Easily Created Prediction Model Using Automated Artificial Intelligence Framework (Prediction One, Sony Network Communications Inc., Tokyo, Japan) for Subarachnoid Hemorrhage Outcomes Treated by Coiling and Delayed Cerebral Ischemia

Can AI predict walking independence in patients with stroke upon admission to a recovery-phase rehabilitation ward?

Ono K, Takahashi R, Morita K, Ara Y, Abe S, Ito S, Uno S, Abe M, Shirasaka T. Can AI predict walking independence in patients with stroke upon admission to a recovery-phase rehabilitation ward? Jpn J Compr Rehabil Sci 2024; 15: 1-7.

Objective

This study aimed to develop a prediction model for walking independence in patients with stroke in the recovery phase at the time of hospital discharge using Prediction One, an artificial intelligence (AI)-based predictive analysis tool, and to examine its utility.

Methods

Prediction One was used to develop a prediction model for walking independence for 280 patients with stroke admitted to a rehabilitation ward-based on physical and mental function information at admission. In 134 patients with stroke hospitalized during different periods, accuracy was confirmed by calculating the correct response rate, sensitivity, specificity, and positive and negative predictive values based on the results of AI-based predictions and actual results.

Results

The prediction accuracy (area under the curve, AUC) of the proposed model was 91.7%. The correct response rate was 79.9%, sensitivity was 95.7%, specificity was 62.5%, positive predictive value was 73.6%, and negative predictive value was 93.5%.

Conclusion

The accuracy of the prediction model developed in this study is not inferior to that of previous studies, and the simplicity of the model makes it highly practical.

Prediction models for the impact of the COVID-19 pandemic on research activities of Japanese nursing researchers using deep learning

AIM

This study aimed to construct and evaluate prediction models using deep learning to explore the impact of attributes and lifestyle factors on research activities of nursing researchers during the COVID-19 pandemic.

METHODS

A secondary data analysis was conducted from a cross-sectional online survey by the Japanese Society of Nursing Science at the inception of the COVID-19 pandemic. A total of 1089 respondents from nursing faculties were divided into a training dataset and a test dataset. We constructed two prediction models with the training dataset using artificial intelligence (AI) predictive analysis tools; motivation and time were used as predictor items for negative impact on research activities. Predictive factors were attributes, lifestyle, and predictor items for each other. The models' accuracy and internal validity were evaluated using an ordinal logistic regression analysis to assess goodness-of-fit; the test dataset was used to assess external validity. Predicted contributions by each factor were also calculated.

RESULTS

The models' accuracy and goodness-of-fit were good. The prediction contribution analysis showed that no increase in research motivation and lack of increase in research time strongly influenced each other. Other factors that negatively influenced research motivation and research time were residing outside the special alert area and lecturer position and living with partner/spouse and associate professor position, respectively.

CONCLUSIONS

Deep learning is a research method enabling early prediction of unexpected events, suggesting new applicability in nursing science. To continue research activities during the COVID-19 pandemic and future contingencies, the research environment needs to be improved, workload corrected by position, and considered in terms of work-life balance.

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.

Serum Soluble Scavenger Receptor A Levels are Associated with Delayed Cerebral Ischemia and Poor Clinical Outcome After Aneurysmal Subarachnoid Hemorrhage: A Prospective Observational Study

OBJECTIVE

Scavenger receptor A (SRA), a pattern recognition molecule, is implicated in immune response after acute brain injury. We strived to identify serum soluble SRA (sSRA) as a potential biomarker of prognosis after aneurysmal subarachnoid hemorrhage (aSAH).

METHODS

In this prospective observational study, we quantified serum sSRA levels of 131 aSAH patients and 131 healthy controls. A poor outcome was defined as extended Glasgow outcome scale (GOSE) scores of 1-4 at 90 days after injury. Relations of serum sSRA levels to severity, delayed cerebral ischemia (DCI) and poor outcome were assessed using multivariate analysis. Predictive efficiency was determined via area under receiver operating characteristic curve (AUC).

RESULTS

Serum sSRA levels were markedly higher in aSAH patients than in controls (median, 2.9 ng/mL versus 1.0 ng/mL; P < 0.001). Serum sSRA levels were independently correlated with Hunt-Hess scores (beta, 0.569; 95% confidence interval (CI), 0.244-0.894; P = 0.001), modified Fisher scores (beta, 0.664; 95% CI, 0.254-1.074; P = 0.002) and 90-day GOSE scores (beta, -0.275; 95% CI, -0.440-0.110; P = 0.005). Serum sSRA levels independently predicted DCI (odds ratio, 1.305; 95% CI, 1.012-1.687; P = 0.040) and a poor outcome (odds ratio, 2.444; 95% CI, 1.264-4.726; P = 0.008), as well as showed significant accuracy for the discrimination of DCI (AUC, 0.753; 95% CI, 0.649-0.857; P < 0.001) and a poor outcome (AUC, 0.800; 95% CI, 0.721-0.880; P < 0.001). Its combination with Hunt-Hess scores and modified Fisher scores displayed significantly improved AUCs for predicting DCI and poor outcome, as compared to any of them (all P < 0.05).

CONCLUSION

There is a significant elevation of serum sSRA levels after aSAH, which in close correlation with illness severity, are independently associated with DCI and poor clinical outcome after aSAH. Hypothetically, SRA may regulate immune response in acute brain injury after aSAH and serum sSRA is presumed to be a potential prognostic biomarker of aSAH.

Deep Learning-Based Functional Independence Measure Score Prediction After Stroke in Kaifukuki (Convalescent) Rehabilitation Ward Annexed to Acute Care Hospital

Introduction

Prediction models of functional independent measure (FIM) score after kaifukuki (convalescent) rehabilitation ward (KRW) are needed to decide the treatment strategies and save medical resources. Statistical models were reported, but their accuracies were not satisfactory. We made such prediction models using the deep learning (DL) framework, Prediction One (Sony Network Communications Inc., Tokyo, Japan).

Methods

Of the 559 consecutive stroke patients, 122 patients were transferred to our KRW. We divided our 122 patients’ data randomly into halves of training and validation datasets. Prediction One made three prediction models from the training dataset using (1) variables at the acute care ward admission, (2) those at the KRW admission, and (3) those combined (1) and (2). The models’ determination coefficients (R²), correlation coefficients (rs), and residuals were calculated using the validation dataset.

Results

Of the 122 patients, the median age was 71, length of stay (LOS) in acute care ward 23 (17-30) days, LOS in KRW 53 days, total FIM scores at the admission of KRW 85, those at discharge 108. The mean FIM gain and FIM efficiency were 19 and 0.417. All patients were discharged home. Model (1), (2), and (3)’s R² were 0.794, 0.970, and 0.972. Their mean residuals between the predicted and actual total FIM scores were -1.56±24.6, -4.49±17.1, and -2.69±15.7.

Conclusion

Our FIM gain and efficiency were better than national averages of FIM gain 17.1 and FIM efficiency 0.187. We made DL-based total FIM score prediction models, and their accuracies were superior to those of previous statistically calculated ones. The DL-based FIM score prediction models would save medical costs and perform efficient stroke and rehabilitation medicine.

Relationship Between Medical Questionnaire and Influenza Rapid Test Positivity: Subjective Pretest Probability, "I Think I Have Influenza," Contributes to the Positivity Rate

Introduction

Rapid influenza diagnostic tests (RIDTs) are considered essential for determining when to start influenza treatment using anti-influenza drugs, but their accuracy is about 70%. Under the COVID-19 pandemic, we hope to refrain from performing unnecessary RIDTs considering droplet infection of COVID-19 and influenza. We re-examined the medical questionnaire’s importance and its relationship to the positivity of RIDTs. Then we built a positivity prediction model for RIDTs using automated artificial intelligence (AI).

Methods

We retrospectively investigated 96 patients who underwent RIDTs at the outpatient department from December 2019 to March 2020. We used a questionnaire sheet with 24 items before conducting RIDTs. The factors associated with the positivity of RIDTs were statistically analyzed. We then used an automated AI framework to produce the positivity prediction model using the 24 items, sex, and age, with five-fold cross-validation.

Results

Of the 47 women and 49 men (median age was 39 years), 56 patients were RIDT positive with influenza A. The AI-based model using 26 variables had an area under the curve (AUC) of 0.980. The stronger variables are subjective pretest probability, which is a numerically described score ranging from 0% to 100% of “I think I have influenza,” cough, past hours after the onset, muscle pain, and maximum body temperature in order.

Conclusion

We easily built the RIDT positivity prediction model using automated AI. Its AUC was satisfactory, and it suggested the importance of a detailed medical interview. Both the univariate analysis and AI-based model suggested that subjective pretest probability, “I think I have influenza,” might be useful.