Analyzing and predicting the risk of death in stroke patients using machine learning

Individualized Analysis of Nipple-Sparing Mastectomy Versus Modified Radical Mastectomy Using Deep Learning

Background

This study aimed to evaluate the impact of nipple-sparing mastectomy (NSM) and modified radical mastectomy (MRM) on individual survival outcomes and to assess the potential of neoadjuvant systemic therapy (NST) in reducing surgical intervention requirements.

Methods

To develop treatment recommendations for breast cancer patients, five machine learning models were trained. To mitigate bias in treatment allocation, advanced statistical methods, including propensity score matching (PSM) and inverse probability treatment weighting (IPTW), were applied.

Results

NSM demonstrated either superior or noninferior survival outcomes compared with MRM across all breast cancer stages, irrespective of adjustments for IPTW and PSM. Among all models and National Comprehensive Cancer Network guidelines, the Balanced Individual and Mixture Effect (BIME) for survival regression model proposed in this study showed the strongest protective effects in treatment recommendations, as evidenced by an IPTW hazard ratio of 0.39 (95% CI: 0.26-0.59), an IPTW risk difference of 19.66% (95% CI: 18.20-21.13), and an IPTW difference in restricted mean survival time of 17.77 months (95% CI: 16.37-19.21). NST independently reduced the probability of surgical intervention by 1.4% (95% CI: 0.9%-2.0%), with the greatest impact observed in patients with locally advanced breast cancer, in whom a 4.5% reduction (95% CI: 3.8%-5.2%) in surgical selection was noted.

Conclusions

The BIME model provides superior accuracy in recommending surgical approaches for breast cancer patients, leading to improved survival outcomes. These findings underscore the potential of BIME to enhance clinical decision-making. However, further investigation incorporating comprehensive prognostic evaluation is needed to optimize the surgical selection process and refine its clinical utility.

Deep learning to optimize radiotherapy decisions for elderly patients with early-stage breast cancer: a novel approach for personalized treatment

The use of routine adjuvant radiotherapy (RT) after breast-conserving surgery (BCS) is controversial in elderly patients with early-stage breast cancer (EBC). This study aimed to evaluate the efficacy of adjuvant RT for elderly EBC patients using deep learning (DL) to personalize treatment plans. Five distinct DL models were developed to generate personalized treatment recommendations. Patients whose actual treatments aligned with the DL model suggestions were classified into the Consistent group, while those with divergent treatments were placed in the Inconsistent group. The efficacy of these models was assessed by comparing outcomes between the two groups. Multivariate logistic regression and Poisson regression analyses were used to visualize and quantify the influence of various features on adjuvant RT selection. In a cohort of 8,047 elderly EBC patients, treatment following the Deep Survival Regression with Mixture Effects (DSME) model's recommendations significantly improved survival, with inverse probability of treatment weighting (IPTW)-adjusted benefits, including a hazard ratio of 0.70 (95% CI, 0.58-0.86), a risk difference of 4.63% (95% CI, 1.59-7.66), and an extended mean survival time of 8.96 months (95% CI, 6.85-10.97), outperforming other models and the National Comprehensive Cancer Network (NCCN) guidelines. The DSME model identified elderly patients with larger tumors and more advanced disease stages as ideal candidates for adjuvant RT, though no benefit was seen in patients not recommended for it. This study introduces a novel DL-guided approach for selecting adjuvant RT in elderly EBC patients, enhancing treatment precision and potentially improving survival outcomes while minimizing unnecessary interventions.

Machine learning-based prediction of one-year mortality in ischemic stroke patients

BACKGROUND

Accurate prediction of mortality following an ischemic stroke is essential for tailoring personalized treatment strategies. This study evaluates the effectiveness of machine learning models in predicting one-year mortality after an ischemic stroke.

METHODS

Five machine learning models were trained using data from a national stroke registry, with logistic regression demonstrating the highest performance. The SHapley Additive exPlanations (SHAP) analysis explained the model's outcomes and defined the influential predictive factors.

RESULTS

Analyzing 8183 ischemic stroke patients, logistic regression achieved 83% accuracy, 0.89 AUC, and an F1 score of 0.83. Significant predictors included stroke severity, pre-stroke functional status, age, hospital-acquired pneumonia, ischemic stroke subtype, tobacco use, and co-existing diabetes mellitus (DM).

DISCUSSION

The model highlights the importance of predicting mortality in enhancing personalized stroke care. Apart from pneumonia, all predictors can serve the early prediction of mortality risk which supports the initiation of early preventive measures and in setting realistic expectations of disease outcomes for all stakeholders. The identified tobacco paradox warrants further investigation.

CONCLUSION

This study offers a promising tool for early prediction of stroke mortality and for advancing personalized stroke care. It emphasizes the need for prospective studies to validate these findings in diverse clinical settings.

Predicting stroke severity of patients using interpretable machine learning algorithms

BACKGROUND

Stroke is a significant global health concern, ranking as the second leading cause of death and placing a substantial financial burden on healthcare systems, particularly in low- and middle-income countries. Timely evaluation of stroke severity is crucial for predicting clinical outcomes, with standard assessment tools being the Rapid Arterial Occlusion Evaluation (RACE) and the National Institutes of Health Stroke Scale (NIHSS). This study aims to utilize Machine Learning (ML) algorithms to predict stroke severity using these two distinct scales.

METHODS

We conducted this study using two datasets collected from hospitals in Urmia, Iran, corresponding to stroke severity assessments based on RACE and NIHSS. Seven ML algorithms were applied, including K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Artificial Neural Network (ANN). Hyperparameter tuning was performed using grid search to optimize model performance, and SHapley Additive Explanations (SHAP) were used to interpret the contribution of individual features.

RESULTS

Among the models, the RF achieved the highest performance, with accuracies of 92.68% for the RACE dataset and 91.19% for the NIHSS dataset. The Area Under the Curve (AUC) was 92.02% and 97.86% for the RACE and NIHSS datasets, respectively. The SHAP analysis identified triglyceride levels, length of hospital stay, and age as critical predictors of stroke severity.

CONCLUSIONS

This study is the first to apply ML models to the RACE and NIHSS scales for predicting stroke severity. The use of SHAP enhances the interpretability of the models, increasing clinicians' trust in these ML algorithms. The best-performing ML model can be a valuable tool for assisting medical professionals in predicting stroke severity in clinical settings.

Determining individual suitability for neoadjuvant systemic therapy in breast cancer patients through deep learning

BACKGROUND

The survival advantage of neoadjuvant systemic therapy (NST) for breast cancer patients remains controversial, especially when considering the heterogeneous characteristics of individual patients.

OBJECTIVE

To discern the variability in responses to breast cancer treatment at the individual level and propose personalized treatment recommendations utilizing deep learning (DL).

METHODS

Six models were developed to offer individualized treatment suggestions. Outcomes for patients whose actual treatments aligned with model recommendations were compared to those whose did not. The influence of certain baseline features of patients on NST selection was visualized and quantified by multivariate logistic regression and Poisson regression analyses.

RESULTS

Our study included 94,487 female breast cancer patients. The Balanced Individual Treatment Effect for Survival data (BITES) model outperformed other models in performance, showing a statistically significant protective effect with inverse probability treatment weighting (IPTW)-adjusted baseline features [IPTW-adjusted hazard ratio: 0.51, 95% confidence interval (CI), 0.41-0.64; IPTW-adjusted risk difference: 21.46, 95% CI 18.90-24.01; IPTW-adjusted difference in restricted mean survival time: 21.51, 95% CI 19.37-23.80]. Adherence to BITES recommendations is associated with reduced breast cancer mortality and fewer adverse effects. BITES suggests that patients with TNM stage IIB, IIIB, triple-negative subtype, a higher number of positive axillary lymph nodes, and larger tumors are most likely to benefit from NST.

CONCLUSIONS

Our results demonstrated the potential of BITES to aid in clinical treatment decisions and offer quantitative treatment insights. In our further research, these models should be validated in clinical settings and additional patient features as well as outcome measures should be studied in depth.

Tailoring nonsurgical therapy for elderly patients with head and neck squamous cell carcinoma: A deep learning-based approach

To assess deep learning models for personalized chemotherapy selection and quantify the impact of baseline characteristics on treatment efficacy for elderly head and neck squamous cell carcinoma (HNSCC) patients who are not surgery candidates. A comparison was made between patients whose treatments aligned with model recommendations and those whose did not, using overall survival as the primary metric. Bias was addressed through inverse probability treatment weighting (IPTW), and the impact of patient characteristics on treatment choice was analyzed via mixed-effects regression. Four thousand two hundred seventy-six elderly HNSCC patients in total met the inclusion criteria. Self-Normalizing Balanced individual treatment effect for survival data model performed best in treatment recommendation (IPTW-adjusted hazard ratio: 0.74, 95% confidence interval [CI], 0.63-0.87; IPTW-adjusted risk difference: 9.92%, 95% CI, 4.96-14.90; IPTW-adjusted the difference in restricted mean survival time: 16.42 months, 95% CI, 10.83-21.22), which surpassed other models and National Comprehensive Cancer Network guidelines. No survival benefit for chemoradiotherapy was seen for patients not recommended to receive this treatment. Self-Normalizing Balanced individual treatment effect for survival data model effectively identifies elderly HNSCC patients who could benefit from chemoradiotherapy, offering personalized survival predictions and treatment recommendations. The practical application will become a reality with further validation in clinical settings.

Personalized chemotherapy selection for patients with triple-negative breast cancer using deep learning

Background

Potential uncertainties and overtreatment exist in adjuvant chemotherapy for triple-negative breast cancer (TNBC) patients.

Objectives

This study aims to explore the performance of deep learning (DL) models in personalized chemotherapy selection and quantify the impact of baseline characteristics on treatment efficacy.

Methods

Patients who received treatment recommended by models were compared to those who did not. Overall survival for treatment according to model recommendations was the primary outcome. To mitigate bias, inverse probability treatment weighting (IPTW) was employed. A mixed-effect multivariate linear regression was employed to visualize the influence of certain baseline features of patients on chemotherapy selection.

Results

A total of 10,070 female TNBC patients met the inclusion criteria. Treatment according to Self-Normalizing Balanced (SNB) individual treatment effect for survival data model recommendations was associated with a survival benefit (IPTW-adjusted hazard ratio: 0.53, 95% CI, 0.32-8.60; IPTW-adjusted risk difference: 12.90, 95% CI, 6.99-19.01; IPTW-adjusted the difference in restricted mean survival time: 5.54, 95% CI, 1.36-8.61), which surpassed other models and the National Comprehensive Cancer Network guidelines. No survival benefit for chemotherapy was seen for patients not recommended to receive this treatment. SNB predicted older patients with larger tumors and more positive lymph nodes are the optimal candidates for chemotherapy.

Conclusion

These findings suggest that the SNB model may identify patients with TNBC who could benefit from chemotherapy. This novel analytical approach may provide debiased individual survival information and treatment recommendations. Further research is required to validate these models in clinical settings with more features and outcome measurements.

Personalized surgical recommendations and quantitative therapeutic insights for patients with metastatic breast cancer: Insights from deep learning

Background

The role of surgery in metastatic breast cancer (MBC) is currently controversial. Several novel statistical and deep learning (DL) methods promise to infer the suitability of surgery at the individual level.

Objective

The objective of this study was to identify the most applicable DL model for determining patients with MBC who could benefit from surgery and the type of surgery required.

Methods

We introduced the deep survival regression with mixture effects (DSME), a semi-parametric DL model integrating three causal inference methods. Six models were trained to make individualized treatment recommendations. Patients who received treatments in line with the DL models' recommendations were compared with those who underwent treatments divergent from the recommendations. Inverse probability weighting (IPW) was used to minimize bias. The effects of various features on surgery selection were visualized and quantified using multivariate linear regression and causal inference.

Results

In total, 5269 female patients with MBC were included. DSME was an independent protective factor, outperforming other models in recommending surgery (IPW-adjusted hazard ratio [HR] = 0.39, 95% confidence interval [CI]: 0.19-0.78) and type of surgery (IPW-adjusted HR = 0.66, 95% CI: 0.48-0.93). DSME was superior to other models and traditional guidelines, suggesting a higher proportion of patients benefiting from surgery, especially breast-conserving surgery. The debiased effect of patient characteristics, including age, tumor size, metastatic sites, lymph node status, and breast cancer subtypes, on surgery decision was also quantified.

Conclusions

Our findings suggested that DSME could effectively identify patients with MBC likely to benefit from surgery and the specific type of surgery needed. This method can facilitate the development of efficient, reliable treatment recommendation systems and provide quantifiable evidence for decision-making.

Utilizing machine learning to facilitate the early diagnosis of posterior circulation stroke

BACKGROUND

Posterior Circulation Syndrome (PCS) presents a diagnostic challenge characterized by its variable and nonspecific symptoms. Timely and accurate diagnosis is crucial for improving patient outcomes. This study aims to enhance the early diagnosis of PCS by employing clinical and demographic data and machine learning. This approach targets a significant research gap in the field of stroke diagnosis and management.

METHODS

We collected and analyzed data from a large national Stroke Registry spanning from January 2014 to July 2022. The dataset included 15,859 adult patients admitted with a primary diagnosis of stroke. Five machine learning models were trained: XGBoost, Random Forest, Support Vector Machine, Classification and Regression Trees, and Logistic Regression. Multiple performance metrics, such as accuracy, precision, recall, F1-score, AUC, Matthew's correlation coefficient, log loss, and Brier score, were utilized to evaluate model performance.

RESULTS

The XGBoost model emerged as the top performer with an AUC of 0.81, accuracy of 0.79, precision of 0.5, recall of 0.62, and F1-score of 0.55. SHAP (SHapley Additive exPlanations) analysis identified key variables associated with PCS, including Body Mass Index, Random Blood Sugar, ataxia, dysarthria, and diastolic blood pressure and body temperature. These variables played a significant role in facilitating the early diagnosis of PCS, emphasizing their diagnostic value.

CONCLUSION

This study pioneers the use of clinical data and machine learning models to facilitate the early diagnosis of PCS, filling a crucial gap in stroke research. Using simple clinical metrics such as BMI, RBS, ataxia, dysarthria, DBP, and body temperature will help clinicians diagnose PCS early. Despite limitations, such as data biases and regional specificity, our research contributes to advancing PCS understanding, potentially enhancing clinical decision-making and patient outcomes early in the patient's clinical journey. Further investigations are warranted to elucidate the underlying physiological mechanisms and validate these findings in broader populations and healthcare settings.

Optimizing adjuvant treatment options for patients with glioblastoma

Background

This study focused on minimizing the costs and toxic effects associated with unnecessary chemotherapy. We sought to optimize the adjuvant therapy strategy, choosing between radiotherapy (RT) and chemoradiotherapy (CRT), for patients based on their specific characteristics. This selection process utilized an innovative deep learning method.

Methods

We trained six machine learning (ML) models to advise on the most suitable treatment for glioblastoma (GBM) patients. To assess the protective efficacy of these ML models, we employed various metrics: hazards ratio (HR), inverse probability treatment weighting (IPTW)-adjusted HR (HRa), the difference in restricted mean survival time (dRMST), and the number needed to treat (NNT).

Results

The Balanced Individual Treatment Effect for Survival data (BITES) model emerged as the most effective, demonstrating significant protective benefits (HR: 0.53, 95% CI, 0.48-0.60; IPTW-adjusted HR: 0.65, 95% CI, 0.55-0.78; dRMST: 7.92, 95% CI, 7.81-8.15; NNT: 1.67, 95% CI, 1.24-2.41). Patients whose treatment aligned with BITES recommendations exhibited notably better survival rates compared to those who received different treatments, both before and after IPTW adjustment. In the CRT-recommended group, a significant survival advantage was observed when choosing CRT over RT (p < 0.001). However, this was not the case in the RT-recommended group (p = 0.06). Males, older patients, and those whose tumor invasion is confined to the ventricular system were more frequently advised to undergo RT.

Conclusion

Our study suggests that BITES can effectively identify GBM patients likely to benefit from CRT. These ML models show promise in transforming the complex heterogeneity of real-world clinical practice into precise, personalized treatment recommendations.

Heterogeneous treatment effects of Cerebrolysin as an early add-on to reperfusion therapy: post hoc analysis of the CEREHETIS trial

Background: There has been intensive research into enhancing the effects of reperfusion therapy to mitigate hemorrhagic transformation (HT) in stroke patients. Using neuroprotective agents alongside intravenous thrombolysis (IVT) appears a promising approach. Cerebrolysin is one of the candidates since it consists of neuropeptides mimicking the action of neurotrophic factors on brain protection and repair. Objectives: We looked at treatment effects of Cerebrolysin as an early add-on to IVT in stroke patients with varying HT risk. Methods: It was post hoc analysis of the CEREHETIS trial (ISRCTN87656744). Patients with middle cerebral artery infarction (n = 238) were selected from the intention-to-treat population. To stratify participants according to their HT risk, the DRAGON, SEDAN and HTI scores were computed for each eligible subject using on-admission data. The study endpoints were any and symptomatic HT, and functional outcome measured with the modified Rankin Scale (mRS) on day 90. Favorable functional outcome (FFO) was defined as an mRS ≤2. The performance of each stratification tool was estimated with regression approaches. Heterogeneous treatment effect analysis was conducted using techniques of meta-analysis and the matching-smoothing method. Results: The HTI score outperformed other tools in terms of HT risk stratification. Heterogeneity of Cerebrolysin treatment effects was moderate (I2, 35.8%-56.7%; H2, 1.56-2.31) and mild (I2, 10.9%; H2, 1.12) for symptomatic and any HT, respectively. A significant positive impact of Cerebrolysin on HT and functional outcome was observed in the moderate (HTI = 1) and high (HTI ≥2) HT risk patients, but it was neutral in those with the low (HTI = 0) risk. In particular, there was a steady decline in the rate of symptomatic (HTI = 0 vs. HTI = 4: by 4.3%, p = 0.077 vs. 21.1%, p < 0.001) and any HT (HTI = 0 vs. HTI = 4: by 1.2%, p = 0.737 vs. 32.7%, p < 0.001). Likewise, an mRS score reduction (HTI = 0 vs. HTI = 4: by 1.8%, p = 0.903 vs. 126%, p < 0.001) with a reciprocal increase of the fraction of FFO patients (HTI = 0 vs. HTI = 4: by 1.2% p = 0.757 vs. 35.5%, p < 0.001) was found. Conclusion: Clinically meaningful heterogeneity of Cerebrolysin treatment effects on HT and functional outcome was established in stroke patients. The beneficial effects were significant in those whose estimated on-admission HT risk was either moderate or high.

Predicting mortality in brain stroke patients using neural networks: outcomes analysis in a longitudinal study

In this study, Neural Networks (NN) modelling has emerged as a promising tool for predicting outcomes in patients with Brain Stroke (BS) by identifying key risk factors. In this longitudinal study, we enrolled 332 patients form Imam hospital in Ardabil, Iran, with mean age: 77.4 (SD 10.4) years, and 50.6% were male. Diagnosis of BS was confirmed using both computerized tomography scan and magnetic resonance imaging, and risk factor and outcome data were collected from the hospital's BS registry, and by telephone follow-up over a period of 10 years, respectively. Using a multilayer perceptron NN approach, we analysed the impact of various risk factors on time to mortality and mortality from BS. A total of 100 NN classification algorithm were trained utilizing STATISTICA 13 software, and the optimal model was selected for further analysis based on their diagnostic performance. We also calculated Kaplan-Meier survival probabilities and conducted Log-rank tests. The five selected NN models exhibited impressive accuracy ranges of 81-85%. However, the optimal model stood out for its superior diagnostic indices. Mortality rate in the training and the validation data set was 7.9 (95% CI 5.7-11.0) per 1000 and 8.2 (7.1-9.6) per 1000, respectively (P = 0.925). The optimal model highlighted significant risk factors for BS mortality, including smoking, lower education, advanced age, lack of physical activity, a history of diabetes, all carrying substantial importance weights. Our study provides compelling evidence that the NN approach is highly effective in predicting mortality in patients with BS based on key risk factors, and has the potential to significantly enhance the accuracy of prediction. Moreover, our findings could inform more effective prevention strategies for BS, ultimately leading to better patient outcomes.