Prediction of Recurrent Ischemic Stroke Using Registry Data and Machine Learning Methods: The Erlangen Stroke Registry

PRERISK: A Personalized, Artificial Intelligence-Based and Statistically-Based Stroke Recurrence Predictor for Recurrent Stroke

BACKGROUND

Predicting stroke recurrence for individual patients is difficult, but individualized prediction may improve stroke survivors' engagement in self-care. We developed PRERISK: a statistical and machine learning classifier to predict individual risk of stroke recurrence.

METHODS

We analyzed clinical and socioeconomic data from a prospectively collected public health care-based data set of 41 975 patients admitted with stroke diagnosis in 88 public health centers over 6 years (2014-2020) in Catalonia-Spain. A new stroke diagnosis at least 24 hours after the index event was considered as a recurrent stroke, which was considered as our outcome of interest. We trained several supervised machine learning models to provide individualized risk over time and compared them with a Cox regression model. Models were trained to predict early, late, and long-term recurrence risk, within 90, 91 to 365, and >365 days, respectively. C statistics and area under the receiver operating characteristic curve were used to assess the accuracy of the models.

RESULTS

Overall, 16.21% (5932 of 36 114) of patients had stroke recurrence during a median follow-up of 2.69 years. The most powerful predictors of stroke recurrence were time from previous stroke, Barthel Index, atrial fibrillation, dyslipidemia, age, diabetes, and sex, which were used to create a simplified model with similar performance, together with modifiable vascular risk factors (glycemia, body mass index, high blood pressure, cholesterol, tobacco dependence, and alcohol abuse). The areas under the receiver operating characteristic curve were 0.76 (95% CI, 0.74-0.77), 0.60 (95% CI, 0.58-0.61), and 0.71 (95% CI, 0.69-0.72) for early, late, and long-term recurrence risk, respectively. The areas under the receiver operating characteristic curve of the Cox risk class probability were 0.73 (95% CI, 0.72-0.75), 0.59 (95% CI, 0.57-0.61), and 0.67 (95% CI, 0.66-0.70); machine learning approaches (random forest and AdaBoost) showed statistically significant improvement (P<0.05) over the Cox model for the 3 recurrence time periods. Stroke recurrence curves can be simulated for each patient under different degrees of control of modifiable factors.

CONCLUSIONS

PRERISK is a novel approach that provides a personalized and fairly accurate risk prediction of stroke recurrence over time. The model has the potential to incorporate dynamic control of risk factors.

Biochemical, biomechanical and imaging biomarkers of ischemic stroke: Time for integrative thinking

Stroke is one of the leading causes of adult disability affecting millions of people worldwide. Post-stroke cognitive and motor impairments diminish quality of life and functional independence. There is an increased risk of having a second stroke and developing secondary conditions with long-term social and economic impacts. With increasing number of stroke incidents, shortage of medical professionals and limited budgets, health services are struggling to provide a care that can break the vicious cycle of stroke. Effective post-stroke recovery hinges on holistic, integrative and personalized care starting from improved diagnosis and treatment in clinics to continuous rehabilitation and support in the community. To improve stroke care pathways, there have been growing efforts in discovering biomarkers that can provide valuable insights into the neural, physiological and biomechanical consequences of stroke and how patients respond to new interventions. In this review paper, we aim to summarize recent biomarker discovery research focusing on three modalities (brain imaging, blood sampling and gait assessments), look at some established and forthcoming biomarkers, and discuss their usefulness and complementarity within the context of comprehensive stroke care. We also emphasize the importance of biomarker guided personalized interventions to enhance stroke treatment and post-stroke recovery.

Identifying and predicting physical limitation and cognitive decline trajectory group of older adults in China: A data-driven machine learning analysis

OBJECTIVE

This study aimed to utilize data-driven machine learning methods to identify and predict potential physical and cognitive function trajectory groups of older adults and determine their crucial factors for promoting active ageing in China.

METHODS

Longitudinal data on 3026 older adults from the Chinese Longitudinal Healthy Longevity and Happy Family Survey was used to identify potential physical and cognitive function trajectory groups using a group-based multi-trajectory model (GBMTM). Predictors were selected from sociodemographic characteristics, lifestyle factors, and physical and mental conditions. The trajectory groups were predicted using data-driven machine learning models and dynamic nomogram. Model performance was evaluated by area under the receiver operating characteristics curve (AUROC), area under the precision-recall curve (PRAUC), and confusion matrix.

RESULTS

Two physical and cognitive function trajectory groups were determined, including a trajectory group with physical limitation and cognitive decline (14.18 %) and a normal trajectory group (85.82 %). Logistic regression performed well in predicting trajectory groups (AUROC = 0.881, PRAUC = 0.649). Older adults with lower baseline score of activities of daily living, older age, less frequent housework, and fewer actual teeth were more likely to experience physical limitation and cognitive decline trajectory group.

LIMITATION

This study didn't carry out external validation.

CONCLUSIONS

This study shows that GBMTM and machine learning models effectively identify and predict physical limitation and cognitive decline trajectory group. The identified predictors might be essential for developing targeted interventions to promote healthy ageing.

Predicting mild cognitive impairment in older adults: A machine learning analysis of the Alzheimer's Disease Neuroimaging Initiative

AIM

Mild cognitive impairment (MCI) in older adults is potentially devastating, but an accurate prediction model is still lacking. We hypothesized that neuropsychological tests and MRI-related markers could predict the onset of MCI early.

METHODS

We analyzed data from 306 older adults who were cognitive normal (CN) attending the Alzheimer's Disease Neuroimaging Initiative sequentially (474 pairs of visits) within 3 years. There were 231 pairs of MCI conversion (CN to MCI), and 242 pairs of CN maintenance (CN to CN). Variables on demographic, neuropsychological tests, genetic, and MRI-related markers were collected. Machine learning was used to construct MCI prediction models, comparing the area under the receiver operating characteristic curve (AUC) as the primary metric of performance. Important predictors were ranked for the optimal model.

RESULTS

The baseline age of the study sample was 74.8 years old. The best-performing model (gradient boosting decision tree) with 13 variables predicted MCI with an AUC of 0.819, and the rank of variable importance showed that intracranial volume, hippocampal volume, and score from task 4 (word recognition) of the Alzheimer's Disease Assessment Scale were important predictors of MCI.

CONCLUSIONS

With the help of machine learning, fewer neuropsychological tests and MRI-related markers are required to accurately predict MCI within 3 years, thereby facilitating targeted intervention. Geriatr Gerontol Int 2024; 24: 96-101.

Declining hip fracture burden in Sweden 1998-2019 and consequences for projections through 2050

We aimed to estimate the absolute and age-standardized number of hip fractures in Sweden during the past two decades to produce time trends and future projections. We used nationwide register data from 1998 to 2019 and a validated algorithm to calculate the annual absolute and age-standardized number of incident hip fractures over time. The total hip fracture burden was 335,399 incident events over the 22 years, with a change from 16,180 in 1998 to 13,929 in 2019, a 14% decrease. One decade after the index hip fracture event, 80% of the patients had died, and 11% had a new hip fracture. After considering the steady growth of the older population, the decline in the age-standardized number of hip fractures from 1998 through 2019 was 29.2% (95% CI 28.1-30.2%) in women and 29.3% (95% CI 27.5-30.7%) in men. With a continued similar reduction in hip fracture incidence, we can predict that 14,800 hip fractures will occur in 2034 and 12,000 in 2050 despite doubling the oldest old (≥ 80 years). Without an algorithm, a naïve estimate of the total number of hip fractures over the study period was 539,947, with a second 10-year hip fracture risk of 35%. We note an ongoing decline in the absolute and age-standardized actual number of hip fractures in Sweden, with consequences for future projections.

A convenient machine learning model to predict full stomach and evaluate the safety and comfort improvements of preoperative oral carbohydrate in patients undergoing elective painless gastrointestinal endoscopy

BACKGROUND AND AIMS

Assessment of the patient's gastric contents is the key to avoiding aspiration incidents, however, there is no effective method to determine whether elective painless gastrointestinal endoscopy (GIE) patients have a full stomach or an empty stomach. And previous studies have shown that preoperative oral carbohydrates (POCs) can improve the discomfort induced by fasting, but there are different perspectives on their safety. This study aimed to develop a convenient, accurate machine learning (ML) model to predict full stomach. And based on the model outcomes, evaluate the safety and comfort improvements of POCs in empty- and full stomach groups.

METHODS

We enrolled 1386 painless GIE patients between October 2022 and January 2023 in Nanjing First Hospital, and 1090 patients without POCs were used to construct five different ML models to identify full stomach. The metrics of discrimination and calibration validated the robustness of the models. For the best-performance model, we further interpreted it through SHapley Additive exPlanations (SHAP) and constructed a web calculator to facilitate clinical use. We evaluated the safety and comfort improvements of POCs by propensity score matching (PSM) in the two groups, respectively.

RESULTS

Random Forest (RF) model showed the greatest discrimination with the area under the receiver operating characteristic curve (AUROC) 0.837 [95% confidence interval (CI): 79.1-88.2], F1 71.5%, and best calibration with a Brier score of 15.2%. The web calculator can be visited at https://medication.shinyapps.io/RF_model/. PSM results demonstrated that POCs significantly reduced the full stomach incident in empty stomach group (p < 0.05), but no differences in full stomach group (p > 0.05). Comfort improved in both groups and was more significant in empty stomach group.

CONCLUSIONS

The developed convenient RF model predicted full stomach with high accuracy and interpretability. POCs were safe and comfortably improved in both groups, with more benefit in empty stomach group. These findings may guide the patients' gastrointestinal preparation.

The Value of Applying Machine Learning in Predicting the Time of Symptom Onset in Stroke Patients: Systematic Review and Meta-Analysis

BACKGROUND

Machine learning is a potentially effective method for identifying and predicting the time of the onset of stroke. However, the value of applying machine learning in this field remains controversial and debatable.

OBJECTIVE

We aimed to assess the value of applying machine learning in predicting the time of stroke onset.

METHODS

PubMed, Web of Science, Embase, and Cochrane were comprehensively searched. The C index and sensitivity with 95% CI were used as effect sizes. The risk of bias was evaluated using PROBAST (Prediction Model Risk of Bias Assessment Tool), and meta-analysis was conducted using R (version 4.2.0; R Core Team).

RESULTS

Thirteen eligible studies were included in the meta-analysis involving 55 machine learning models with 41 models in the training set and 14 in the validation set. The overall C index was 0.800 (95% CI 0.773-0.826) in the training set and 0.781 (95% CI 0.709-0.852) in the validation set. The sensitivity and specificity were 0.76 (95% CI 0.73-0.80) and 0.79 (95% CI 0.74-0.82) in the training set and 0.81 (95% CI 0.68-0.90) and 0.83 (95% CI 0.73-0.89) in the validation set, respectively. Subgroup analysis revealed that the accuracy of machine learning in predicting the time of stroke onset within 4.5 hours was optimal (training: 0.80, 95% CI 0.77-0.83; validation: 0.79, 95% CI 0.71-0.86).

CONCLUSIONS

Machine learning has ideal performance in identifying the time of stroke onset. More reasonable image segmentation and texture extraction methods in radiomics should be used to promote the value of applying machine learning in diverse ethnic backgrounds.

TRIAL REGISTRATION

PROSPERO CRD42022358898; https://www.crd.york.ac.uk/Prospero/display_record.php?RecordID=358898.

Prediction of subjective cognitive decline after corpus callosum infarction by an interpretable machine learning-derived early warning strategy

Background and purpose

Corpus callosum (CC) infarction is an extremely rare subtype of cerebral ischemic stroke, however, the symptoms of cognitive impairment often fail to attract early attention of patients, which seriously affects the long-term prognosis, such as high mortality, personality changes, mood disorders, psychotic reactions, financial burden and so on. This study seeks to develop and validate models for early predicting the risk of subjective cognitive decline (SCD) after CC infarction by machine learning (ML) algorithms.

Methods

This is a prospective study that enrolled 213 (only 3.7%) CC infarction patients from a nine-year cohort comprising 8,555 patients with acute ischemic stroke. Telephone follow-up surveys were carried out for the patients with definite diagnosis of CC infarction one-year after disease onset, and SCD was identified by Behavioral Risk Factor Surveillance System (BRFSS) questionnaire. Based on the significant features selected by the least absolute shrinkage and selection operator (LASSO), seven ML models including Extreme Gradient Boosting (XGBoost), Logistic Regression (LR), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Gaussian Naïve Bayes (GNB), Complement Naïve Bayes (CNB), and Support vector machine (SVM) were established and their predictive performances were compared by different metrics. Importantly, the SHapley Additive exPlanations (SHAP) was also utilized to examine internal behavior of the highest-performance ML classifier.

Results

The Logistic Regression (LR)-model performed better than other six ML-models in SCD predictability after the CC infarction, with the area under the receiver characteristic operator curve (AUC) of 77.1% in the validation set. Using LASSO and SHAP analysis, we found that infarction subregions of CC infarction, female, 3-month modified Rankin Scale (mRS) score, age, homocysteine, location of angiostenosis, neutrophil to lymphocyte ratio, pure CC infarction, and number of angiostenosis were the top-nine significant predictors in the order of importance for the output of LR-model. Meanwhile, we identified that infarction subregion of CC, female, 3-month mRS score and pure CC infarction were the factors which independently associated with the cognitive outcome.

Conclusion

Our study firstly demonstrated that the LR-model with 9 common variables has the best-performance to predict the risk of post-stroke SCD due to CC infarcton. Particularly, the combination of LR-model and SHAP-explainer could aid in achieving personalized risk prediction and be served as a decision-making tool for early intervention since its poor long-term outcome.

A Metabolism-Based Interpretable Machine Learning Prediction Model for Diabetic Retinopathy Risk: A Cross-Sectional Study in Chinese Patients with Type 2 Diabetes

The burden of diabetic retinopathy (DR) is increasing, and the sensitive biomarkers of the disease were not enough. Studies have found that the metabolic profile, such as amino acid (AA) and acylcarnitine (AcylCN), in the early stages of DR patients might have changed, indicating the potential of metabolites to become new biomarkers. We are amid to construct a metabolite-based prediction model for DR risk. This study was conducted on type 2 diabetes (T2D) patients with or without DR. Logistic regression and extreme gradient boosting (XGBoost) prediction models were constructed using the traditional clinical features and the screening features, respectively. Assessing the predictive power of the models in terms of both discrimination and calibration, the optimal model was interpreted using the Shapley Additive exPlanations (SHAP) to quantify the effect of features on prediction. Finally, the XGBoost model incorporating AA and AcylCN variables had the best comprehensive evaluation (ROCAUC = 0.82, PRAUC = 0.44, Brier score = 0.09). C18 : 1OH lower than 0.04 μmol/L, C18 : 1 lower than 0.70 μmol/L, threonine higher than 27.0 μmol/L, and tyrosine lower than 36.0 μmol/L were associated with an increased risk of developing DR. Phenylalanine higher than 52.0 μmol/L was associated with a decreased risk of developing DR. In conclusion, our study mainly used AAs and AcylCNs to construct an interpretable XGBoost model to predict the risk of developing DR in T2D patients which is beneficial in identifying high-risk groups and preventing or delaying the onset of DR. In addition, our study proposed possible risk cut-off values for DR of C18 : 1OH, C18 : 1, threonine, tyrosine, and phenylalanine.

Association between red blood cell distribution width and ischemic stroke recurrence in patients with acute ischemic stroke: a 10-years retrospective cohort analysis

Numerous studies have reported that a higher red blood cell distribution width (RDW) level was associated with adverse outcomes in patients with the first stroke. However, no studies have examined the association between RDW and recurrent ischemic stroke. We performed a population-based cohort data analysis from 2007 to 2017. Baseline RDW was measured in 6402 first ischemic stroke participants, who were followed for about five years on average. During 62 months of median follow-up, 205 participants (3.20%) reported a recurrence (self-reported). RDW showed a nonlinear relationship with the risk of ischemic stroke recurrence. When RDW was assessed as quartiles (quartile 1, RDW<12.4; quartile 2, 12.4 to 12.8; quartile 3,12.8 to 13.3, quartile4, RDW>13.3), compared with the reference group (quartile 1), the hazard ratios (HRs) of ischemic stroke recurrence were 1.372 (95% confidence interval [CI]=0.671-2.805, P=0.386) in quartile 2, 1.835 (95% CI=1.222-2.755, P=0.003) in quartile 3, and 1.732 (95% CI=1.114-2.561, P<0.001) in quartile 4. The trend test was significant (P<0.001). When quartiles 3 and 4 were combined, the adjusted HR of ischemic stroke recurrence was 1.439 (95% CI=1.330-1.556, P<0.001) compared with the combined quartiles 1 and 2 subgroups. This study demonstrated that elevated RDW levels were positively associated with an increased risk of recurrent ischemic stroke. RDW can provide a new perspective for initial risk assessment and identify high-risk patients early. Further research is required to confirm our results.