. Test set performances evaluated using area under the receiver operating characteristic curve (AUC) were: TBI event (AUC = 0.85), external cause of injury: falls (AUC = 0.85), struck by/against (AUC = 0.83), cyclist collision (AUC = 0.76), motor vehicle collision (AUC = 0.83). Our analysis successfully demonstrated the feasibility of using machine learning to predict TBI due to various external causes and identified the most important factors that contribute to this prediction.

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

BACKGROUND

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

OBJECTIVE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

The Use of Artificial Intelligence to Predict the Prognosis of Patients Undergoing Central Nervous System Rehabilitation: A Narrative Review

Applications of machine learning in the healthcare field have become increasingly diverse. In this review, we investigated the integration of artificial intelligence (AI) in predicting the prognosis of patients with central nervous system disorders such as stroke, traumatic brain injury, and spinal cord injury. AI algorithms have shown promise in prognostic assessment, but challenges remain in achieving a higher prediction accuracy for practical clinical use. We suggest that accumulating more diverse data, including medical imaging and collaborative efforts among hospitals, can enhance the predictive capabilities of AI. As healthcare professionals become more familiar with AI, its role in central nervous system rehabilitation is expected to advance significantly, revolutionizing patient care.

Machine learning models in clinical practice for the prediction of postoperative complications after major abdominal surgery

Complications after surgery have a major impact on short- and long-term outcomes, and decades of technological advancement have not yet led to the eradication of their risk. The accurate prediction of complications, recently enhanced by the development of machine learning algorithms, has the potential to completely reshape surgical patient management. In this paper, we reflect on multiple issues facing the implementation of machine learning, from the development to the actual implementation of machine learning models in daily clinical practice, providing suggestions on the use of machine learning models for predicting postoperative complications after major abdominal surgery.

Predicting return to work after traumatic brain injury using machine learning and administrative data

BACKGROUND

Accurate patient-specific predictions on return-to-work after traumatic brain injury (TBI) can support both clinical practice and policymaking. The use of machine learning on large administrative data provides interesting opportunities to create such prognostic models.

AIM

The current study assesses whether return-to-work one year after TBI can be predicted accurately from administrative data. Additionally, this study explores how model performance and feature importance change depending on whether a distinction is made between mild and moderate-to-severe TBI.

METHODS

This study used a population-based dataset that combined discharge, claims and social security data of patients hospitalized with a TBI in Belgium during the year 2016. The prediction of TBI was attempted with three algorithms, elastic net logistic regression, random forest and gradient boosting and compared in their performance by their accuracy, sensitivity, specificity and area under the receiver operator curve (ROC AUC).

RESULTS

The distinct modelling algorithms resulted in similar results, with 83% accuracy (ROC AUC 85%) for a binary classification of employed vs. not employed and up to 76% (ROC AUC 82%) for a multiclass operationalization of employment outcome. Modelling mild and moderate-to-severe TBI separately did not result in considerable differences in model performance and feature importance. The features of main importance for return-to-work prediction were related to pre-injury employment.

DISCUSSION

While clearly offering some information beneficial for predicting return-to-work, administrative data needs to be supplemented with additional information to allow further improvement of patient-specific prognose.

Machine learning versus logistic regression for the prediction of complications after pancreatoduodenectomy

BACKGROUND

Machine learning is increasingly advocated to develop prediction models for postoperative complications. It is, however, unclear if machine learning is superior to logistic regression when using structured clinical data. Postoperative pancreatic fistula and delayed gastric emptying are the two most common complications with the biggest impact on patient condition and length of hospital stay after pancreatoduodenectomy. This study aimed to compare the performance of machine learning and logistic regression in predicting pancreatic fistula and delayed gastric emptying after pancreatoduodenectomy.

METHODS

This retrospective observational study used nationwide data from 16 centers in the Dutch Pancreatic Cancer Audit between January 2014 and January 2021. The area under the curve of a machine learning and logistic regression model for clinically relevant postoperative pancreatic fistula and delayed gastric emptying were compared.

RESULTS

Overall, 799 (16.3%) patients developed a postoperative pancreatic fistula, and 943 developed (19.2%) delayed gastric emptying. For postoperative pancreatic fistula, the area under the curve of the machine learning model was 0.74, and the area under the curve of the logistic regression model was 0.73. For delayed gastric emptying, the area under the curve of the machine learning model and logistic regression was 0.59.

CONCLUSION

Machine learning did not outperform logistic regression modeling in predicting postoperative complications after pancreatoduodenectomy.

Machine Learning to Predict Three Types of Outcomes After Traumatic Brain Injury Using Data at Admission: A Multi-Center Study for Development and Validation

The difficulty of accurately identifying patients who would benefit from promising treatments makes it challenging to prove the efficacy of novel treatments for traumatic brain injury (TBI). Although machine learning is being increasingly applied to this task, existing binary outcome prediction models are insufficient for the effective stratification of TBI patients. The aim of this study was to develop an accurate 3-class outcome prediction model to enable appropriate patient stratification. To this end, retrospective balanced data of 1200 blunt TBI patients admitted to six Japanese hospitals from January 2018 onwards (200 consecutive cases at each institution) were used for model training and validation. We incorporated 21 predictors obtained in the emergency department, including age, sex, six clinical findings, four laboratory parameters, eight computed tomography findings, and an emergency craniotomy. We developed two machine learning models (XGBoost and dense neural network) and logistic regression models to predict 3-class outcomes based on the Glasgow Outcome Scale-Extended (GOSE) at discharge. The prediction models were developed using a training dataset with n = 1000, and their prediction performances were evaluated over two validation rounds on a validation dataset (n = 80) and a test dataset (n = 120) using the bootstrap method. Of the 1200 patients in aggregate, the median patient age was 71 years, 199 (16.7%) exhibited severe TBI, and emergency craniotomy was performed on 104 patients (8.7%). The median length of stay was 13.0 days. The 3-class outcomes were good recovery/moderate disability for 709 patients (59.1%), severe disability/vegetative state in 416 patients (34.7%), and death in 75 patients (6.2%). XGBoost model performed well with 69.5% sensitivity, 82.5% accuracy, and an area under the receiver operating characteristic curve of 0.901 in the final validation. In terms of the receiver operating characteristic curve analysis, the XGBoost outperformed the neural network-based and logistic regression models slightly. In particular, XGBoost outperformed the logistic regression model significantly in predicting severe disability/vegetative state. Although each model predicted favorable outcomes accurately, they tended to miss the mortality prediction. The proposed machine learning model was demonstrated to be capable of accurate prediction of in-hospital outcomes following TBI, even with the three GOSE-based categories. As a result, it is expected to be more impactful in the development of appropriate patient stratification methods in future TBI studies than conventional binary prognostic models. Further, outcomes were predicted based on only clinical data obtained from the emergency department. However, developing a robust model with consistent performance in diverse scenarios remains challenging, and further efforts are needed to improve generalization performance.

Prediction performance of the machine learning model in predicting mortality risk in patients with traumatic brain injuries: a systematic review and meta-analysis

PURPOSE

With the in-depth application of machine learning(ML) in clinical practice, it has been used to predict the mortality risk in patients with traumatic brain injuries(TBI). However, there are disputes over its predictive accuracy. Therefore, we implemented this systematic review and meta-analysis, to explore the predictive value of ML for TBI.

METHODOLOGY

We systematically retrieved literature published in PubMed, Embase.com, Cochrane, and Web of Science as of November 27, 2022. The prediction model risk of bias(ROB) assessment tool (PROBAST) was used to assess the ROB of models and the applicability of reviewed questions. The random-effects model was adopted for the meta-analysis of the C-index and accuracy of ML models, and a bivariate mixed-effects model for the meta-analysis of the sensitivity and specificity.

RESULT

A total of 47 papers were eligible, including 156 model, with 122 newly developed ML models and 34 clinically recommended mature tools. There were 98 ML models predicting the in-hospital mortality in patients with TBI; the pooled C-index, sensitivity, and specificity were 0.86 (95% CI: 0.84, 0.87), 0.79 (95% CI: 0.75, 0.82), and 0.89 (95% CI: 0.86, 0.92), respectively. There were 24 ML models predicting the out-of-hospital mortality; the pooled C-index, sensitivity, and specificity were 0.83 (95% CI: 0.81, 0.85), 0.74 (95% CI: 0.67, 0.81), and 0.75 (95% CI: 0.66, 0.82), respectively. According to multivariate analysis, GCS score, age, CT classification, pupil size/light reflex, glucose, and systolic blood pressure (SBP) exerted the greatest impact on the model performance.

CONCLUSION

According to the systematic review and meta-analysis, ML models are relatively accurate in predicting the mortality of TBI. A single model often outperforms traditional scoring tools, but the pooled accuracy of models is close to that of traditional scoring tools. The key factors related to model performance include the accepted clinical variables of TBI and the use of CT imaging.

Machine learning algorithms for predicting outcomes of traumatic brain injury: A systematic review and meta-analysis

BACKGROUND

Traumatic brain injury (TBI) is a leading cause of death and disability worldwide. The use of machine learning (ML) has emerged as a key advancement in TBI management. This study aimed to identify ML models with demonstrated effectiveness in predicting TBI outcomes.

METHODS

We conducted a systematic review in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis statement. In total, 15 articles were identified using the search strategy. Patient demographics, clinical status, ML outcome variables, and predictive characteristics were extracted. A small meta-analysis of mortality prediction was performed, and a meta-analysis of diagnostic accuracy was conducted for ML algorithms used across multiple studies.

RESULTS

ML algorithms including support vector machine (SVM), artificial neural networks (ANN), random forest, and Naïve Bayes were compared to logistic regression (LR). Thirteen studies found significant improvement in prognostic capability using ML versus LR. The accuracy of the above algorithms was consistently over 80% when predicting mortality and unfavorable outcome measured by Glasgow Outcome Scale. Receiver operating characteristic curves analyzing the sensitivity of ANN, SVM, decision tree, and LR demonstrated consistent findings across studies. Lower admission Glasgow Coma Scale (GCS), older age, elevated serum acid, and abnormal glucose were associated with increased adverse outcomes and had the most significant impact on ML algorithms.

CONCLUSION

ML algorithms were stronger than traditional regression models in predicting adverse outcomes. Admission GCS, age, and serum metabolites all have strong predictive power when used with ML and should be considered important components of TBI risk stratification.

Use of Support Vector Machines Approach via ComBat Harmonized Diffusion Tensor Imaging for the Diagnosis and Prognosis of Mild Traumatic Brain Injury: A CENTER-TBI Study

The prediction of functional outcome after mild traumatic brain injury (mTBI) is challenging. Conventional magnetic resonance imaging (MRI) does not do a good job of explaining the variance in outcome, as many patients with incomplete recovery will have normal-appearing clinical neuroimaging. More advanced quantitative techniques such as diffusion MRI (dMRI), can detect microstructural changes not otherwise visible, and so may offer a way to improve outcome prediction. In this study, we explore the potential of linear support vector classifiers (linearSVCs) to identify dMRI biomarkers that can predict recovery after mTBI. Simultaneously, the harmonization of fractional anisotropy (FA) and mean diffusivity (MD) via ComBat was evaluated and compared for the classification performances of the linearSVCs. We included dMRI scans of 179 mTBI patients and 85 controls from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI), a multi-center prospective cohort study, up to 21 days post-injury. Patients were dichotomized according to their Extended Glasgow Outcome Scale (GOSE) scores at 6 months into complete (n = 92; GOSE = 8) and incomplete (n = 87; GOSE <8) recovery. FA and MD maps were registered to a common space and harmonized via the ComBat algorithm. LinearSVCs were applied to distinguish: (1) mTBI patients from controls and (2) mTBI patients with complete from those with incomplete recovery. The linearSVCs were trained on (1) age and sex only, (2) non-harmonized, (3) two-category-harmonized ComBat, and (4) three-category-harmonized ComBat FA and MD images combined with age and sex. White matter FA and MD voxels and regions of interest (ROIs) within the John Hopkins University (JHU) atlas were examined. Recursive feature elimination was used to identify the 10% most discriminative voxels or the 10 most discriminative ROIs for each implementation. mTBI patients displayed significantly higher MD and lower FA values than controls for the discriminative voxels and ROIs. For the analysis between mTBI patients and controls, the three-category-harmonized ComBat FA and MD voxel-wise linearSVC provided significantly higher classification scores (81.4% accuracy, 93.3% sensitivity, 80.3% F1-score, and 0.88 area under the curve [AUC], p < 0.05) compared with the classification based on age and sex only and the ROI approaches (accuracies: 59.8% and 64.8%, respectively). Similar to the analysis between mTBI patients and controls, the three-category-harmonized ComBat FA and MD maps voxelwise approach yields statistically significant prediction scores between mTBI patients with complete and those with incomplete recovery (71.8% specificity, 66.2% F1-score and 0.71 AUC, p < 0.05), which provided a modest increase in the classification score (accuracy: 66.4%) compared with the classification based on age and sex only and ROI-wise approaches (accuracy: 61.4% and 64.7%, respectively). This study showed that ComBat harmonized FA and MD may provide additional information for diagnosis and prognosis of mTBI in a multi-modal machine learning approach. These findings demonstrate that dMRI may assist in the early detection of patients at risk of incomplete recovery from mTBI.

AI-Based Decision Support System for Traumatic Brain Injury: A Survey

Traumatic brain injury (TBI) is one of the major causes of disability and mortality worldwide. Rapid and precise clinical assessment and decision-making are essential to improve the outcome and the resulting complications. Due to the size and complexity of the data analyzed in TBI cases, computer-aided data processing, analysis, and decision support systems could play an important role. However, developing such systems is challenging due to the heterogeneity of symptoms, varying data quality caused by different spatio-temporal resolutions, and the inherent noise associated with image and signal acquisition. The purpose of this article is to review current advances in developing artificial intelligence-based decision support systems for the diagnosis, severity assessment, and long-term prognosis of TBI complications.

Primer on Machine Learning in Electrophysiology

Artificial intelligence has become ubiquitous. Machine learning, a branch of artificial intelligence, leads the current technological revolution through its remarkable ability to learn and perform on data sets of varying types. Machine learning applications are expected to change contemporary medicine as they are brought into mainstream clinical practice. In the field of cardiac arrhythmia and electrophysiology, machine learning applications have enjoyed rapid growth and popularity. To facilitate clinical acceptance of these methodologies, it is important to promote general knowledge of machine learning in the wider community and continue to highlight the areas of successful application. The authors present a primer to provide an overview of common supervised (least squares, support vector machine, neural networks and random forest) and unsupervised (k-means and principal component analysis) machine learning models. The authors also provide explanations as to how and why the specific machine learning models have been used in arrhythmia and electrophysiology studies.

An efficient edge/cloud medical system for rapid detection of level of consciousness in emergency medicine based on explainable machine learning models

Emergency medicine (EM) is one of the attractive research fields in which researchers investigate their efforts to diagnose and treat unforeseen illnesses or injuries. There are many tests and observations are involved in EM. Detection of the level of consciousness is one of these observations, which can be detected using several methods. Among these methods, the automatic estimation of the Glasgow coma scale (GCS) is studied in this paper. The GCS is a medical score used to describe a patient’s level of consciousness. This type of scoring system requires medical examination that may not be available with the shortage of the medical expert. Therefore, the automatic medical calculation for a patient’s level of consciousness is highly needed. Artificial intelligence has been deployed in several applications and appears to have a high performance regarding providing automatic solutions. The main objective of this work is to introduce the edge/cloud system to improve the efficiency of the consciousness measurement through efficient local data processing. Moreover, an efficient machine learning (ML) model to predict the level of consciousness of a certain patient based on the patient’s demographic, vital signs, and laboratory tests is proposed, as well as maintaining the explainability issue using Shapley additive explanations (SHAP) that provides natural language explanation in a form that helps the medical expert to understand the final prediction. The developed ML model is validated using vital signs and laboratory tests extracted from the MIMIC III dataset, and it achieves superior performance (mean absolute error (MAE) = 0.269, mean square error (MSE) = 0.625, R² score = 0.964). The resulting model is accurate, medically intuitive, and trustworthy.

Prediction of Mortality among Patients with Isolated Traumatic Brain Injury Using Machine Learning Models in Asian Countries: An International Multi-Center Cohort Study

Traumatic brain injury (TBI) is a significant healthcare concern in several countries, accounting for a major burden of morbidity, mortality, disability, and socioeconomic losses. Although conventional prognostic models for patients with TBI have been validated, their performance has been limited. Therefore, we aimed to construct machine learning (ML) models to predict the clinical outcomes in adult patients with isolated TBI in Asian countries. The Pan-Asian Trauma Outcome Study registry was used in this study, and the data were prospectively collected from January 1, 2015, to December 31, 2020. Among a total of 6540 patients (≥ 15 years) with isolated moderate and severe TBI, 3276 (50.1%) patients were randomly included with stratification by outcomes and subgrouping variables for model evaluation, and 3264 (49.9%) patients were included for model training and validation. Logistic regression was considered as a baseline, and ML models were constructed and evaluated using the area under the precision-recall curve (AUPRC) as the primary outcome metric, area under the receiver operating characteristic curve (AUROC), and precision at fixed levels of recall. The contribution of the variables to the model prediction was measured using the SHapley Additive exPlanations (SHAP) method. The ML models outperformed logistic regression in predicting the in-hospital mortality. Among the tested models, the gradient-boosted decision tree showed the best performance (AUPRC, 0.746 [0.700-0.789]; AUROC, 0.940 [0.929-0.952]). The most powerful contributors to model prediction were the Glasgow Coma Scale, O₂ saturation, transfusion, systolic and diastolic blood pressure, body temperature, and age. Our study suggests that ML techniques might perform better than conventional multi-variate models in predicting the outcomes among adult patients with isolated moderate and severe TBI.

An end-end deep learning framework for lesion segmentation on multi-contrast MR images-an exploratory study in a rat model of traumatic brain injury

Traumatic brain injury (TBI) engenders traumatic necrosis and penumbra-areas of secondary neural injury which are crucial targets for therapeutic interventions. Segmenting manually areas of ongoing changes like necrosis, edema, hematoma, and inflammation is tedious, error-prone, and biased. Using the multi-parametric MR data from a rodent model study, we demonstrate the effectiveness of an end-end deep learning global-attention-based UNet (GA-UNet) framework for automatic segmentation and quantification of TBI lesions. Longitudinal MR scans (2 h, 1, 3, 7, 14, 30, and 60 days) were performed on eight Sprague-Dawley rats after controlled cortical injury was performed. TBI lesion and sub-regions segmentation was performed using 3D-UNet and GA-UNet. Dice statistics (DSI) and Hausdorff distance were calculated to assess the performance. MR scan variations-based (bias, noise, blur, ghosting) data augmentation was performed to develop a robust model.Training/validation median DSI for U-Net was 0.9368 with T2w and MPRAGE inputs, whereas GA-UNet had 0.9537 for the same. Testing accuracies were higher for GA-UNet than U-Net with a DSI of 0.8232 for the T2w-MPRAGE inputs.Longitudinally, necrosis remained constant while oligemia and penumbra decreased, and edema appearing around day 3 which increased with time. GA-UNet shows promise for multi-contrast MR image-based segmentation/quantification of TBI in large cohort studies.

Logistic regression technique is comparable to complex machine learning algorithms in predicting cognitive impairment related to post intensive care syndrome

To evaluate the performance of machine learning (ML) models and to compare it with logistic regression (LR) technique in predicting cognitive impairment related to post intensive care syndrome (PICS-CI). We conducted a prospective observational study of ICU patients at two tertiary hospitals. A cohort of 2079 patients was screened, and finally 481 patients were included. Seven different ML models were considered, decision tree (DT), random forest (RF), XGBoost, neural network (NN), naïve bayes (NB), and support vector machine (SVM), and compared with logistic regression (LR). Discriminative ability was evaluated by area under the receiver operating characteristic curve (AUC), calibration belt plots, and Hosmer-Lemeshow test was used to assess calibration. Decision curve analysis was performed to quantify clinical utility. Duration of delirium, poor Richards-Campbell sleep questionnaire (RCSQ) score, advanced age, and sepsis were the most frequent and important candidates risk factors for PICS-CI. All ML models showed good performance (AUC range: 0.822-0.906). NN model had the highest AUC (0.906 [95% CI 0.857-0.955]), which was slightly higher than, but not significantly different from that of LR (0.898 [95% CI 0.847-0.949]) (P > 0.05, Delong test). Given the overfitting and complexity of some ML models, the LR model was then used to develop a web-based risk calculator to aid decision-making ( https://model871010.shinyapps.io/dynnomapp/ ). In a low dimensional data, LR may yield as good performance as other complex ML models to predict cognitive impairment after ICU hospitalization.

Prognosis prediction in traumatic brain injury patients using machine learning algorithms

Predicting treatment outcomes in traumatic brain injury (TBI) patients is challenging worldwide. The present study aimed to achieve the most accurate machine learning (ML) algorithms to predict the outcomes of TBI treatment by evaluating demographic features, laboratory data, imaging indices, and clinical features. We used data from 3347 patients admitted to a tertiary trauma centre in Iran from 2016 to 2021. After the exclusion of incomplete data, 1653 patients remained. We used ML algorithms such as random forest (RF) and decision tree (DT) with ten-fold cross-validation to develop the best prediction model. Our findings reveal that among different variables included in this study, the motor component of the Glasgow coma scale, the condition of pupils, and the condition of cisterns were the most reliable features for predicting in-hospital mortality, while the patients' age takes the place of cisterns condition when considering the long-term survival of TBI patients. Also, we found that the RF algorithm is the best model to predict the short-term mortality of TBI patients. However, the generalized linear model (GLM) algorithm showed the best performance (with an accuracy rate of 82.03 ± 2.34) in predicting the long-term survival of patients. Our results showed that using appropriate markers and with further development, ML has the potential to predict TBI patients' survival in the short- and long-term.

Identification of chronic mild traumatic brain injury using resting state functional MRI and machine learning techniques

Mild traumatic brain injury (mTBI) is a major public health concern that can result in a broad spectrum of short-term and long-term symptoms. Recently, machine learning (ML) algorithms have been used in neuroscience research for diagnostics and prognostic assessment of brain disorders. The present study aimed to develop an automatic classifier to distinguish patients suffering from chronic mTBI from healthy controls (HCs) utilizing multilevel metrics of resting-state functional magnetic resonance imaging (rs-fMRI). Sixty mTBI patients and forty HCs were enrolled and allocated to training and testing datasets with a ratio of 80:20. Several rs-fMRI metrics including fractional amplitude of low-frequency fluctuation (fALFF), regional homogeneity (ReHo), degree centrality (DC), voxel-mirrored homotopic connectivity (VMHC), functional connectivity strength (FCS), and seed-based FC were generated from two main analytical categories: local measures and network measures. Statistical two-sample t-test was employed comparing between mTBI and HCs groups. Then, for each rs-fMRI metric the features were selected extracting the mean values from the clusters showing significant differences. Finally, the support vector machine (SVM) models based on separate and multilevel metrics were built and the performance of the classifiers were assessed using five-fold cross-validation and via the area under the receiver operating characteristic curve (AUC). Feature importance was estimated using Shapley additive explanation (SHAP) values. Among local measures, the range of AUC was 86.67-100% and the optimal SVM model was obtained based on combined multilevel rs-fMRI metrics and DC as a separate model with AUC of 100%. Among network measures, the range of AUC was 80.42-93.33% and the optimal SVM model was obtained based on the combined multilevel seed-based FC metrics. The SHAP analysis revealed the DC value in the left postcentral and seed-based FC value between the motor ventral network and right superior temporal as the most important local and network features with the greatest contribution to the classification models. Our findings demonstrated that different rs-fMRI metrics can provide complementary information for classifying patients suffering from chronic mTBI. Moreover, we showed that ML approach is a promising tool for detecting patients with mTBI and might serve as potential imaging biomarker to identify patients at individual level.

Clinical trial registration

[clinicaltrials.gov], identifier [NCT03241732].

Early prediction of 30- and 14-day all-cause unplanned readmissions

BACKGROUND

An unplanned readmission is a dual metric for both the cost and quality of medical care.

METHODS

We employed the random forest (RF) method to build a prediction model using a large dataset from patients' electronic health records (EHRs) from a medical center in Taiwan. The discrimination abilities between the RF and regression-based models were compared using the areas under the ROC curves (AUROC).

RESULTS

When compared with standardized risk prediction tools, the RF constructed using data readily available at admission had a marginally yet significantly better ability to identify high-risk readmissions within 30 and 14 days without compromising sensitivity and specificity. The most important predictor for 30-day readmissions was directly related to the representing factors of index hospitalization, whereas for 14-day readmissions the most important predictor was associated with a higher chronic illness burden.

CONCLUSIONS

Identifying dominant risk factors based on index admission and different readmission time intervals is crucial for healthcare planning.

Emerging Materials, Wearables, and Diagnostic Advancements in Therapeutic Treatment of Brain Diseases

Among the most critical health issues, brain illnesses, such as neurodegenerative conditions and tumors, lower quality of life and have a significant economic impact. Implantable technology and nano-drug carriers have enormous promise for cerebral brain activity sensing and regulated therapeutic application in the treatment and detection of brain illnesses. Flexible materials are chosen for implantable devices because they help reduce biomechanical mismatch between the implanted device and brain tissue. Additionally, implanted biodegradable devices might lessen any autoimmune negative effects. The onerous subsequent operation for removing the implanted device is further lessened with biodegradability. This review expands on current developments in diagnostic technologies such as magnetic resonance imaging, computed tomography, mass spectroscopy, infrared spectroscopy, angiography, and electroencephalogram while providing an overview of prevalent brain diseases. As far as we are aware, there hasn't been a single review article that addresses all the prevalent brain illnesses. The reviewer also looks into the prospects for the future and offers suggestions for the direction of future developments in the treatment of brain diseases.

Multi-Parameter Predictive Model of Mobile Robot's Battery Discharge for Intelligent Mission Planning in Multi-Robot Systems

The commercially available battery management and mission scheduling systems for fleets of autonomous mobile robots use different algorithms to calculate the current state of charge of the robot's battery. This information alone cannot be used to predict whether it will be possible for a single robot in the fleet to execute all of the scheduled missions. This paper provides insight into how to develop a universal battery discharge model based on key mission parameters, which allows for predicting the battery usage over the course of the scheduled missions and can, in turn, be used to determine which missions to delegate to other robots in the fleet, or if more robots are needed in the fleet to accomplish the production plan. The resulting model is, therefore, necessary for mission scheduling in a flexible production system, including autonomous mobile robot transportation networks.

Prognostic value of global deep white matter DTI metrics for 1-year outcome prediction in ICU traumatic brain injury patients: an MRI-COMA and CENTER-TBI combined study

PURPOSE

A reliable tool for outcome prognostication in severe traumatic brain injury (TBI) would improve intensive care unit (ICU) decision-making process by providing objective information to caregivers and family. This study aimed at designing a new classification score based on magnetic resonance (MR) diffusion metrics measured in the deep white matter between day 7 and day 35 after TBI to predict 1-year clinical outcome.

METHODS

Two multicenter cohorts (29 centers) were used. MRI-COMA cohort (NCT00577954) was split into MRI-COMA-Train (50 patients enrolled between 2006 and mid-2014) and MRI-COMA-Test (140 patients followed up in clinical routine from 2014) sub-cohorts. These latter patients were pooled with 56 ICU patients (enrolled from 2014 to 2020) from CENTER-TBI cohort (NCT02210221). Patients were dichotomised depending on their 1-year Glasgow outcome scale extended (GOSE) score: GOSE 1-3, unfavorable outcome (UFO); GOSE 4-8, favorable outcome (FO). A support vector classifier incorporating fractional anisotropy and mean diffusivity measured in deep white matter, and age at the time of injury was developed to predict whether the patients would be either UFO or FO.

RESULTS

The model achieved an area under the ROC curve of 0.93 on MRI-COMA-Train training dataset, and 49% sensitivity for 96.8% specificity in predicting UFO and 58.5% sensitivity for 97.1% specificity in predicting FO on the pooled MRI-COMA-Test and CENTER-TBI validation datasets.

CONCLUSION

The model successfully identified, with a specificity compatible with a personalized decision-making process in ICU, one in two patients who had an unfavorable outcome at 1 year after the injury, and two-thirds of the patients who experienced a favorable outcome.

An interpretable neural network for outcome prediction in traumatic brain injury

Background

Traumatic Brain Injury (TBI) is a common condition with potentially severe long-term complications, the prediction of which remains challenging. Machine learning (ML) methods have been used previously to help physicians predict long-term outcomes of TBI so that appropriate treatment plans can be adopted. However, many ML techniques are “black box”: it is difficult for humans to understand the decisions made by the model, with post-hoc explanations only identifying isolated relevant factors rather than combinations of factors. Moreover, such models often rely on many variables, some of which might not be available at the time of hospitalization.

Methods

In this study, we apply an interpretable neural network model based on tropical geometry to predict unfavorable outcomes at six months from hospitalization in TBI patients, based on information available at the time of admission.

Results

The proposed method is compared to established machine learning methods—XGBoost, Random Forest, and SVM—achieving comparable performance in terms of area under the receiver operating characteristic curve (AUC)—0.799 for the proposed method vs. 0.810 for the best black box model. Moreover, the proposed method allows for the extraction of simple, human-understandable rules that explain the model’s predictions and can be used as general guidelines by clinicians to inform treatment decisions.

Conclusions

The classification results for the proposed model are comparable with those of traditional ML methods. However, our model is interpretable, and it allows the extraction of intelligible rules. These rules can be used to determine relevant factors in assessing TBI outcomes and can be used in situations when not all necessary factors are known to inform the full model’s decision.

Machine learning did not beat logistic regression in time series prediction for severe asthma exacerbations

Early detection of severe asthma exacerbations through home monitoring data in patients with stable mild-to-moderate chronic asthma could help to timely adjust medication. We evaluated the potential of machine learning methods compared to a clinical rule and logistic regression to predict severe exacerbations. We used daily home monitoring data from two studies in asthma patients (development: n = 165 and validation: n = 101 patients). Two ML models (XGBoost, one class SVM) and a logistic regression model provided predictions based on peak expiratory flow and asthma symptoms. These models were compared with an asthma action plan rule. Severe exacerbations occurred in 0.2% of all daily measurements in the development (154/92,787 days) and validation cohorts (94/40,185 days). The AUC of the best performing XGBoost was 0.85 (0.82-0.87) and 0.88 (0.86-0.90) for logistic regression in the validation cohort. The XGBoost model provided overly extreme risk estimates, whereas the logistic regression underestimated predicted risks. Sensitivity and specificity were better overall for XGBoost and logistic regression compared to one class SVM and the clinical rule. We conclude that ML models did not beat logistic regression in predicting short-term severe asthma exacerbations based on home monitoring data. Clinical application remains challenging in settings with low event incidence and high false alarm rates with high sensitivity.

Supervised machine learning and associated algorithms: applications in orthopedic surgery

Supervised learning is the most common form of machine learning utilized in medical research. It is used to predict outcomes of interest or classify positive and/or negative cases with a known ground truth. Supervised learning describes a spectrum of techniques, ranging from traditional regression modeling to more complex tree boosting, which are becoming increasingly prevalent as the focus on "big data" develops. While these tools are becoming increasingly popular and powerful, there is a paucity of literature available that describe the strengths and limitations of these different modeling techniques. Typically, there is no formal training for health care professionals in the use of machine learning models. As machine learning applications throughout medicine increase, it is important that physicians and other health care professionals better understand the processes underlying application of these techniques. The purpose of this study is to provide an overview of commonly used supervised learning techniques with recent case examples within the orthopedic literature. An additional goal is to address disparities in the understanding of these methods to improve communication within and between research teams.

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.

Traumatic Brain Injury (TBI) Detection: Past, Present, and Future

Traumatic brain injury (TBI) can produce temporary biochemical imbalance due to leaks through cell membranes or disruption of the axoplasmic flow due to the misalignment of intracellular neurofilaments. If untreated, TBI can lead to Alzheimer's, Parkinson's, or total disability. Mild TBI (mTBI) accounts for about about 90 percent of all TBI cases. The detection of TBI as soon as it happens is crucial for successful treatment management. Neuroimaging-based tests provide only a structural and functional mapping of the brain with poor temporal resolution. Such tests may not detect mTBI. On the other hand, the electroencephalogram (EEG) provides good spatial resolution and excellent temporal resolution of the brain activities beside its portability and low cost. The objective of this paper is to provide clinicians and scientists with a one-stop source of information to quickly learn about the different technologies used for TBI detection, their advantages and limitations. Our research led us to conclude that even though EEG-based TBI detection is potentially a powerful technology, it is currently not able to detect the presence of a mTBI with high confidence. The focus of the paper is to review existing approaches and provide the reason for the unsuccessful state of EEG-based detection of mTBI.

A Machine Learning-Based Prognostic Model for the Prediction of Early Death After Traumatic Brain Injury: Comparison with the Corticosteroid Randomization After Significant Head Injury (CRASH) Model

BACKGROUND

Machine learning (ML) has been used to predict the outcomes of traumatic brain injury. However, few studies have reported the use of ML models to predict early death. This study aimed to develop ML models for early death prediction and to compare performance with the corticosteroid randomization after significant head injury (CRASH) model.

METHODS

We retrospectively reviewed traumatic brain injury patients between February 2017 and August 2021. The patients were randomly assigned to a training set and a test set. Predictive variables included clinical findings, laboratory values, and computed tomography findings. The ML models (random forest, support vector machine [SVM], logistic regression) were developed with the training set. The CRASH model is a prognostic model that was developed based on 10,008 patients included in the CRASH trial. The ML and CRASH models were applied to the test set to evaluate the performance.

RESULTS

A total of 423 patients were included; 317 and 106 patients were randomly assigned to the training and test sets, respectively. The area under the curve was highest in the SVM (0.952, 95% confidence interval = 0.906-0.990) and lowest in the CRASH model (0.942, 95% confidence interval = 0.886-0.999). There were no significant differences between the area under the curves of the ML and CRASH models (P = 0.899 for random forest vs. the CRASH model, P = 0.760 for SVM vs. the CRASH model, P = 0.806 for logistic regression vs. the CRASH model).

CONCLUSIONS

The ML models may have comparable performances compared to the CRASH model despite being developed with a smaller sample size.

Development and external validation of a clinical prediction model for survival in patients with IDH wild-type glioblastoma

OBJECTIVE

Prognostication of glioblastoma survival has become more refined due to the molecular reclassification of these tumors into isocitrate dehydrogenase (IDH) wild-type and IDH mutant. Since this molecular stratification, however, robust clinical prediction models relevant to the entire IDH wild-type glioblastoma patient population are lacking. This study aimed to provide an updated model that predicts individual survival prognosis in patients with IDH wild-type glioblastoma.

METHODS

Databases from Germany and the Netherlands provided data on 1036 newly diagnosed glioblastoma patients treated between 2012 and 2018. A clinical prediction model for all-cause mortality was developed with Cox proportional hazards regression. This model included recent glioblastoma-associated molecular markers in addition to well-known classic prognostic variables, which were updated and refined with additional categories. Model performance was evaluated according to calibration (using calibration plots and calibration slope) and discrimination (using a C-statistic) in a cross-validation procedure by country to assess external validity.

RESULTS

The German and Dutch patient cohorts consisted of 710 and 326 patients, respectively, of whom 511 (72%) and 308 (95%) had died. Three models were developed, each with increasing complexity. The final model considering age, sex, preoperative Karnofsky Performance Status, extent of resection, O6-methylguanine DNA methyltransferase (MGMT) promoter methylation status, and adjuvant therapeutic regimen showed an optimism-corrected C-statistic of 0.73 (95% confidence interval 0.71-0.75). Cross-validation between the national cohorts yielded comparable results.

CONCLUSIONS

This prediction model reliably predicts individual survival prognosis in patients with newly diagnosed IDH wild-type glioblastoma, although additional validation, especially for long-term survival, may be desired. The nomogram and web application of this model may support shared decision-making if used properly.

Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics

Defining reliable tools for early prediction of outcome is the main target for physicians to guide care decisions in patients with brain injury. The application of machine learning (ML) is rapidly increasing in this field of study, but with a poor translation to clinical practice. This is basically dependent on the uncertainty about the advantages of this novel technique with respect to traditional approaches. In this review we address the main differences between ML techniques and traditional statistics (such as logistic regression, LR) applied for predicting outcome in patients with stroke and traumatic brain injury (TBI). Thirteen papers directly addressing the different performance among ML and LR methods were included in this review. Basically, ML algorithms do not outperform traditional regression approaches for outcome prediction in brain injury. Better performance of specific ML algorithms (such as Artificial neural networks) was mainly described in the stroke domain, but the high heterogeneity in features extracted from low-dimensional clinical data reduces the enthusiasm for applying this powerful method in clinical practice. To better capture and predict the dynamic changes in patients with brain injury during intensive care courses ML algorithms should be extended to high-dimensional data extracted from neuroimaging (structural and fMRI), EEG and genetics.

Severe Acquired Brain Injury: Prognostic Factors of Discharge Outcome in Older Adults

Severe Acquired Brain Injury (sABI) is a leading cause of disability and requires intensive rehabilitation treatment. Discharge from the rehabilitation ward is a key moment in patient management. Delays in patient discharge can adversely affect hospital productivity and increase healthcare costs. The discharge should be structured from the hospital admission toward the most appropriate environment. The purpose of our study is to investigate early predictors of outcome for discharge in older adults with sABI. A retrospective study was performed on 22 patients who were admitted to an intensive neurorehabilitation unit between June 2019 and December 2021. Patients were divided into two outcome categories, good outcome (GO) or poor outcome (PO), based on discharge destination, and the possible prognostic factors were analyzed at one and two months after admission. Among the factors analyzed, changes in the Disability Rating Scale (DRS) and Level of Cognitive Functioning (LCF) at the first and second month of hospitalization were predictive of GO at discharge (DRS, p = 0.025; LCF, p = 0.011). The presence of percutaneous endoscopic gastrostomy at two months after admission was also significantly associated with PO (p = 0.038). High Body Mass Index (BMI) and the presence of sepsis at one month after admission were possible predictors of PO (BMI p = 0.048; sepsis p = 0.014). An analysis of dynamic predictors could be useful to guarantee an early evaluation of hospital discharge in frail patients with sABI.

Machine learning versus logistic regression for prognostic modelling in individuals with non-specific neck pain

PURPOSE

Prognostic models play an important clinical role in the clinical management of neck pain disorders. No study has compared the performance of modern machine learning (ML) techniques, against more traditional regression techniques, when developing prognostic models in individuals with neck pain.

METHODS

A total of 3001 participants suffering from neck pain were included into a clinical registry database. Three dichotomous outcomes of a clinically meaningful improvement in neck pain, arm pain, and disability at 3 months follow-up were used. There were 26 predictors included, five numeric and 21 categorical. Seven modelling techniques were used (logistic regression, least absolute shrinkage and selection operator [LASSO], gradient boosting [Xgboost], K nearest neighbours [KNN], support vector machine [SVM], random forest [RF], and artificial neural networks [ANN]). The primary measure of model performance was the area under the receiver operator curve (AUC) of the validation set.

RESULTS

The ML algorithm with the greatest AUC for predicting arm pain (AUC = 0.765), neck pain (AUC = 0.726), and disability (AUC = 0.703) was Xgboost. The improvement in classification AUC from stepwise logistic regression to the best performing machine learning algorithms was 0.081, 0.103, and 0.077 for predicting arm pain, neck pain, and disability, respectively.

CONCLUSION

The improvement in prediction performance between ML and logistic regression methods in the present study, could be due to the potential greater nonlinearity between baseline predictors and clinical outcome. The benefit of machine learning in prognostic modelling may be dependent on factors like sample size, variable type, and disease investigated.

Deep Learning to Predict Traumatic Brain Injury Outcomes in the Low-Resource Setting

OBJECTIVE

Traumatic brain injury (TBI) disproportionately affects low- and middle-income countries (LMICs). In these settings, accurate patient prognostication is both difficult and essential for high-quality patient care. With the ultimate goal of enhancing TBI triage in LMICs, we aim to develop the first deep learning model to predict outcomes after TBI and compare its performance with that of less complex algorithms.

METHODS

TBI patients' data were prospectively collected in Kampala, Uganda, from 2016 to 2020. To predict good versus poor outcome at hospital discharge, we created deep neural network, shallow neural network, and elastic-net regularized logistic regression models. Predictors included 13 easily acquirable clinical variables. We assessed model performance with 5-fold cross-validation to calculate areas under both the receiver operating characteristic curve and precision-recall curve (AUPRC), in addition to standardized partial AUPRC to focus on comparisons at clinically relevant operating points.

RESULTS

We included 2164 patients for model training, of which 12% had poor outcomes. The deep neural network performed best as measured by the area under the receiver operating characteristic curve (0.941) and standardized partial AUPRC in region maximizing recall (0.291), whereas the shallow neural network was best by the area under the precision-recall curve (0.770). In several other comparisons, the elastic-net regularized logistic regression was noninferior to the neural networks.

CONCLUSIONS

We present the first use of deep learning for TBI prognostication, with an emphasis on LMICs, where there is great need for decision support to allocate limited resources. Optimal algorithm selection depends on the specific clinical setting; deep learning is not a panacea, though it may have a role in these efforts.

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.