Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy. PLoS One. 2014;9:e88225. [PMID: 24520356 PMCID: PMC3919736 DOI: 10.1371/journal.pone.0088225]

TDC-2: Multimodal Foundation for Therapeutic Science

Therapeutics Data Commons (tdcommons.ai) is an open science initiative with unified datasets, AI models, and benchmarks to support research across therapeutic modalities and drug discovery and development stages. The Commons 2.0 (TDC-2) is a comprehensive overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new multimodal tasks and model frameworks, and comprehensive benchmarks. TDC-2 introduces over 1,000 multimodal datasets spanning approximately 85 million cells, pre-calculated embeddings from 5 state-of-the-art single-cell models, and a biomedical knowledge graph. TDC-2 drastically expands the coverage of ML tasks across therapeutic pipelines and 10+ new modalities, spanning but not limited to single-cell gene expression data, clinical trial data, peptide sequence data, peptidomimetics protein-peptide interaction data regarding newly discovered ligands derived from AS-MS spectroscopy, novel 3D structural data for proteins, and cell-type-specific protein-protein interaction networks at single-cell resolution. TDC-2 introduces multimodal data access under an API-first design using the model-view-controller paradigm. TDC-2 introduces 7 novel ML tasks with fine-grained biological contexts: contextualized drug-target identification, single-cell chemical/genetic perturbation response prediction, protein-peptide binding affinity prediction task, and clinical trial outcome prediction task, which introduce antigen-processing-pathway-specific, cell-type-specific, peptide-specific, and patient-specific biological contexts. TDC-2 also releases benchmarks evaluating 15+ state-of-the-art models across 5+ new learning tasks evaluating models on diverse biological contexts and sampling approaches. Among these, TDC-2 provides the first benchmark for context-specific learning. TDC-2, to our knowledge, is also the first to introduce a protein-peptide binding interaction benchmark.

Developing machine learning models to predict multi-class functional outcomes and death three months after stroke in Sweden

Globally, stroke is the third-leading cause of mortality and disability combined, and one of the costliest diseases in society. More accurate predictions of stroke outcomes can guide healthcare organizations in allocating appropriate resources to improve care and reduce both the economic and social burden of the disease. We aim to develop and evaluate the performance and explainability of three supervised machine learning models and the traditional multinomial logistic regression (mLR) in predicting functional dependence and death three months after stroke, using routinely-collected data. This prognostic study included adult patients, registered in the Swedish Stroke Registry (Riksstroke) from 2015 to 2020. Riksstroke contains information on stroke care and outcomes among patients treated in hospitals in Sweden. Prognostic factors (features) included demographic characteristics, pre-stroke functional status, cardiovascular risk factors, medications, acute care, stroke type, and severity. The outcome was measured using the modified Rankin Scale at three months after stroke (a scale of 0-2 indicates independent, 3-5 dependent, and 6 dead). Outcome prediction models included support vector machines, artificial neural networks (ANN), eXtreme Gradient Boosting (XGBoost), and mLR. The models were trained and evaluated on 75% and 25% of the dataset, respectively. Model predictions were explained using SHAP values. The study included 102,135 patients (85.8% ischemic stroke, 53.3% male, mean age 75.8 years, and median NIHSS of 3). All models demonstrated similar overall accuracy (69%-70%). The ANN and XGBoost models performed significantly better than the mLR in classifying dependence with F1-scores of 0.603 (95% CI; 0.594-0.611) and 0.577 (95% CI; 0.568-0.586), versus 0.544 (95% CI; 0.545-0.563) for the mLR model. The factors that contributed most to the predictions were expectedly similar in the models, based on clinical knowledge. Our ANN and XGBoost models showed a modest improvement in prediction performance and explainability compared to mLR using routinely-collected data. Their improved ability to predict functional dependence may be of particular importance for the planning and organization of acute stroke care and rehabilitation.

Predicting the complexity and mortality of polytrauma patients with machine learning models

We aim to develop machine learning (ML) models for predicting the complexity and mortality of polytrauma patients using clinical features, including physician diagnoses and physiological data. We conducted a retrospective analysis of a cohort comprising 756 polytrauma patients admitted to the intensive care unit (ICU) at Pizhou People's Hospital Trauma Center, Jiangsu, China between 2020 and 2022. Clinical parameters encompassed demographics, vital signs, laboratory values, clinical scores and physician diagnoses. The two primary outcomes considered were mortality and complexity. We developed ML models to predict polytrauma mortality or complexity using four ML algorithms, including Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN) and eXtreme Gradient Boosting (XGBoost). We assessed the models' performance and compared the optimal ML model against three existing trauma evaluation scores, including Injury Severity Score (ISS), Trauma Index (TI) and Glasgow Coma Scale (GCS). In addition, we identified several important clinical predictors that made contributions to the prognostic models. The XGBoost-based polytrauma mortality prediction model demonstrated a predictive ability with an accuracy of 90% and an F-score of 88%, outperforming SVM, RF and ANN models. In comparison to conventional scoring systems, the XGBoost model had substantial improvements in predicting the mortality of polytrauma patients. External validation yielded strong stability and generalization with an accuracy of up to 91% and an AUC of 82%. To predict polytrauma complexity, the XGBoost model maintained its performance over other models and scoring systems with good calibration and discrimination abilities. Feature importance analysis highlighted several clinical predictors of polytrauma complexity and mortality, such as Intracranial hematoma (ICH). Leveraging ML algorithms in polytrauma care can enhance the prognostic estimation of polytrauma patients. This approach may have potential value in the management of polytrauma patients.

The Artificial Intelligence Revolution in Stroke Care: A Decade of Scientific Evidence in Review

BACKGROUND

The emergence of artificial intelligence (AI) has significantly influenced the diagnostic evaluation of stroke and has revolutionized acute stroke care delivery. The scientific evidence evaluating the role of AI, especially in areas of stroke treatment and rehabilitation is limited but continues to accumulate. We performed a systemic review of current scientific evidence evaluating the use of AI in stroke evaluation and care and examined the publication trends during the past decade.

METHODS

A systematic search of electronic databases was conducted to identify all studies published from 2012 to 2022 that incorporated AI in any aspect of stroke care. Studies not directly relevant to stroke care in the context of AI and duplicate studies were excluded. The level of evidence and publication trends were examined.

RESULTS

A total of 623 studies were examined, including 101 reviews (16.2%), 9 meta-analyses (1.4%), 140 original articles on AI methodology (22.5%), 2 case reports (0.3%), 2 case series (0.3%), 31 case-control studies (5%), 277 cohort studies (44.5%), 16 cross-sectional studies (2.6%), and 45 experimental studies (7.2%). The highest published area of AI in stroke was diagnosis (44.1%) and the lowest was rehabilitation (12%). A 10-year trend analysis revealed a significant increase in AI literature in stroke care.

CONCLUSIONS

Most research on AI is in the diagnostic area of stroke care, with a recent noteworthy trend of increased research focus on stroke treatment and rehabilitation.

Integrating clinical pharmacology and artificial intelligence: potential benefits, challenges, and role of clinical pharmacologists

INTRODUCTION

The integration of artificial intelligence (AI) into clinical pharmacology could be a potential approach for accelerating drug discovery and development, improving patient care, and streamlining medical research processes.

AREAS COVERED

We reviewed the current state of AI applications in clinical pharmacology, focusing on drug discovery and development, precision medicine, pharmacovigilance, and other ventures. Key AI applications in clinical pharmacology are examined, including machine learning, natural language processing, deep learning, and reinforcement learning etc. Additionally, the evolving role of clinical pharmacologists, ethical considerations, and challenges in implementing AI in clinical pharmacology are discussed.

EXPERT OPINION

The AI could be instrumental in accelerating drug discovery, predicting drug safety and efficacy, and optimizing clinical trial designs. It can play a vital role in precision medicine by helping in personalized drug dosing, treatment selection, and predicting drug response based on genetic, clinical, and environmental factors. The role of AI in pharmacovigilance, such as signal detection and adverse event prediction, is also promising. The collaboration between clinical pharmacologists and AI experts also poses certain ethical and practical challenges. Clinical pharmacologists can be instrumental in shaping the future of AI-driven clinical pharmacology and contribute to the improvement of healthcare systems.

Evaluating the Stroke Risk of Patients using Machine Learning: A New Perspective from Sichuan and Chongqing

Stroke is the leading cause of death and disability among people in China, and it leads to heavy burdens for patients, their families and society. An accurate prediction of the risk of stroke has important implications for early intervention and treatment. In light of recent advances in machine learning, the application of this technique in stroke prediction has achieved plentiful promising results. To detect the relationship between potential factors and the risk of stroke and examine which machine learning method significantly can enhance the prediction accuracy of stroke. We employed six machine learning methods including logistic regression, naive Bayes, decision tree, random forest, K-nearest neighbor and support vector machine, to model and predict the risk of stroke. Participants were 233 patients from Sichuan and Chongqing. Four indicators (accuracy, precision, recall and F1 metric) were examined to evaluate the predictive performance of the different models. The empirical results indicate that random forest yields the best accuracy, recall and F1 in predicting the risk of stroke, with an accuracy of .7548, precision of .7805, recall of .7619 and F1 of .7711. Additionally, the findings show that age, cerebral infarction, PM 8 (an anti-atrial fibrillation drug), and drinking are independent risk factors for stroke. Further studies should adopt a broader assortment of machine learning methods to analyze the risk of stroke, by which better accuracy can be expected. In particular, RF can successfully enhance the forecasting accuracy for stroke.

Uncertainty-aware deep learning for trustworthy prediction of long-term outcome after endovascular thrombectomy

Acute ischemic stroke (AIS) is a leading global cause of mortality and morbidity. Improving long-term outcome predictions after thrombectomy can enhance treatment quality by supporting clinical decision-making. With the advent of interpretable deep learning methods in recent years, it is now possible to develop trustworthy, high-performing prediction models. This study introduces an uncertainty-aware, graph deep learning model that predicts endovascular thrombectomy outcomes using clinical features and imaging biomarkers. The model targets long-term functional outcomes, defined by the three-month modified Rankin Score (mRS), and mortality rates. A sample of 220 AIS patients in the anterior circulation who underwent endovascular thrombectomy (EVT) was included, with 81 (37%) demonstrating good outcomes (mRS ≤ 2). The performance of the different algorithms evaluated was comparable, with the maximum validation under the curve (AUC) reaching 0.87 using graph convolutional networks (GCN) for mRS prediction and 0.86 using fully connected networks (FCN) for mortality prediction. Moderate performance was obtained at admission (AUC of 0.76 using GCN), which improved to 0.84 post-thrombectomy and to 0.89 a day after stroke. Reliable uncertainty prediction of the model could be demonstrated.

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.

Predicting stroke outcome: A case for multimodal deep learning methods with tabular and CT Perfusion data

MOTIVATION

Acute ischemic stroke is one of the leading causes of morbidity and disability worldwide, often followed by a long rehabilitation period. To improve and personalize stroke rehabilitation, it is essential to provide a reliable prognosis to caregivers and patients. Deep learning techniques might improve the predictions by incorporating different data modalities. We present a multimodal approach to predict the functional status of acute ischemic stroke patients after their discharge based on tabular data and CT perfusion imaging.

METHODS

We conducted experiments on tabular, imaging, and multimodal deep learning architectures to predict dichotomized mRS scores 3 months after the event. The dataset was collected from a Dutch hospital and includes 98 CVA patients with a visible occlusion on their CT perfusion scan. Tabular data is based on the Dutch Acute Stroke Audit data, and imaging data consists of summed-up CT perfusion maps.

RESULTS

On the tabular data, TabNet outperformed our baselines with an AUC of 0.71, while ResNet-10 on the imaging data performed comparably with an AUC of 0.70. Our implementation of the multimodal DAFT architecture outperforms baselines as well as comparable studies by achieving an 0.75 AUC, and 0.80 F1 score. This was achieved with a final model of less than a hundred thousand optimizable parameters, and a dataset less than half the size of reference papers.

CONCLUSION

Overall, we demonstrate the feasibility of predicting the functional outcome for ischemic stroke patients and the usability of multimodal deep learning architectures for this purpose.

Dialysis resource allocation in critical care: the impact of the COVID-19 pandemic and the promise of big data analytics

The COVID-19 pandemic resulted in an unprecedented burden on intensive care units (ICUs). With increased demands and limited supply, critical care resources, including dialysis machines, became scarce, leading to the undertaking of value-based cost-effectiveness analyses and the rationing of resources to deliver patient care of the highest quality. A high proportion of COVID-19 patients admitted to the ICU required dialysis, resulting in a major burden on resources such as dialysis machines, nursing staff, technicians, and consumables such as dialysis filters and solutions and anticoagulation medications. Artificial intelligence (AI)-based big data analytics are now being utilized in multiple data-driven healthcare services, including the optimization of healthcare system utilization. Numerous factors can impact dialysis resource allocation to critically ill patients, especially during public health emergencies, but currently, resource allocation is determined using a small number of traditional factors. Smart analytics that take into account all the relevant healthcare information in the hospital system and patient outcomes can lead to improved resource allocation, cost-effectiveness, and quality of care. In this review, we discuss dialysis resource utilization in critical care, the impact of the COVID-19 pandemic, and how AI can improve resource utilization in future public health emergencies. Research in this area should be an important priority.

End to end stroke triage using cerebrovascular morphology and machine learning

Background

Rapid and accurate triage of acute ischemic stroke (AIS) is essential for early revascularization and improved patient outcomes. Response to acute reperfusion therapies varies significantly based on patient-specific cerebrovascular anatomy that governs cerebral blood flow. We present an end-to-end machine learning approach for automatic stroke triage.

Methods

Employing a validated convolutional neural network (CNN) segmentation model for image processing, we extract each patient's cerebrovasculature and its morphological features from baseline non-invasive angiography scans. These features are used to detect occlusion's presence and the site automatically, and for the first time, to estimate collateral circulation without manual intervention. We then use the extracted cerebrovascular features along with commonly used clinical and imaging parameters to predict the 90 days functional outcome for each patient.

Results

The CNN model achieved a segmentation accuracy of 94% based on the Dice similarity coefficient (DSC). The automatic stroke detection algorithm had a sensitivity and specificity of 92% and 94%, respectively. The models for occlusion site detection and automatic collateral grading reached 96% and 87.2% accuracy, respectively. Incorporating the automatically extracted cerebrovascular features significantly improved the 90 days outcome prediction accuracy from 0.63 to 0.83.

Conclusion

The fast, automatic, and comprehensive model presented here can improve stroke diagnosis, aid collateral assessment, and enhance prognostication for treatment decisions, using cerebrovascular morphology.

Recombination of the right cerebral cortex in patients with left side USN after stroke: fNIRS evidence from resting state

Objective

Unilateral spatial neglect (USN) is an impaired contralesional stimulus detection, response, or action, causing functional disability. After a stroke, the right hemisphere experiences USN more noticeably, severely, and persistently than the left. However, few studies using fNIRS have been reported in cases of USN. This study aimed to confirm weaker RSFC in USN and investigate the potential inherent features in hemodynamic fluctuations that may be associated with USN. Furthermore, these features were combined into a mathematical model for more accurate classification.

Methods

A total of 33 stroke patients with right-sided brain damage were chosen, of whom 12 had non-USN after stroke, and 21 had USN after stroke (the USN group). Graph theory was used to evaluate the hemodynamic signals of the brain's right cerebral cortex during rest. Furthermore, a support vector machine model was built to categorize the subjects into two groups based on the chosen network properties.

Results

First, mean functional connectivity was lower in the USN group (0.745 ± 0.239) than in the non-USN group (0.843 ± 0.254) (t = -4.300, p < 0.001). Second, compared with the non-USN group, USN patients had a larger clustering coefficient (C) (t = 3.145, p < 0.001), local efficiency (LE) (t = 3.189, p < 0.001), and smaller global efficiency (GE) (t = 3.047, p < 0.001). Notably, there were differences in characteristic path length (L) and small worldness (σ) values between the two groups at certain thresholds, mainly as higher L (t = 3.074, p < 0.001) and lower small worldness (σ) values (t = 2.998, p < 0.001) in USN patients compared with non-USN patients. Finally, the classification accuracy of the SVM model based on AUC aC (t = -2.259, p = 0.031) and AUC aLE (t = -2.063, p = 0.048) was 85%, the sensitivity was 75%, and the specificity was 89%.

Conclusion

The functional network architecture of the right cerebral cortex exhibits significant topological alterations in individuals with USN following stroke, and the sensitivity index based on the small-world property AUC may be utilized to identify these patients accurately.

Comprehensive analysis of clinical data for COVID-19 outcome estimation with machine learning models

COVID-19 is a global threat for the healthcare systems due to the rapid spread of the pathogen that causes it. In such situation, the clinicians must take important decisions, in an environment where medical resources can be insufficient. In this task, the computer-aided diagnosis systems can be very useful not only in the task of supporting the clinical decisions but also to perform relevant analyses, allowing them to understand better the disease and the factors that can identify the high risk patients. For those purposes, in this work, we use several machine learning algorithms to estimate the outcome of COVID-19 patients given their clinical information. Particularly, we perform 2 different studies: the first one estimates whether the patient is at low or at high risk of death whereas the second estimates if the patient needs hospitalization or not. The results of the analyses of this work show the most relevant features for each studied scenario, as well as the classification performance of the considered machine learning models. In particular, the XGBoost algorithm is able to estimate the need for hospitalization of a patient with an AUC-ROC of 0 . 8415 ± 0 . 0217 while it can also estimate the risk of death with an AUC-ROC of 0 . 7992 ± 0 . 0104 . Results have demonstrated the great potential of the proposal to determine those patients that need a greater amount of medical resources for being at a higher risk. This provides the healthcare services with a tool to better manage their resources.

Machine learning prediction model for treatment responders in patients with primary biliary cholangitis

Background and Aim

Treatment response to ursodeoxycholic acid may predict the prognosis of patients with primary biliary cholangitis (PBC). Recent studies have suggested the benefits of using machine learning (ML) to forecast complex medical predictions. We aimed to predict treatment response in patients with PBC using ML and pretreatment data.

Methods

We conducted a single-center retrospective study and collected data from 194 patients with PBC who were followed up for at least 12 months after treatment initiation. Patient data were analyzed with five ML models, namely random forest, extreme gradient boosting (XGB), decision tree, naïve Bayes, or logistic regression, to predict treatment response using the Paris II criteria. The established models were assessed using an out-of-sample validation. The area under the curve (AUC) was used to evaluate the efficacy of each algorithm. Overall survival and liver-related deaths were analyzed using Kaplan-Meier analysis.

Results

Compared to logistic regression (AUC = 0.595, P = 0.0219, 0.031 models), ML analyses showed significantly high AUC in the random forest (AUC = 0.84) and XGB (AUC = 0.83) models; however, the AUC was not significantly high for decision tree (AUC = 0.633) or naïve Bayes (AUC = 0.584) models. Kaplan-Meier analysis showed significantly improved prognoses in patients predicted to achieve the Paris II criteria by XGB (log-rank = 0.005 and 0.007).

Conclusion

ML algorithms could improve treatment response prediction using pretreatment data, which could lead to better prognoses. In addition, the ML model using XGB could predict the prognosis of patients before treatment initiation.

Predicting poststroke dyskinesia with resting-state functional connectivity in the motor network

SIGNIFICANCE

Motor function evaluation is essential for poststroke dyskinesia rehabilitation. Neuroimaging techniques combined with machine learning help decode a patient's functional status. However, more research is needed to investigate how individual brain function information predicts the dyskinesia degree of stroke patients.

AIM

We investigated stroke patients' motor network reorganization and proposed a machine learning-based method to predict the patients' motor dysfunction.

APPROACH

Near-infrared spectroscopy (NIRS) was used to measure hemodynamic signals of the motor cortex in the resting state (RS) from 11 healthy subjects and 31 stroke patients, 15 with mild dyskinesia (Mild), and 16 with moderate-to-severe dyskinesia (MtS). The graph theory was used to analyze the motor network characteristics.

RESULTS

The small-world properties of the motor network were significantly different between groups: (1) clustering coefficient, local efficiency, and transitivity: MtS > Mild > Healthy and (2) global efficiency: MtS < Mild < Healthy. These four properties linearly correlated with patients' Fugl-Meyer Assessment scores. Using the small-world properties as features, we constructed support vector machine (SVM) models that classified the three groups of subjects with an accuracy of 85.7%.

CONCLUSIONS

Our results show that NIRS, RS functional connectivity, and SVM together constitute an effective method for assessing the poststroke dyskinesia degree at the individual level.

Machine Learning Logistic Regression Model for Early Decision Making in Referral of Children with Cervical Lymphadenopathy Suspected of Lymphoma

While cervical lymphadenopathy is common in children, a decision model for detecting high-grade lymphoma is lacking. Previously reported individual lymphoma-predicting factors and multivariate models were not sufficiently discriminative for clinical application. To develop a diagnostic scoring tool, we collected data from all children with cervical lymphadenopathy referred to our national pediatric oncology center within 30 months (n = 182). Thirty-nine putative lymphoma-predictive factors were investigated. The outcome groups were classical Hodgkin lymphoma (cHL), nodular lymphocyte-predominant Hodgkin lymphoma (NLPHL), non-Hodgkin lymphoma (NHL), other malignancies, and a benign group. We integrated the best univariate predicting factors into a multivariate, machine learning model. Logistic regression allocated each variable a weighing factor. The model was tested in a different patient cohort (n = 60). We report a 12-factor diagnostic model with a sensitivity of 95% (95% CI 89-98%) and a specificity of 88% (95% CI 77-94%) for detecting cHL and NHL. Our 12-factor diagnostic scoring model is highly sensitive and specific in detecting high-grade lymphomas in children with cervical lymphadenopathy. It may enable fast referral to a pediatric oncologist in patients with high-grade lymphoma and may reduce the number of referrals and unnecessary invasive procedures in children with benign lymphadenopathy.

The top 100 most cited articles on artificial intelligence in radiology: a bibliometric analysis

AIM

To identify the most influential publications relating to artificial intelligence (AI) in radiology in order to identify current trends in the literature and to highlight areas requiring further research.

MATERIALS AND METHODS

A retrospective bibliometric analysis was performed of the top 100 most cited articles on this topic. Data pertaining to year of publication, publishing journal, journal impact factor, authorship, article title, institution, country, type of article, article subject, and keywords were collected.

RESULTS

The number of citations per article for the top 100 list ranged from 254 to 3,576 (median 353). The number of citations per year, per article ranged from 10.4 to 894 (median 65.6). The majority of articles (n=62) were published within the last 10 years. The USA was the most common country of origin (n=44). The journal with the greatest number of articles was IEEE Transactions On Medical Imaging (n=38). University Medical Center Utrecht contributed the greatest number of articles (n=6). There were 92 original research articles, 52 of which were clinical studies. The most common clinical subjects were neuroimaging (n=25) and oncology (n=16). The most common keyword used was "deep learning" (n=34).

CONCLUSION

This study provides an in-depth analysis of the top 100 most-cited papers on the use of AI in radiology. It also provides researchers with detailed insight into the current influential papers in this field, the characteristics of those studies, as well as potential future trends in this fast-developing area of radiology.

A Machine Learning Approach to Support Urgent Stroke Triage Using Administrative Data and Social Determinants of Health at Hospital Presentation: Retrospective Study

BACKGROUND

The key to effective stroke management is timely diagnosis and triage. Machine learning (ML) methods developed to assist in detecting stroke have focused on interpreting detailed clinical data such as clinical notes and diagnostic imaging results. However, such information may not be readily available when patients are initially triaged, particularly in rural and underserved communities.

OBJECTIVE

This study aimed to develop an ML stroke prediction algorithm based on data widely available at the time of patients' hospital presentations and assess the added value of social determinants of health (SDoH) in stroke prediction.

METHODS

We conducted a retrospective study of the emergency department and hospitalization records from 2012 to 2014 from all the acute care hospitals in the state of Florida, merged with the SDoH data from the American Community Survey. A case-control design was adopted to construct stroke and stroke mimic cohorts. We compared the algorithm performance and feature importance measures of the ML models (ie, gradient boosting machine and random forest) with those of the logistic regression model based on 3 sets of predictors. To provide insights into the prediction and ultimately assist care providers in decision-making, we used TreeSHAP for tree-based ML models to explain the stroke prediction.

RESULTS

Our analysis included 143,203 hospital visits of unique patients, and it was confirmed based on the principal diagnosis at discharge that 73% (n=104,662) of these patients had a stroke. The approach proposed in this study has high sensitivity and is particularly effective at reducing the misdiagnosis of dangerous stroke chameleons (false-negative rate <4%). ML classifiers consistently outperformed the benchmark logistic regression in all 3 input combinations. We found significant consistency across the models in the features that explain their performance. The most important features are age, the number of chronic conditions on admission, and primary payer (eg, Medicare or private insurance). Although both the individual- and community-level SDoH features helped improve the predictive performance of the models, the inclusion of the individual-level SDoH features led to a much larger improvement (area under the receiver operating characteristic curve increased from 0.694 to 0.823) than the inclusion of the community-level SDoH features (area under the receiver operating characteristic curve increased from 0.823 to 0.829).

CONCLUSIONS

Using data widely available at the time of patients' hospital presentations, we developed a stroke prediction model with high sensitivity and reasonable specificity. The prediction algorithm uses variables that are routinely collected by providers and payers and might be useful in underresourced hospitals with limited availability of sensitive diagnostic tools or incomplete data-gathering capabilities.

Henry gas solubility optimization double machine learning classifier for neurosurgical patients

This study aims to predict head trauma outcome for Neurosurgical patients in children, adults, and elderly people. As Machine Learning (ML) algorithms are helpful in healthcare field, a comparative study of various ML techniques is developed. Several algorithms are utilized such as k-nearest neighbor, Random Forest (RF), C4.5, Artificial Neural Network, and Support Vector Machine (SVM). Their performance is assessed using anonymous patients' data. Then, a proposed double classifier based on Henry Gas Solubility Optimization (HGSO) is developed with Aquila optimizer (AQO). It is implemented for feature selection to classify patients' outcome status into four states. Those are mortality, morbidity, improved, or the same. The double classifiers are evaluated via various performance metrics including recall, precision, F-measure, accuracy, and sensitivity. Another contribution of this research is the original use of hybrid technique based on RF-SVM and HGSO to predict patient outcome status with high accuracy. It determines outcome status relationship with age and mode of trauma. The algorithm is tested on more than 1000 anonymous patients' data taken from a Neurosurgical unit of Mansoura International Hospital, Egypt. Experimental results show that the proposed method has the highest accuracy of 99.2% (with population size = 30) compared with other classifiers.

Deep Learning in Ischemic Stroke Imaging Analysis: A Comprehensive Review

Ischemic stroke is a cerebrovascular disease with a high morbidity and mortality rate, which poses a serious challenge to human health and life. Meanwhile, the management of ischemic stroke remains highly dependent on manual visual analysis of noncontrast computed tomography (CT) or magnetic resonance imaging (MRI). However, artifacts and noise of the equipment as well as the radiologist experience play a significant role on diagnostic accuracy. To overcome these defects, the number of computer-aided diagnostic (CAD) methods for ischemic stroke is increasing substantially during the past decade. Particularly, deep learning models with massive data learning capabilities are recognized as powerful auxiliary tools for the acute intervention and guiding prognosis of ischemic stroke. To select appropriate interventions, facilitate clinical practice, and improve the clinical outcomes of patients, this review firstly surveys the current state-of-the-art deep learning technology. Then, we summarized the major applications in acute ischemic stroke imaging, particularly in exploring the potential function of stroke diagnosis and multimodal prognostication. Finally, we sketched out the current problems and prospects.

Predicting futile recanalization, malignant cerebral edema, and cerebral herniation using intelligible ensemble machine learning following mechanical thrombectomy for acute ischemic stroke

Purpose

To establish an ensemble machine learning (ML) model for predicting the risk of futile recanalization, malignant cerebral edema (MCE), and cerebral herniation (CH) in patients with acute ischemic stroke (AIS) who underwent mechanical thrombectomy (MT) and recanalization.

Methods

This prospective study included 110 patients with premorbid mRS ≤ 2 who met the inclusion criteria. Futile recanalization was defined as a 90-day modified Rankin Scale score &gt;2. Clinical and imaging data were used to construct five ML models that were fused into a logistic regression algorithm using the stacking method (LR-Stacking). We added the Shapley Additive Explanation method to display crucial factors and explain the decision process of models for each patient. Prediction performances were compared using area under the receiver operating characteristic curve (AUC), F1-score, and decision curve analysis (DCA).

Results

A total of 61 patients (55.5%) experienced futile recanalization, and 34 (30.9%) and 22 (20.0%) patients developed MCE and CH, respectively. In test set, the AUCs for the LR-Stacking model were 0.949, 0.885, and 0.904 for the three outcomes mentioned above. The F1-scores were 0.882, 0.895, and 0.909, respectively. The DCA showed that the LR-Stacking model provided more net benefits for predicting MCE and CH. The most important factors were the hypodensity volume and proportion in the corresponding vascular supply area.

Conclusion

Using the ensemble ML model to analyze the clinical and imaging data of AIS patients with successful recanalization at admission and within 24 h after MT allowed for accurately predicting the risks of futile recanalization, MCE, and CH.

Dynamic Prediction of Mechanical Thrombectomy Outcome for Acute Ischemic Stroke Patients Using Machine Learning

The unfavorable outcome of acute ischemic stroke (AIS) with large vessel occlusion (LVO) is related to clinical factors at multiple time points. However, predictive models used for dynamically predicting unfavorable outcomes using clinically relevant preoperative and postoperative time point variables have not been developed. Our goal was to develop a machine learning (ML) model for the dynamic prediction of unfavorable outcomes. We retrospectively reviewed patients with AIS who underwent a consecutive mechanical thrombectomy (MT) from three centers in China between January 2014 and December 2018. Based on the eXtreme gradient boosting (XGBoost) algorithm, we used clinical characteristics on admission (“Admission” Model) and additional variables regarding intraoperative management and the postoperative National Institute of Health stroke scale (NIHSS) score (“24-Hour” Model, “3-Day” Model and “Discharge” Model). The outcome was an unfavorable outcome at the three-month mark (modified Rankin scale, mRS 3–6: unfavorable). The area under the receiver operating characteristic curve and Brier scores were the main evaluating indexes. The unfavorable outcome at the three-month mark was observed in 156 (62.0%) of 238 patients. These four models had a high accuracy in the range of 75.0% to 87.5% and had a good discrimination with AUC in the range of 0.824 to 0.945 on the testing set. The Brier scores of the four models ranged from 0.122 to 0.083 and showed a good predictive ability on the testing set. This is the first dynamic, preoperative and postoperative predictive model constructed for AIS patients who underwent MT, which is more accurate than the previous prediction model. The preoperative model could be used to predict the clinical outcome before MT and support the decision to perform MT, and the postoperative models would further improve the predictive accuracy of the clinical outcome after MT and timely adjust therapeutic strategies.

Use artificial neural network to recommend the lumbar spinal endoscopic surgical corridor

Objectives

The transforaminal and interlaminar approaches are the two main surgical corridors of full endoscopic lumbar surgery. However, there are no quantifying methods for assessing the best surgical approach for each patient. This study aimed to establish an artificial intelligence (AI) model using an artificial neural network (ANN).

Materials and Methods

Patients who underwent full endoscopic lumbar spinal surgery were enrolled in this research. Fourteen pre-operative factors were fed into the ANN. A three-layer deep neural network was constructed. Patient data were divided into the training, validation, and testing datasets.

Results

There were 899 patients enrolled. The accuracy of the training, validation, and test datasets were 87.3%, 85.5%, and 85.0%, respectively. The positive predictive values for the transforaminal and interlaminar approaches were 85.1% and 89.1%, respectively. The area under the curve of the receiver operating characteristic was 0.91. The SHapley Additive exPlanations algorithm was utilized to explain the relative importance of each factor. The surgical lumbar level was the most important factor, followed by herniated disc localization and migrating disc zone level.

Conclusion

ANN can effectively learn from the choice of an experienced spinal endoscopic surgeon and can accurately predict the appropriate surgical approach.

Predicting the Mortality of ICU Patients by Topic Model with Machine-Learning Techniques

Predicting clinical patients’ vital signs is a leading critical issue in intensive care units (ICUs) related studies. Early prediction of the mortality of ICU patients can reduce the overall mortality and cost of complication treatment. Some studies have predicted mortality based on electronic health record (EHR) data by using machine learning models. However, the semi-structured data (i.e., patients’ diagnosis data and inspection reports) is rarely used in these models. This study utilized data from the Medical Information Mart for Intensive Care III. We used a Latent Dirichlet Allocation (LDA) model to classify text in the semi-structured data of some particular topics and established and compared the classification and regression trees (CART), logistic regression (LR), multivariate adaptive regression splines (MARS), random forest (RF), and gradient boosting (GB). A total of 46,520 ICU Patients were included, with 11.5% mortality in the Medical Information Mart for Intensive Care III group. Our results revealed that the semi-structured data (diagnosis data and inspection reports) of ICU patients contain useful information that can assist clinical doctors in making critical clinical decisions. In addition, in our comparison of five machine learning models (CART, LR, MARS, RF, and GB), the GB model showed the best performance with the highest area under the receiver operating characteristic curve (AUROC) (0.9280), specificity (93.16%), and sensitivity (83.25%). The RF, LR, and MARS models showed better performance (AUROC are 0.9096, 0.8987, and 0.8935, respectively) than the CART (0.8511). The GB model showed better performance than other machine learning models (CART, LR, MARS, and RF) in predicting the mortality of patients in the intensive care unit. The analysis results could be used to develop a clinically useful decision support system.

FeMA: Feature matching auto-encoder for predicting ischaemic stroke evolution and treatment outcome

Although, predicting ischaemic stroke evolution and treatment outcome provide important information one step towards individual treatment planning, classifying functional outcome and modelling the brain tissue evolution remains a challenge due to data complexity and visually subtle changes in the brain. We propose a novel deep learning approach, Feature Matching Auto-encoder (FeMA) that consists of two stages, predicting ischaemic stroke evolution at one week without voxel-wise annotation and predicting ischaemic stroke treatment outcome at 90 days from a baseline scan. In the first stage, we introduce feature similarity and consistency objective, and in the second stage, we show that adding stroke evolution information increase the performance of functional outcome prediction. Comparative experiments demonstrate that our proposed method is more effective to extract representative follow-up features and achieves the best results for functional outcome of stroke treatment.

Persistent Hemodynamic Depression After Carotid Artery Stenting: A Review and Update

According to the American Heart Association, ischemic stroke is the second leading cause of death globally and is responsible for approximately 11% of deaths. Carotid endarterectomy (CEA) is the standard treatment for moderate or severe extracranial internal carotid artery (ICA) stenoses. With the development of materials and technology in neurointervention, the Centers for Medicare and Medicaid Services (CMS) have proposed that carotid artery stenting (CAS) can serve as an alternative treatment for CEA. As CAS is widely used worldwide, comorbidities, especially persistent hemodynamic depression (PHD) and stroke, have attracted public attention. In this review, we summarized the current advances in PHD after CAS. A better understanding of CAS-related PHD may inspire the design of potential prognostic and therapeutic tools.

Robotics and Artificial Intelligence in Endovascular Neurosurgery

The use of artificial intelligence (AI) and robotics in endovascular neurosurgery promises to transform neurovascular care. We present a review of the recently published neurosurgical literature on artificial intelligence and robotics in endovascular neurosurgery to provide insights into the current advances and applications of this technology.

The PubMed database was searched for "neurosurgery" OR "endovascular" OR "interventional" AND "robotics" OR "artificial intelligence" between January 2016 and August 2021. A total of 1296 articles were identified, and after applying the inclusion and exclusion criteria, 38 manuscripts were selected for review and analysis. These manuscripts were divided into four categories: 1) robotics and AI for the diagnosis of cerebrovascular pathology, 2) robotics and AI for the treatment of cerebrovascular pathology, 3) robotics and AI for training in neuroendovascular procedures, and 4) robotics and AI for clinical outcome optimization.

The 38 articles presented include 23 articles on AI-based diagnosis of cerebrovascular disease, 10 articles on AI-based treatment of cerebrovascular disease, two articles on AI-based training techniques for neuroendovascular procedures, and three articles reporting AI prediction models of clinical outcomes in vascular disorders of the brain. Innovation with robotics and AI focus on diagnostic efficiency, optimizing treatment and interventional procedures, improving physician procedural performance, and predicting clinical outcomes with the use of artificial intelligence and robotics. Experimental studies with robotic systems have demonstrated safety and efficacy in treating cerebrovascular disorders, and novel microcatheterization techniques may permit access to deeper brain regions. Other studies show that pre-procedural simulations increase overall physician performance. Artificial intelligence also shows superiority over existing statistical tools in predicting clinical outcomes.

The recent advances and current usage of robotics and AI in the endovascular neurosurgery field suggest that the collaboration between physicians and machines has a bright future for the improvement of patient care. The aim of this work is to equip the medical readership, in particular the neurosurgical specialty, with tools to better understand and apply findings from research on artificial intelligence and robotics in endovascular neurosurgery.

The intersection of prognostication and code status in patients with severe brain injury

Accurately estimating the prognosis of brain injury patients can be difficult, especially early in their course. Prognostication is important because it largely determines the care level we provide, from aggressive treatment for patients we predict could have a good outcome to withdrawal of treatment for those we expect will have a poor outcome. Accurate prognostication is required for ethical decision-making. However, several studies have shown that prognostication is frequently inaccurate and variable. Overly optimistic prognostication can lead to false hope and futile care. Overly pessimistic prognostication can lead to therapeutic nihilism. Overlapping is the powerful effect that cognitive biases, in particular code status, can play in shaping our perceptions and the care level we provide. The presence of Do Not Resuscitate orders has been shown to be associated with increased mortality. Based on a comprehensive search of peer-reviewed journals using a wide range of key terms, including prognostication, critical illness, brain injury, cognitive bias, and code status, the following is a review of prognostic accuracy and the effect of code status on outcome. Because withdrawal of treatment is the most common cause of death in the ICU, a clearer understanding of this intersection of prognostication and code status is needed.

Enriching the Study Population for Ischemic Stroke Therapeutic Trials Using a Machine Learning Algorithm

Background

Strokes represent a leading cause of mortality globally. The evolution of developing new therapies is subject to safety and efficacy testing in clinical trials, which operate in a limited timeframe. To maximize the impact of these trials, patient cohorts for whom ischemic stroke is likely during that designated timeframe should be identified. Machine learning may improve upon existing candidate identification methods in order to maximize the impact of clinical trials for stroke prevention and treatment and improve patient safety.

Methods

A retrospective study was performed using 41,970 qualifying patient encounters with ischemic stroke from inpatient visits recorded from over 700 inpatient and ambulatory care sites. Patient data were extracted from electronic health records and used to train and test a gradient boosted machine learning algorithm (MLA) to predict the patients' risk of experiencing ischemic stroke from the period of 1 day up to 1 year following the patient encounter. The primary outcome of interest was the occurrence of ischemic stroke.

Results

After training for optimization, XGBoost obtained a specificity of 0.793, a positive predictive value (PPV) of 0.194, and a negative predictive value (NPV) of 0.985. The MLA further obtained an area under the receiver operating characteristic (AUROC) of 0.88. The Logistic Regression and multilayer perceptron models both achieved AUROCs of 0.862. Among features that significantly impacted the prediction of ischemic stroke were previous stroke history, age, and mean systolic blood pressure.

Conclusion

MLAs have the potential to more accurately predict the near risk of ischemic stroke within a 1-year prediction window for individuals who have been hospitalized. This risk stratification tool can be used to design clinical trials to test stroke prevention treatments in high-risk populations by identifying subjects who would be more likely to benefit from treatment.

Predicting Ischemic Stroke Outcome Using Deep Learning Approaches

Predicting functional outcomes after an Ischemic Stroke (IS) is highly valuable for patients and desirable for physicians. This facilitates physicians to set reasonable goals for patients and cooperate with patients and relatives effectively, and furthermore to reach common after-stroke care decisions for recovery and make exercise plans to facilitate rehabilitation. The objective of this research is to apply three current Deep Learning (DL) approaches for 6-month IS outcome predictions, using the openly accessible International Stroke Trial (IST) dataset. Furthermore, another objective of this research is to compare these DL approaches with machine learning (ML) for performing in clinical prediction. After comparing various ML methods (Deep Forest, Random Forest, Support Vector Machine, etc.) with current DL frameworks (CNN, LSTM, Resnet), the results show that DL doesn’t outperform ML significantly. DL methods and reporting used for analyzing structured medical data should be developed and improved.

Predicting Continuity of Asthma Care Using a Machine Learning Model: Retrospective Cohort Study

Continuity of care (COC) has been shown to possess numerous health benefits for chronic diseases. Specifically, the establishment of its level can facilitate clinical decision-making and enhanced allocation of healthcare resources. However, the use of a generalizable predictive methodology to determine the COC in patients has been underinvestigated. To fill this research gap, this study aimed to develop a machine learning model to predict the future COC of asthma patients and explore the associated factors. We included 31,724 adult outpatients with asthma who received care from the University of Washington Medicine between 2011 and 2018, and examined 138 features to build the machine learning model. Following the 10-fold cross-validations, the proposed model yielded an accuracy of 88.20%, an average area under the receiver operating characteristic curve of 0.96, and an average F1 score of 0.86. Further analysis revealed that the severity of asthma, comorbidities, insurance, and age were highly correlated with the COC of patients with asthma. This study used predictive methods to obtain the COC of patients, and our excellent modeling strategy achieved high performance. After further optimization, the model could facilitate future clinical decisions, hospital management, and improve outcomes.

Using machine learning to predict atrial fibrillation diagnosed after ischemic stroke

BACKGROUND

Selecting best candidates for prolonged poststroke cardiac monitoring in acute ischemic stroke (AIS) patients is still challenging. We aimed to develop a machine learning (ML) model to select AIS patients at high risk of poststroke atrial fibrillation (AF) for prolonged cardiac monitoring and then to compare ML model with traditional risk scores and classic statistical logistic regression (classic-LR) model.

METHODS

AIS patients from July 2012 to September 2020 across Nanjing First Hospital were collected. We performed the LASSO regression for selecting the critical features and built five ML models to assess the risk of poststroke AF. The SHAP and partial dependence plot (PDP) method were introduced to interpret the optimal model. We also compared ML model with CHADS₂ score, CHA₂DS₂-VASc score, AS5F score, HAVOC score, and classic-LR model.

RESULTS

A total of 3929 AIS patients were included. Among the five ML models, deep neural network (DNN) was the model with best performance. It also exhibited superior performance compared with CHADS₂ score, CHA₂DS₂-VASc score, AS5F score, HAVOC score and classic-LR model. The results of SHAP and PDP method revealed age, cardioembolic stroke, large-artery atherosclerosis stroke, and NIHSS score at admission were the top four important features and revealed the DNN model had good interpretability and reliability.

CONCLUSION

The DNN model achieved best performance and improved prediction performance compared with traditional risk scores and classic-LR model. The DNN model can be applied to identify AIS patients at high risk of poststroke AF as best candidates for prolonged poststroke cardiac monitoring.

Current approaches and advances in the imaging of stroke

A stroke occurs when the blood flow to the brain is suddenly interrupted, depriving brain cells of oxygen and glucose and leading to further cell death. Neuroimaging techniques, such as computed tomography and magnetic resonance imaging, have greatly improved our ability to visualise brain structures and are routinely used to diagnose the affected vascular region of a stroke patient's brain and to inform decisions about clinical care. Currently, these multimodal imaging techniques are the backbone of the clinical management of stroke patients and have immensely improved our ability to visualise brain structures. Here, we review recent developments in the field of neuroimaging and discuss how different imaging techniques are used in the diagnosis, prognosis and treatment of stroke.

Summary: Stroke imaging has undergone seismic shifts in the past decade. Although magnetic resonance imaging (MRI) is superior to computed tomography in providing vital information, further research on MRI is still required to bring its full potential into clinical practice.

Impact of Pretreatment Ischemic Location on Functional Outcome after Thrombectomy

Pretreatment ischemic location may be an important determinant for functional outcome prediction in acute ischemic stroke. In total, 143 anterior circulation ischemic stroke patients in the THRACE study were included. Ischemic lesions were semi-automatically segmented on pretreatment diffusion-weighted imaging and registered on brain atlases. The percentage of ischemic tissue in each atlas-segmented region was calculated. Statistical models with logistic regression and support vector machine were built to analyze the predictors of functional outcome. The investigated parameters included: age, baseline National Institutes of Health Stroke Scale score, and lesional volume (three-parameter model), together with the ischemic percentage in each atlas-segmented region (four-parameter model). The support vector machine with radial basis functions outperformed logistic regression in prediction accuracy. The support vector machine three-parameter model demonstrated an area under the curve of 0.77, while the four-parameter model achieved a higher area under the curve (0.82). Regions with marked impacts on outcome prediction were the uncinate fasciculus, postcentral gyrus, putamen, middle occipital gyrus, supramarginal gyrus, and posterior corona radiata in the left hemisphere; and the uncinate fasciculus, paracentral lobule, temporal pole, hippocampus, inferior occipital gyrus, middle temporal gyrus, pallidum, and anterior limb of the internal capsule in the right hemisphere. In conclusion, pretreatment ischemic location provided significant prognostic information for functional outcome in ischemic stroke.

Deep Learning-Based Automated Thrombolysis in Cerebral Infarction Scoring: A Timely Proof-of-Principle Study

Background and Purpose

Mechanical thrombectomy is an established procedure for treatment of acute ischemic stroke. Mechanical thrombectomy success is commonly assessed by the Thrombolysis in Cerebral Infarction (TICI) score, assigned by visual inspection of X-ray digital subtraction angiography data. However, expert-based TICI scoring is highly observer-dependent. This represents a major obstacle for mechanical thrombectomy outcome comparison in, for instance, multicentric clinical studies. Focusing on occlusions of the M1 segment of the middle cerebral artery, the present study aimed to develop a deep learning (DL) solution to automated and, therefore, objective TICI scoring, to evaluate the agreement of DL- and expert-based scoring, and to compare corresponding numbers to published scoring variability of clinical experts.

Methods

The study comprises 2 independent datasets. For DL system training and initial evaluation, an in-house dataset of 491 digital subtraction angiography series and modified TICI scores of 236 patients with M1 occlusions was collected. To test the model generalization capability, an independent external dataset with 95 digital subtraction angiography series was analyzed. Characteristics of the DL system were modeling TICI scoring as ordinal regression, explicit consideration of the temporal image information, integration of physiological knowledge, and modeling of inherent TICI scoring uncertainties.

Results

For the in-house dataset, the DL system yields Cohen’s kappa, overall accuracy, and specific agreement values of 0.61, 71%, and 63% to 84%, respectively, compared with the gold standard: the expert rating. Values slightly drop to 0.52/64%/43% to 87% when the model is, without changes, applied to the external dataset. After model updating, they increase to 0.65/74%/60% to 90%. Literature Cohen’s kappa values for expert-based TICI scoring agreement are in the order of 0.6.

Conclusions

The agreement of DL- and expert-based modified TICI scores in the range of published interobserver variability of clinical experts highlights the potential of the proposed DL solution to automated TICI scoring.

Current Perspectives of Artificial Intelligence in Pediatric Neuroradiology: An Overview

Artificial Intelligence, Machine Learning, and myriad related techniques are becoming ever more commonplace throughout industry and society, and radiology is by no means an exception. It is essential for every radiologists of every subspecialty to gain familiarity and confidence with these techniques as they become increasingly incorporated into the routine practice in both academic and private practice settings. In this article, we provide a brief review of several definitions and techniques that are commonly used in AI, and in particular machine vision, and examples of how they are currently being applied to the setting of clinical neuroradiology. We then review the unique challenges that the adoption and application of faces within the subspecialty of pediatric neuroradiology, and how these obstacles may be overcome. We conclude by presenting specific examples of how AI is currently being applied within the field of pediatric neuroradiology and the potential opportunities that are available for future applications.

Prediction of Hemorrhagic Transformation after Ischemic Stroke Using Machine Learning

Hemorrhagic transformation (HT) is one of the leading causes of a poor prognostic marker after acute ischemic stroke (AIS). We compared the performances of the several machine learning (ML) algorithms to predict HT after AIS using only structured data. A total of 2028 patients with AIS, who were admitted within seven days of symptoms onset, were included in this analysis. HT was defined based on the criteria of the European Co-operative Acute Stroke Study-II trial. The whole dataset was randomly divided into a training and a test dataset with a 7:3 ratio. Binary logistic regression, support vector machine, extreme gradient boosting, and artificial neural network (ANN) algorithms were used to assess the performance of predicting the HT occurrence after AIS. Five-fold cross validation and a grid search technique were used to optimize the hyperparameters of each ML model, which had its performance measured by the area under the receiver operating characteristic (AUROC) curve. Among the included AIS patients, the mean age and number of male subjects were 69.6 years and 1183 (58.3%), respectively. HT was observed in 318 subjects (15.7%). There were no significant differences in corresponding variables between the training and test dataset. Among all the ML algorithms, the ANN algorithm showed the best performance in terms of predicting the occurrence of HT in our dataset (0.844). Feature scaling including standardization and normalization, and the resampling strategy showed no additional improvement of the ANN's performance. The ANN-based prediction of HT after AIS showed better performance than the conventional ML algorithms. Deep learning may be used to predict important outcomes for structured data-based prediction.

[Progress in computer-assisted Alberta stroke program early computer tomography score of acute ischemic stroke based on different modal images]

Clinically, non-contrastive computed tomography (NCCT) is used to quickly diagnose the type and area of ​​stroke, and the Alberta stroke program early computer tomography score (ASPECTS) is used to guide the next treatment. However, in the early stage of acute ischemic stroke (AIS), it's difficult to distinguish the mild cerebral infarction on NCCT with the naked eye, and there is no obvious boundary between brain regions, which makes clinical ASPECTS difficult to conduct. The method based on machine learning and deep learning can help physicians quickly and accurately identify cerebral infarction areas, segment brain areas, and operate ASPECTS quantitative scoring, which is of great significance for improving the inconsistency in clinical ASPECTS. This article describes current challenges in the field of AIS ASPECTS, and then summarizes the application of computer-aided technology in ASPECTS from two aspects including machine learning and deep learning. Finally, this article summarizes and prospects the research direction of AIS-assisted assessment, and proposes that the computer-aided system based on multi-modal images is of great value to improve the comprehensiveness and accuracy of AIS assessment, which has the potential to open up a new research field for AIS-assisted assessment.

Interventional Radiology ex-machina: impact of Artificial Intelligence on practice

Artificial intelligence (AI) is a branch of Informatics that uses algorithms to tirelessly process data, understand its meaning and provide the desired outcome, continuously redefining its logic. AI was mainly introduced via artificial neural networks, developed in the early 1950s, and with its evolution into "computational learning models." Machine Learning analyzes and extracts features in larger data after exposure to examples; Deep Learning uses neural networks in order to extract meaningful patterns from imaging data, even deciphering that which would otherwise be beyond human perception. Thus, AI has the potential to revolutionize the healthcare systems and clinical practice of doctors all over the world. This is especially true for radiologists, who are integral to diagnostic medicine, helping to customize treatments and triage resources with maximum effectiveness. Related in spirit to Artificial intelligence are Augmented Reality, mixed reality, or Virtual Reality, which are able to enhance accuracy of minimally invasive treatments in image guided therapies by Interventional Radiologists. The potential applications of AI in IR go beyond computer vision and diagnosis, to include screening and modeling of patient selection, predictive tools for treatment planning and navigation, and training tools. Although no new technology is widely embraced, AI may provide opportunities to enhance radiology service and improve patient care, if studied, validated, and applied appropriately.

Artificial intelligence in clinical decision support and outcome prediction - applications in stroke

Artificial intelligence (AI) is making a profound impact in healthcare, with the number of AI applications in medicine increasing substantially over the past five years. In acute stroke, it is playing an increasingly important role in clinical decision-making. Contemporary advances have increased the amount of information - both clinical and radiological - which clinicians must consider when managing patients. In the time-critical setting of acute stroke, AI offers the tools to rapidly evaluate and consolidate available information, extracting specific predictions from rich, noisy data. It has been applied to the automatic detection of stroke lesions on imaging and can guide treatment decisions through the prediction of tissue outcomes and long-term functional outcomes. This review examines the current state of AI applications in stroke, exploring their potential to reform stroke care through clinical decision support, as well as the challenges and limitations which must be addressed to facilitate their acceptance and adoption for clinical use.

Using Computational Methods to Improve Integrated Disease Management for Asthma and Chronic Obstructive Pulmonary Disease: Protocol for a Secondary Analysis

Background

Asthma and chronic obstructive pulmonary disease (COPD) impose a heavy burden on health care. Approximately one-fourth of patients with asthma and patients with COPD are prone to exacerbations, which can be greatly reduced by preventive care via integrated disease management that has a limited service capacity. To do this well, a predictive model for proneness to exacerbation is required, but no such model exists. It would be suboptimal to build such models using the current model building approach for asthma and COPD, which has 2 gaps due to rarely factoring in temporal features showing early health changes and general directions. First, existing models for other asthma and COPD outcomes rarely use more advanced temporal features, such as the slope of the number of days to albuterol refill, and are inaccurate. Second, existing models seldom show the reason a patient is deemed high risk and the potential interventions to reduce the risk, making already occupied clinicians expend more time on chart review and overlook suitable interventions. Regular automatic explanation methods cannot deal with temporal data and address this issue well.

Objective

To enable more patients with asthma and patients with COPD to obtain suitable and timely care to avoid exacerbations, we aim to implement comprehensible computational methods to accurately predict proneness to exacerbation and recommend customized interventions.

Methods

We will use temporal features to accurately predict proneness to exacerbation, automatically find modifiable temporal risk factors for every high-risk patient, and assess the impact of actionable warnings on clinicians’ decisions to use integrated disease management to prevent proneness to exacerbation.

Results

We have obtained most of the clinical and administrative data of patients with asthma from 3 prominent American health care systems. We are retrieving other clinical and administrative data, mostly of patients with COPD, needed for the study. We intend to complete the study in 6 years.

Conclusions

Our results will help make asthma and COPD care more proactive, effective, and efficient, improving outcomes and saving resources.

International Registered Report Identifier (IRRID)

PRR1-10.2196/27065

Predictive and diagnosis models of stroke from hemodynamic signal monitoring

This work presents a novel and promising approach to the clinical management of acute stroke. Using machine learning techniques, our research has succeeded in developing accurate diagnosis and prediction real-time models from hemodynamic data. These models are able to diagnose stroke subtype with 30 min of monitoring, to predict the exitus during the first 3 h of monitoring, and to predict the stroke recurrence in just 15 min of monitoring. Patients with difficult access to a CT scan and all patients that arrive at the stroke unit of a specialized hospital will benefit from these positive results. The results obtained from the real-time developed models are the following: stroke diagnosis around 98% precision (97.8% sensitivity, 99.5% specificity), exitus prediction with 99.8% precision (99.8% Sens., 99.9% Spec.), and 98% precision predicting stroke recurrence (98% Sens., 99% Spec.). Graphical abstract depicting the complete process since a patient is monitored until the data collected is used to generate models.

Random forest-based prediction of stroke outcome

We research into the clinical, biochemical and neuroimaging factors associated with the outcome of stroke patients to generate a predictive model using machine learning techniques for prediction of mortality and morbidity 3-months after admission. The dataset consisted of patients with ischemic stroke (IS) and non-traumatic intracerebral hemorrhage (ICH) admitted to Stroke Unit of a European Tertiary Hospital prospectively registered. We identified the main variables for machine learning Random Forest (RF), generating a predictive model that can estimate patient mortality/morbidity according to the following groups: (1) IS + ICH, (2) IS, and (3) ICH. A total of 6022 patients were included: 4922 (mean age 71.9 ± 13.8 years) with IS and 1100 (mean age 73.3 ± 13.1 years) with ICH. NIHSS at 24, 48 h and axillary temperature at admission were the most important variables to consider for evolution of patients at 3-months. IS + ICH group was the most stable for mortality prediction [0.904 ± 0.025 of area under the receiver operating characteristics curve (AUC)]. IS group presented similar results, although variability between experiments was slightly higher (0.909 ± 0.032 of AUC). ICH group was the one in which RF had more problems to make adequate predictions (0.9837 vs. 0.7104 of AUC). There were no major differences between IS and IS + ICH groups according to morbidity prediction (0.738 and 0.755 of AUC) but, after checking normality with a Shapiro Wilk test with the null hypothesis that the data follow a normal distribution, it was rejected with W = 0.93546 (p-value < 2.2e-16). Conditions required for a parametric test do not hold, and we performed a paired Wilcoxon Test assuming the null hypothesis that all the groups have the same performance. The null hypothesis was rejected with a value < 2.2e-16, so there are statistical differences between IS and ICH groups. In conclusion, machine learning algorithms RF can be effectively used in stroke patients for long-term outcome prediction of mortality and morbidity.

A Machine Learning Approach to First Pass Reperfusion in Mechanical Thrombectomy: Prediction and Feature Analysis

INTRODUCTION

Novel machine learning (ML) methods are being investigated across medicine for their predictive capabilities while boasting increased adaptability and generalizability. In our study, we compare logistic regression with machine learning for feature importance analysis and prediction in first-pass reperfusion.

METHODS

We retrospectively identified cases of ischemic stroke treated with mechanical thrombectomy (MT) at our institution from 2012-2018. Significant variables used in predictive modeling were demographic characteristics, medical history, admission NIHSS, and stroke characteristics. Outcome was binarized TICI on first pass (0-2a vs 2b-3). Shapley feature importance plots were used to identify variables that strongly affected outcomes.

RESULTS

Accuracy for the Random Forest and SVM models were 67.1% compared to 65.8% for the logistic regression model. Brier score was lower for the Random Forest model (0.329 vs 0.342) indicating better predictive capability. Other supervised learning models performed worse than the logistic regression model, with accuracy of 56.2% for Naïve Bayes and 61.6% for XGBoost. Shapley plots for the Random Forest model showed use of aspiration, hyperlipidemia, hypertension, use of stent retriever, and time between symptom onset and catheterization as the top five predictors of first pass reperfusion.

CONCLUSION

Use of machine learning models, such as Random Forest, for the study of MT outcomes, is more accurate than logistic regression for our dataset, and identifies new factors that contribute to achieving first pass reperfusion. The benefits of machine learning, such as improved predictive capabilities, integration of new data, and generalizability, establish ML as the preferred model for studying outcomes in stroke.

Forecasting Future Asthma Hospital Encounters of Patients With Asthma in an Academic Health Care System: Predictive Model Development and Secondary Analysis Study

Background

Asthma affects a large proportion of the population and leads to many hospital encounters involving both hospitalizations and emergency department visits every year. To lower the number of such encounters, many health care systems and health plans deploy predictive models to prospectively identify patients at high risk and offer them care management services for preventive care. However, the previous models do not have sufficient accuracy for serving this purpose well. Embracing the modeling strategy of examining many candidate features, we built a new machine learning model to forecast future asthma hospital encounters of patients with asthma at Intermountain Healthcare, a nonacademic health care system. This model is more accurate than the previously published models. However, it is unclear how well our modeling strategy generalizes to academic health care systems, whose patient composition differs from that of Intermountain Healthcare.

Objective

This study aims to evaluate the generalizability of our modeling strategy to the University of Washington Medicine (UWM), an academic health care system.

Methods

All adult patients with asthma who visited UWM facilities between 2011 and 2018 served as the patient cohort. We considered 234 candidate features. Through a secondary analysis of 82,888 UWM data instances from 2011 to 2018, we built a machine learning model to forecast asthma hospital encounters of patients with asthma in the subsequent 12 months.

Results

Our UWM model yielded an area under the receiver operating characteristic curve (AUC) of 0.902. When placing the cutoff point for making binary classification at the top 10% (1464/14,644) of patients with asthma with the largest forecasted risk, our UWM model yielded an accuracy of 90.6% (13,268/14,644), a sensitivity of 70.2% (153/218), and a specificity of 90.91% (13,115/14,426).

Conclusions

Our modeling strategy showed excellent generalizability to the UWM, leading to a model with an AUC that is higher than all of the AUCs previously reported in the literature for forecasting asthma hospital encounters. After further optimization, our model could be used to facilitate the efficient and effective allocation of asthma care management resources to improve outcomes.

International Registered Report Identifier (IRRID)

RR2-10.2196/resprot.5039

Natural Language Processing and Machine Learning for Identifying Incident Stroke From Electronic Health Records: Algorithm Development and Validation

Background

Stroke is an important clinical outcome in cardiovascular research. However, the ascertainment of incident stroke is typically accomplished via time-consuming manual chart abstraction. Current phenotyping efforts using electronic health records for stroke focus on case ascertainment rather than incident disease, which requires knowledge of the temporal sequence of events.

Objective

The aim of this study was to develop a machine learning–based phenotyping algorithm for incident stroke ascertainment based on diagnosis codes, procedure codes, and clinical concepts extracted from clinical notes using natural language processing.

Methods

The algorithm was trained and validated using an existing epidemiology cohort consisting of 4914 patients with atrial fibrillation (AF) with manually curated incident stroke events. Various combinations of feature sets and machine learning classifiers were compared. Using a heuristic rule based on the composition of concepts and codes, we further detected the stroke subtype (ischemic stroke/transient ischemic attack or hemorrhagic stroke) of each identified stroke. The algorithm was further validated using a cohort (n=150) stratified sampled from a population in Olmsted County, Minnesota (N=74,314).

Results

Among the 4914 patients with AF, 740 had validated incident stroke events. The best-performing stroke phenotyping algorithm used clinical concepts, diagnosis codes, and procedure codes as features in a random forest classifier. Among patients with stroke codes in the general population sample, the best-performing model achieved a positive predictive value of 86% (43/50; 95% CI 0.74-0.93) and a negative predictive value of 96% (96/100). For subtype identification, we achieved an accuracy of 83% in the AF cohort and 80% in the general population sample.

Conclusions

We developed and validated a machine learning–based algorithm that performed well for identifying incident stroke and for determining type of stroke. The algorithm also performed well on a sample from a general population, further demonstrating its generalizability and potential for adoption by other institutions.

Predicting Clinical Outcomes in Acute Ischemic Stroke Patients Undergoing Endovascular Thrombectomy with Machine Learning : A Systematic Review and Meta-analysis

PURPOSE

Conventional predictive models are based on a combination of clinical and neuroimaging parameters using traditional statistical approaches. Emerging studies have shown that the machine learning (ML) prediction models with multiple pretreatment clinical variables have the potential to accurately prognosticate the outcomes in acute ischemic stroke (AIS) patients undergoing thrombectomy, and hence identify patients suitable for thrombectomy. This article summarizes the published studies on ML models in large vessel occlusion AIS patients undergoing thrombectomy.

METHODS

We searched electronic databases including PubMed from 1 January 2000 up to 14 October 2019 for studies that evaluated ML algorithms for the prediction of outcomes in stroke patients undergoing thrombectomy. We then used random-effects bivariate meta-analysis models to summarize the studies.

RESULTS

We retained a total of five studies that evaluated ML (4 support vector machine, 1 decision tree model) with a combined cohort of 802 patients. The prevalence of good functional outcome defined by 90-day mRS of 0-2 when available. Random effects model demonstrated that the AUC was 0.846 (95% confidence interval, CI 0.686-0.902). A pooled diagnostic odds ratio of 12.6 was computed. The pooled sensitivity and specificity were 0.795 (95% CI 0.651-0.889) and 0.780 (95% CI 0.634-0.879), respectively.

CONCLUSION

ML may be useful as an adjunct to clinical assessment to predict functional outcomes in AIS patients undergoing thrombectomy, and hence identify suitable patients for treatment. Further studies validating ML models in large multicenter cohorts are necessary to explore this further.