Enhancing Perioperative Decision-Making: Utilizing Machine Learning to Predict Postoperative Stroke Following Craniotomy

doi:10.21203/rs.3.rs-5202842/v1

Download PDF

Research Article

Enhancing Perioperative Decision-Making: Utilizing Machine Learning to Predict Postoperative Stroke Following Craniotomy

https://doi.org/10.21203/rs.3.rs-5202842/v1

This work is licensed under a CC BY 4.0 License

You are reading this latest preprint version

Objection:

Postoperative stroke (PS) represents a significant and grave complication, which often remains challenging to detect until clear clinical symptoms emerge. The early identification of populations at high risk for PS is essential for enabling timely intervention and enhancing postoperative outcomes. This study seeks to employ machine learning (ML) techniques to create a predictive model for PS following elective craniotomy.

Methods

This study encompassed a total of 1,349 cases that underwent elective craniotomy between January 2013 and August 2021. Perioperative data, encompassing demographics, etiology, laboratory results, comorbidities, and medications, were utilized to construct predictive models. Nine distinct ML models were developed for the prediction of PS and assessed based on the area under the receiver-operating characteristic curve (AUC), along with sensitivity, specificity, and accuracy metrics.

Results

Among the 1,349 patients included in the study, 137 cases (10.2%) were diagnosed with PS, which was associated with a worse prognosis. Of the nine ML prediction models evaluated, the logistic regression (LR) model exhibited superior performance, as indicated by an AUC value of 0.741 (0.64–0.85), and competitive performance metrics, including an accuracy of 0.668, sensitivity of 0.650, and specificity of 0.670. Notably, feature importance analysis identified "preoperative albumin," "ASA classification," and "preoperative hemoglobin" as the top three factors contributing to the prediction of PS.

Conclusion

Our study successfully developed a real-time and easily accessible parameter requiring LR-based PS prediction model for post-elective craniotomy patients, which enhanced perioperative decision-making.

intracranial surgery

complication

predictive model

postoperative stroke

machine learning

Stroke is globally acknowledged as the second leading cause of death and disability[1]. China, in particular, carries the highest burden of stroke, as indicated by its age-standardized prevalence rates[2]. Numerous studies have consistently shown that the Chinese population exhibits a slightly higher incidence of stroke and intracerebral hemorrhage compared to Caucasian populations[3]. Incidence is reported in the 0.1–0.7% range in adults undergoing non-cardiac and non-neurological surgery, in the 1–5% range in patients undergoing cardiac surgery and in the 1–10% range following neurological surgery[4].

Early postoperative stroke (PS), which is defined as a stroke occurring within 7 days following surgery, exhibits a relatively low incidence rate, thanks to advancements in surgical and anesthetic techniques[5]. Nonetheless, the occurrence of PS significantly affects patient outcomes, manifesting as an 8-fold increase in mortality. The inconspicuous onset of stroke during intraoperative anesthesia, coupled with the administration of postoperative sedative drugs and associated complications, poses challenges in promptly identifying symptoms[6]. As a result, the absence of early, clear, and reliable diagnostic methods impedes the prompt recognition and provision of effective treatment for patients experiencing early PS[7].

Anesthesiologists typically give precedence to factors such as preoperative laboratory tests, intraoperative fluid therapy, monitoring of intraoperative vital signs, and intraoperative drug therapy. However, these specific data points have not yet been formally integrated into diagnostic tools designed to aid in the early detection of PS[8]. At present, making a comprehensive and accurate assessment based solely on physicians' electronic medical records and intraoperative data for prognostication is impractical[9]. The adoption of machine learning (ML) technology presents an opportunity to augment physicians' diagnostic abilities in predicting PS by enabling detailed analyses of large datasets. Currently, there have been numerous articles discussing machine learning prediction models for perioperative stroke[10; 11; 12]; however, no studies specifically addressing perioperative stroke after craniotomy have been documented In intracranial surgery, surgical approaches may inadvertently injure adjacent nerves tissue and blood vessels, which can cause bleeding[13]. Certain risk factors have been identified as contributing to a higher risk of PS[14], such as hypertension, cancer, congestive heart failure, chronic pulmonary disease, and peripheral vascular disease[15]. Factors related to intraoperative anesthesia also significantly influence PS, yet previous studies have largely overlooked anesthesia's role. The incidence of PS following craniotomy exceeds that observed in non-aortic surgeries due to the intricate nature of the surgical site[4]. Additionally, it is crucial to acknowledge that the occurrence of PS after craniotomy is not solely attributed to surgical factors but also influenced by the patients' perianaesthetic period condition[16]. Consequently, the aim of this study was to identify independent risk factors for PS in patients undergoing elective intracranial surgery, to develop predictive models using ML algorithms, and to evaluate their effectiveness in predicting PS.

2.1 Ethics statements

This study, conducted at the Third Affiliated Hospital of Sun Yat-sen University, received approval from the Ethics Review Committee [No. (2019)02-609-01]. The study design involved extracting a restricted dataset from the perioperative database. Given the retrospective design, the requirement for informed patient consent was waived. The study was conducted according to STROBE guidelines.

2.2 Study population

In this retrospective study, the selection of the patient cohort and the study design were based on data retrieved from the electronic patient record (EPR) systems at the Third Affiliated Hospital of Sun Yat-sen University, situated in Guangzhou, Guangdong, China.

A comprehensive database platform was developed within the EPR systems of our hospital by integrating medical records from multiple systems, including the Hospital Information System (HIS), Laboratory Information System (LIS), Picture Archiving and Communication System (PACS), and the Docare Anesthesia System (2005–2020, Medical System Co., Ltd., Suzhou, China). This innovative database platform enabled the efficient retrieval of extensive data encompassing various facets of hospitalization, such as admission details, length of stay, and follow-up post-hospital visits. The platform provided access to a broad spectrum of information, including demographic details, daily documentation, laboratory test results, imaging findings, anesthesia records, and other pertinent clinical characteristics.

2.3 Primary outcome

The primary outcome of this study was the incidence of PS following elective craniotomy. PS was defined as either cerebral ischemia or cerebral hemorrhage occurring within 7 days post-surgery. The diagnostic criteria for PS adhered to the guidelines provided by the American Stroke Association, which include: (1) Cerebral ischemia resulting from thrombosis, embolism, or systemic hypoperfusion; (2) Intracerebral hemorrhage, where hemorrhage within the brain parenchyma directly affects brain tissue, and hemorrhage within the subarachnoid space impacts the cerebrospinal fluid that surrounds the brain and spinal cord.

2.4 Data collection

The database platform provided data elements categorized into the following sections for analysis:

1. Demographics: This included age, sex, height, and weight of the patients.

2. Preoperative comorbidities: Data on hypertension, coronary heart disease, myocardial infarction, diabetes mellitus, history of alcohol abuse, smoking, and previous surgeries were collected.

3. Etiology: The primary diseases necessitating intracranial surgery were identified, with a focus on brain tumors, cerebrovascular diseases, and other conditions.

Perioperative laboratory values: Laboratory results encompassing liver function, kidney function, electrolytes, and blood cell count were analyzed.

Preoperative complications: Information was gathered on complications and metrics indicating patient severity, including complications from hypertension, documentation of treatment escalation such as length of stay in the ICU, use of continuous blood purification (CBP), and mechanical ventilation.

Intraoperative events: Events indicative of hemodynamic instability, such as cardiac arrest, arrhythmia, lactic acidosis, acidosis, hypernatremia, hypokalemia, and hypotension, were recorded.

Intraoperative fluid and transfusion: Data on the total intraoperative fluid infusion and output, along with the total transfused blood products, were extracted. This included RBC transfusion, plasma transfusion, total blood product transfusion, and total fluid transfusion, categorized based on specific criteria.

Perioperative medications: The administration of medications during the surgery and the subsequent seven-day postoperative period was closely monitored. This primarily included glucocorticoids, mannitol, and sedatives. After extraction of the original data, patients were divided into two groups with PS as the primary outcome measure. An analysis was then performed to examine the differences in the distribution of each characteristic between the two groups.

2.5 Variable selection

With a total of 50 variables, the potential for overfitting during the training process poses a risk to the overall performance of the model. The implementation of a univariate test is only on the training set, in order to ensure the independence of the validation set. Consequently, we proceeded to remove variables that exhibited a missing data rate exceeding 30% within the training set, as well as those with a correlation coefficient greater than 0.7, which indicated poor predictive capability. Subsequently, the data underwent preprocessing with mean imputation for continuous variables and mode imputation for categorical variables. Following this, Yeo-Johnson normality transformation, centralization, and normalization were conducted. The LASSO(Least Absolute Shrinkage and Selection Operator) method is employed for feature selection, which involves analyzing the dataset prior to model training in order to identify features that contribute to predicting the target variable or impacting the model's performance.

2.6 Model training

Before deploying ML models, all variables in the study were subjected to centralization and normalization processes. Continuous variables were transformed for normality using the Yeo-Johnson method and missing values were imputed with the mean, whereas categorical variables had their missing values filled with the mode. The dataset was then split into an 80% training set and a 20% test set. The training set was utilized for the development of predictive models, and the test set served to validate the performance of these models.

After preprocessing and feature selection, we constructed ML classifiers employing nine techniques, including logistic regression (LR) [17], random forest (RF) [14], adaptive boosting (Adaboosting) [18], XGboosting[19], bootstrap aggregating (Bagging) [20], gradient boosting (GB) [21], K-Nearest neighbor (KNN)[22], decision trees (DT)[23], and Gaussian NB [24].. A grid search was used to find the optimal hyperparameters for each algorithm (Supplementary Table 4). To estimate the performance of each model, we compared them using the AUC, sensitivity, specificity, F1 value, and accuracy, and then, the optimal model was chosen for external validation. Permutation was used to rank the importance of the variables that were included in the final model. Based on the above 14 predictors, we evaluated the nine machine learning algorithms, using the best hyperparameter values selected by the GridSearchCV technique (Supplementary Table 3).

2.7 Statistical methods

The statistical analysis was performed using SPSS 22.0. The frequency or percentage was used to describe categorical variables, while the Pearson chi-square test was employed to compare groups. Mean ± standard deviation (SD) was used to describe continuous variable data, whereas median and quartile were used for skewed distribution data. T-test and nonparametric rank-sum test were utilized to compare normal and skewed distribution data, respectively.

The dataset comprised data from 3,297 patients who underwent elective craniotomy between January 2013 and August 2021. In the course of retrospective enrollment, patients were excluded from this study for the following reasons: preoperative stroke (n = 589), absence of electronic medical records (n = 273), undergoing a second surgery (n = 589), and undergoing non-intracranial surgery (n = 497).

This study conducted a retrospective analysis of the clinical data from 1,349 patients who underwent elective craniotomy at our hospital. Among these patients, 137 experienced early PS, yielding an incidence of 10.2% (Fig. 1).

3.1 Baseline characteristics

Table 1 presents the baseline characteristics of the study's patient population, offering summary statistics for the perioperative variables of the 1,349 patients included in the complete analysis cohort. Baseline data of the training and test sets are presented in Supplementary Table 1. The median age of the participants was 48.6 years, with males constituting 47% of the cohort. Compared to healthy controls, elderly patients with an ASA grade of ≥ 3, those requiring preoperative endotracheal intubation, and those showing preoperative reductions in fibrinogen were observed to have a significantly higher prevalence of PS (all P < 0.05). Furthermore, patients who experienced PS tended to have longer surgical durations and were associated with higher estimated blood loss.

Table 1

Baseline information of included patients
Category	Entire Cohort (n = 1349)	Stroke (n = 137)	Healthy Control (n = 1212)
Age,y	48.6 ± 14.4	52.9 ± 13.3	48.1 ± 14.4
Male sex	634(47%)	75(55%)	557(45.0%)
Height(cm)	163.3 ± 8.0	164.5 ± 7.6	163.1 ± 8.0
Weight(kg)	60.5 ± 11.3	61.8 ± 11.4	60.4 ± 11.3
BMI	22.7 ± 3.6	22.7 ± 3.8	22.7 ± 3.6
Diabetes	256(19.0%)	35(25.5%)	220(18.2%)
Hypertension	411(30.5%)	39(28.5%)	372(30.7%)
abnormal kidney function	29(2.1%)	6(4.4%)	23(1.9%)
abnormal liver function	52(3.9%)	5(3.6%)	47(3.9%)
abnormal Coagulation	38(2.8%)	4(2.9%)	34(2.8%)
Allergy history	31(2.3%)	5(3.6%)	26(2.1%)
ICU admission before surgery	7(0.5%)	0(0%)	7(0.6%)
Preoperative tracheal intubation	36(2.7%)	9(6.6%)	27(2.2%)
Preoperative WBC	6.88 ± 2.31	6.89 ± 2.3	6.81 ± 2.2
Preoperative HGB	132.12 ± 16.71	129.00 ± 15.01	132.5 ± 16.9
Preoperative NEUT%	0.60 ± 0.11	0.63 ± 0.10	0.59 ± 0.11
Preoperative Plt	250.04 ± 69.74	252.7 ± 83.5	249.7 ± 68.1
Preoperative APTT	36.94 ± 4.468	36.4 ± 4.3	37.0 ± 4.5
Preoperative PT	0.99 ± 0.08	0.98 ± 0.07	0.99 ± 0.09
Preoperative Fib	3.41 ± 1.02	3.6 ± 1.1	3.4 ± 1.0
Preoperative Na	141.30 ± 3.22	141.2 ± 3.1	141.3 ± 3.2
Preoperative K	3.90 ± 0.43	3.94 ± 0.40	3.90 ± 0.43
Preoperative Ca	2.39 ± 0.13	2.39 ± 0.13	2.39 ± 0.13
Preoperative AST	21.61 ± 14.66	24.51 ± 31.84	21.3 ± 11.3
Preoperative ALT	24.31 ± 22.45	28.1 ± 38.9	23.9 ± 19.8
Preoperative ALB	42.82 ± 4.25	41.9 ± 4.5	42.9 ± 4.2
Preoperative TBLIL	9.86 ± 5.55	9.23 ± 9.5	9.9 ± 4.9
Preoperative Glu	5.62 ± 1.71	5.6 ± 1.6	5.6 ± 1.7
Preoperative A/G	1.65 ± 0.31	1.68 ± 0.32	1.65 ± 0.30
Preoperative BUN	5.10 ± 1.96	5.4 ± 2.5	5.1 ± 1.9
Preoperative eGFR	102.45 ± 19.70	104.79 ± 18.37	100.92 ± 19.49
Operation time (min)	173(105,267)	199.6(102,237)	197.6(105,283)
Intraoperative crystalloid volume (mL)	1300(600, 2200)	1300(700, 2000)	1375(600,2200)
Intraoperative colloid volume(mL)	500(500,1000)	500(500,1000)	500(500,1000)
Intraoperative urine(mL)	750(300,1300)	700(300,1300)	800(300,1400)
Intraoperative blood loss(mL)	100(20,200)	80(20,200)	100(30, 200)
Intraoperative amount(mL)	2000(1100,3200)	1950(1200,2900)	2000(1100,3225)
Intraoperative blood transfusion(mL)	0(0,0)	0(0,0)	0(0,0)
Intraoperative mannitol(mL)	0(0,62.5)	0(0,0)	0(0,100)
Intraoperative total output(mL)	715(212,1350)	700(230,1300)	750(210,1400)
postoperative hospital stay	9.0(5.0,15.0)	7.0(3.0,10.5)	10(6.0,17.0)
Total cost of hospitalization	61494(44732,87487)	56150(41623,79370)	64331(46626,90364)
ASA Classfication ≥III	245(18.2%)	44(32.1%)	201(16.7%)
Abbreviations:
BMI, body mass index; WBC, white blood cell; HGB, hemoglobin; NEUT%, percentage of neutrophils; Plt, platelet count; APTT, activated partial thromboplastin time; PT, prothrombin time; Fib, fibrinogen; AST, aspartate aminotransferase; ALT, alanine aminotransferase; ALB, albumin; TBILI, total bilirubin. Glu, glucose. A/G, albumin /globulin; BUN, blood urea nitrogen; eGFR, estimated glomerular filtration rate.

3.2 Feature selection

Based on tenfold cross-validation, we chose the optimal value of ln (lambda) for LASSO regression as – 5.254 (1-SE criterion). By filtering out the nonzero coefficient features, 14 predictors, which included "gender," "preoperative ICU admission," "preoperative diabetes," "age," "ASA classification," "leukocyte count," "hemoglobin," "fibrinogen," "prothrombin time," "albumin," "alanine aminotransferase," "total bilirubin," "albumin/globulin ratio," and "serum potassium.", were finally selected for model building, as shown in Fig. 2. The correlation among the included variables in the training set is presented in Supplementary Fig. 1.

3.3 Model performance

To predict PS following elective intracranial surgery, we utilized several ML algorithms. Based on the receiver operating characteristic (ROC) curves (Fig. 3) and the performance characteristics (Table 2) of the nine distinct ML models, the LR model demonstrated superior predictive performance, achieving the highest AUC of 0.741 (95% Confidence Interval [CI]: 0.64–0.85). Additionally, the LR model attained noteworthy sensitivity, specificity, and accuracy values of 0.650, 0.670, and 0.668, respectively. The AUCs of the LR algorithm in the training set, and test set were 0.741 (95% CI 0.638, 0.844), and 0.655 (95% CI 0.559–0.752), respectively (Supplementary Table 2 and Supplementary Fig. 2), which showed well performance in predicting prognosis.

Table 2

Features of each machine learning model.
Metrics	AUC	Cutoff	Sensitivity	Specificity	Accuracy
Logistic Regression	0.741 (0.638, 0.844)	0.111	0.650	0.670	0.668
AdaBoost	0.728 (0.607, 0.85)	0.195	0.800	0.644	0.659
Bagging	0.637 (0.511, 0.764)	0.120	0.600	0.598	0.598
Gradient Boost	0.645 (0.525, 0.764)	0.077	0.600	0.598	0.598
Random Forest	0.739 (0.637, 0.84)	0.111	0.700	0.701	0.701
XGBoost	0.578 (0.43, 0.726)	0.231	0.550	0.552	0.551
Gaussian NB	0.727 (0.616, 0.837)	0.030	0.650	0.649	0.650
KNN	0.628 (0.486, 0.769)	0.097	0.600	0.598	0.598
Decision Tree	0.537 (0.407, 0.667)	0.009	0.550	0.515	0.519
Abbreviations: NB, naïve Bayesian; KNN, k-nearest neighbor.

3.4 Feature importance

The results depicted in Fig. 4 revealed that within the LR model, the five features with the highest importance were "preoperative plasma albumin level", "ASA classification", "preoperative routine blood hemoglobin level", "plasma albumin/globulin ratio", and "total bilirubin level". These variables exhibited a significant impact on the model's outcome. In contrast, variables ranked lower demonstrated minimal significance and offered limited interpretability in the context of the study.

In our study, we enrolled 1,349 patients following elective intracranial surgery, observing a morbidity rate of PS at 10.2%, with 6.3% attributed to hemorrhagic stroke and 4.7% to ischemic stroke. In this study, we developed nine ML prediction models, including LR, GDB, RF, XGBoost, NB, KNN, and DT, was assessed using the test set. Our findings indicate that the LR model excelled in predicting PS, achieving an AUC of 0.741. Furthermore, the LR model exhibited an accuracy rate of 0.668, a sensitivity of 0.650, and a specificity of 0.670.

Through feature importance analysis, it was identified that "preoperative plasma albumin level", "ASA classification", "preoperative routine blood hemoglobin level", "plasma albumin/globulin ratio", and "total bilirubin level" emerged as the top five significant features for predicting PS. Most patients with a high ASA classification possess comorbidities, including diabetes mellitus and hypertension, which are recognized risk factors for stroke[25].Several studies have shown that serum albumin levels are significantly and negatively associated with stroke risk[26; 27]. Moreover, long-term mortality is increased in acute ischemic stroke with low or below normal albumin[27]. This correlates with the role of albumin in modulating pyruvate dehydrogenase, which increases the flux of glucose and lactate in astrocytes, enhances the formation of anti-inflammatory lipoxins, resolvins, and protectins derived from docosahexaenoic acid and other polyunsaturated fatty acids, thereby reducing ischemia-induced neuronal damage[28]. Previous studies have consistently demonstrated a correlation between preoperative hemoglobin levels and the incidence and prognosis of PS[29]. Moreover, a meta-analysis provided compelling evidence supporting the association between admission anemia and both ischemic and hemorrhagic stroke, as well as elevated mortality rates related to stroke[30]. The direct link between anaemia and cerebrovascular events is the blood supply, as anaemia results in a reduction of oxygen supply, potentially leading to hypoxic neuronal damage. Moreover, anaemia is considered a hyperkinetic state that disrupts endothelial adhesion molecule genes, which may contribute to thrombus formation[31]. Another contributing factor to the incidence of PS is the preoperative plasma albumin/globulin ratio. In a recent study, Beamer et al. observed that patients presenting with high clinical risk factors for stroke were significantly more likely to experience subsequent vascular events, which were associated with a lower blood albumin/globulin ratio[32]. Wang et al. demonstrated that elevated bilirubin levels are associated with a reduced risk of stroke in adults, which aligns with our results[33]. This finding correlates with the antioxidant, anti-inflammatory, and anti-atherosclerotic properties of serum bilirubin [34; 35].

These indicators mentioned were all incorporated into our prediction model, which typically utilizes data routinely collected after admission, underscoring the model's practical feasibility and generalizability within a hospital setting. The predictive factors identified in our model align with the risk factors highlighted in several prior studies, reinforcing its validity. The LR algorithm employed in this study offers distinct advantages over traditional statistical methods, including a transparent model structure and a probability derivation that is robust and open to scrutiny. The parameters within the model elucidate the impact of each feature on the outcome, providing high interpretability. Moreover, the model supports online learning, enabling easy parameter updates without the need for retraining the entire model. Consequently, this model not only integrates the predictive efficiency of key factors but boasts commendable interpretability.

Currently, there is a paucity of research on PS in the field of neuroanesthesiology[36]. Nonetheless, among the sparse ML studies available, one conducted by Zhang et al. stands out[11]. They discovered that the XGBoost model displayed the highest AUC of 0.78 for predicting PS in elderly patients. The study identified hypertension, cancer, congestive heart failure, chronic lung disease, and peripheral vascular disease as the top five predictors[11]. It is important to highlight that the study did not place any restrictions on the types of surgical procedures evaluated, potentially encompassing high-risk interventions for stroke, such as cardiac macrovascular surgery. Additionally, another study identified advanced age, pre-existing valvular heart disease, previous stroke, emergency surgery, and postoperative hypotension as independent risk factors for PS[37]. Patients necessitating emergency surgery exhibit a heightened vulnerability to postoperative complications, including postoperative seizures. Consequently, these patients were excluded from the aforementioned studies to ensure a more focused and controlled analysis of risk factors and outcomes.

The incidence of PS can be linked to a variety of pathologic and physiologic mechanisms. The administration of anesthesia and the execution of the surgical procedure provoke a systemic inflammatory response, leading to alterations in the concentrations of inflammatory mediators and the coagulation status of the blood. These alterations enhance the risk of perioperative thrombosis and intravascular plaque instability, subsequently elevating the probability of stroke in perioperative patients [38; 39].

Our research represents the inaugural effort to construct a predictive model for PS using a ML-based LR algorithm, specifically designed for patients undergoing elective intracranial surgery. This model is distinguished by its explainability through feature importance analysis. Moreover, by statistically addressing the issue of unbalanced data, we have developed a practical predictive tool that enables clinicians to fine-tune clinical therapy.

Nonetheless, our study is not without its limitations. Firstly, the presence of missing values in the original dataset could compromise the stability of our predictive ML model. Secondly, the study's sample size was relatively small, necessitating a larger, multicenter sample to further substantiate the predictive model's validity. Thirdly, this predictive model requires an independent dataset to assess its extrapolation and generalization capabilities accurately. The accuracy of our final model is limited by the relative inadequacy of included data items and the complexity of PS. Lastly, anesthesia-related incidents such as persistent intraoperative hypotension/hypertension during the perianesthetic period were not included due to insufficient data availability. Future endeavors will focus on gathering comprehensive external validation datasets to enhance the validity of this model.

This study has successfully created a real-time and readily accessible LR-based prediction model for PS in patients following elective craniotomy. The optimal application of this ML model facilitates prompt risk assessment and clinical decision-making, with the potential to enhance patient outcomes. Nonetheless, additional research and validation are essential to refine and broaden the model's applicability.

Funding

This study was partly supported by the Natural Science Foundation of Guangdong Province (Grant No. 2022A1515012603), Science and Technology Program of Guangzhou City (No.2024A04J4246 and 202201020429); Joint Funds of the National Natural Science Foundation of China (No.U22A20276), Science and Technology Planning Project of Guangdong Province-Regional Innovation Capacity and Support System Construction (No. 2023B110006). Provincial-enterprise Joint Funds of Guangdong Basic and Applied Basic Research Foundation (No.2021B1515230012) and the “Five and five” Project of the Third Affiliated Hospital of Sun Yat-Sen University (No.2023WW501)

Acknowledgement

The authors thank all the patients participated in the study.

Conflict of interest

The authors declare no competing interests.

Authors’ contributions

TYL, CJC and ZQH conducted the research design. TYL and CYW participated in the writing of the paper. TYL, YXP and TSL analyzed and explained the data; YXL, WJL, LPL and JC collected and helped with analyzing the data of the study. All authors read and approved the final manuscript.

Ethics

Our study was approved by the Ethnic Committee of the Third Affiliated Hospital of Sun Yat-sen University [No. (2019)02-609-01].

Consent for publication

Not applicable.

Data availability statements

As this experimental data is classified as internal hospital data, the information presented in this study can be obtained upon request from the corresponding author.

Global regional, national burden of neurological disorders. 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet Neurol. 2019;18:459–80.
Wang W, Jiang B, Sun H, Ru X, Sun D, Wang L, Wang L, Jiang Y, Li Y, Wang Y, Chen Z, Wu S, Zhang Y, Wang D, Wang Y, Feigin VL. Prevalence, Incidence, and Mortality of Stroke in China: Results from a Nationwide Population-Based Survey of 480 687 Adults. Circulation. 2017;135:759–71.
Tsai C-F, Thomas B, Sudlow CLM. Epidemiology of stroke and its subtypes in Chinese vs white populations: a systematic review. Neurology. 2013;81:264–72.
Fanning JP, Campbell BCV, Bulbulia R, Gottesman RF, Ko S-B, Floyd TF, Messé SR. Perioperative stroke. Nat Rev Dis Primers. 2024;10:3.
Wilhelmsen L, Svärdsudd K, Korsan-Bengtsen K, Larsson B, Welin L, Tibblin G. Fibrinogen as a risk factor for stroke and myocardial infarction. N Engl J Med. 1984;311:501–5.
Mashour GA, Shanks AM, Kheterpal S. Perioperative stroke and associated mortality after noncardiac, nonneurologic surgery. Anesthesiology. 2011;114:1289–96.
Borger V, Schuss P, Kinfe TM, Vatter H, Güresir E. Decompressive Craniectomy for Stroke: Early Cranioplasty Is a Predictor for Postoperative Complications. World Neurosurg. 2016;92:83–8.
Kim HJ, Lee E-J, Jung S-H, Lee JW, Kim JS, Kim JB, Kwon SU. Cerebral atherosclerosis and early ischemic stroke after left-sided valve replacement surgery. J Thorac Cardiovasc Surg 163 (2022).
Teoh D. Towards stroke prediction using electronic health records. BMC Med Inf Decis Mak. 2018;18:127.
Dai D, Tu S, Gao Z. Development and validation of a machine learning-based model for postoperative ischemic stroke in middle-aged and elderly patients with hip or knee arthroplasty. Medicine. 2022;101:e29542.
Zhang X, Fei N, Zhang X, Wang Q, Fang Z. Machine Learning Prediction Models for Postoperative Stroke in Elderly Patients: Analyses of the MIMIC Database. Front Aging Neurosci. 2022;14:897611.
Ren Y, Loftus TJ, Datta S, Ruppert MM, Guan Z, Miao S, Shickel B, Feng Z, Giordano C, Upchurch GR, Rashidi P, Ozrazgat-Baslanti T, Bihorac A. Performance of a Machine Learning Algorithm Using Electronic Health Record Data to Predict Postoperative Complications and Report on a Mobile Platform. JAMA Netw Open. 2022;5:e2211973.
Nadig AS, King AT. Traumatic extradural haematoma revealed after contralateral decompressive craniectomy. Br J Neurosurg. 2012;26:877–9.
Heo J, Yoon JG, Park H, Kim YD, Nam HS, Heo JH. Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke. Stroke. 2019;50:1263–5.
Pai S-L, Wang RD, Aniskevich S. Perioperative stroke: incidence, etiologic factors, and prevention. Minerva Anestesiol. 2017;83:1178–89.
Fadayomi AB, Akeju O. Anesthesia for stroke rescue. Curr Opin Anaesthesiol. 2018;31:544–8.
Zhang Z, Ho KM, Hong Y. Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care. Crit Care (London England). 2019;23:112.
Wang J, Xue W, Shi X, Xu Y, Dong C. Adaboost-Based Machine Learning Improved the Modeling Robust and Estimation Accuracy of Pear Leaf Nitrogen Concentration by In-Field VIS-NIR Spectroscopy. Sens (Basel) 21 (2021).
Hou N, Li M, He L, Xie B, Wang L, Zhang R, Yu Y, Sun X, Pan Z, Wang K. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost. J Transl Med. 2020;18:462.
Lin E, Lin C-H, Lane H-Y. A bagging ensemble machine learning framework to predict overall cognitive function of schizophrenia patients with cognitive domains and tests. Asian J Psychiatr. 2022;69:103008.
Lee YW, Choi JW, Shin E-H. Machine learning model for predicting malaria using clinical information. Comput Biol Med. 2021;129:104151.
Liu W, Wang S, Ye Z, Xu P, Xia X, Guo M. Prediction of lung metastases in thyroid cancer using machine learning based on SEER database. Cancer Med. 2022;11:2503–15.
Elhazmi A, Al-Omari A, Sallam H, Mufti HN, Rabie AA, Alshahrani M, Mady A, Alghamdi A, Altalaq A, Azzam MH, Sindi A, Kharaba A, Al-Aseri ZA, Almekhlafi GA, Tashkandi W, Alajmi SA, Faqihi F, Alharthy A, Al-Tawfiq JA, Melibari RG, Al-Hazzani W, Arabi YM. Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU. J Infect Public Health. 2022;15:826–34.
Singh SK, Taylor RW, Pradhan B, Shirzadi A, Pham BT. Predicting sustainable arsenic mitigation using machine learning techniques. Ecotoxicol Environ Saf. 2022;232:113271.
Global regional. national burden of stroke and its risk factors, 1990–2019: a systematic analysis for the Global Burden of Disease Study 2019. Lancet Neurol. 2021;20:795–820.
Wang Y, Zhuang Y, Huang H, Ke J, Lin S, Chen F. Association of serum albumin levels and stroke risk in adults over 40 years: A population-based study. Medicine. 2023;102:e34848.
Li J, Imano H, Yamagishi K, Cui R, Muraki I, Umesawa M, Hayama-Terada M, Ohira T, Kiyama M, Okada T, Sankai T, Tanigawa T, Kitamura A, Iso H. Serum Albumin and Risks of Stroke and Its Subtypes - The Circulatory Risk in Communities Study (CIRCS). Circ J. 2021;85:385–92.
Das UN. Albumin and lipid enriched albumin for the critically ill. J Assoc Physicians India. 2009;57:53–9.
Wang Y, Qin W, Hu W. An analysis of the risk of perioperative ischemic stroke in patients undergoing non-cardiovascular and non-neurological surgeries. Neurol Res. 2020;42:55–61.
Barlas RS, Honney K, Loke YK, McCall SJ, Bettencourt-Silva JH, Clark AB, Bowles KM, Metcalf AK, Mamas MA, Potter JF, Myint PK. Impact of Hemoglobin Levels and Anemia on Mortality in Acute Stroke: Analysis of UK Regional Registry Data, Systematic Review, and Meta-Analysis. J Am Heart Assoc 5 (2016).
Kaiafa G, Savopoulos C, Kanellos I, Mylonas KS, Tsikalakis G, Tegos T, Kakaletsis N, Hatzitolios AI. Anemia and stroke: Where do we stand? Acta Neurol Scand. 2017;135:596–602.
Beamer N, Coull BM, Sexton G, de Garmo P, Knox R, Seaman G. Fibrinogen and the albumin-globulin ratio in recurrent stroke. Stroke. 1993;24:1133–9.
Wang G, Qiao L, Tang Z, Zhou S, Min J, Li M. Association between bilirubin levels and risk of stroke: a systematic review and meta-analysis. BMJ open. 2023;13:e064433.
Vítek L. The role of bilirubin in diabetes, metabolic syndrome, and cardiovascular diseases. Front Pharmacol. 2012;3:55.
Schwertner HA, Vítek L. Gilbert syndrome, UGT1A1*28 allele, and cardiovascular disease risk: possible protective effects and therapeutic applications of bilirubin. Atherosclerosis 198 (2008).
Pasternak JJ. Neuroanesthesiology Update. J Neurosurg Anesthesiol. 2019;31:178–98.
Vasivej T, Sathirapanya P, Kongkamol C. Incidence and Risk Factors of Perioperative Stroke in Noncardiac, and Nonaortic and Its Major Branches Surgery. J Stroke Cerebrovasc Dis. 2016;25:1172–6.
Schietroma M, Carlei F, Mownah A, Franchi L, Mazzotta C, Sozio A, Amicucci G. Changes in the blood coagulation, fibrinolysis, and cytokine profile during laparoscopic and open cholecystectomy. Surg Endosc. 2004;18:1090–6.
Rost NS, Wolf PA, Kase CS, Kelly-Hayes M, Silbershatz H, Massaro JM, D'Agostino RB, Franzblau C, Wilson PW. Plasma concentration of C-reactive protein and risk of ischemic stroke and transient ischemic attack: the Framingham study. Stroke. 2001;32:2575–9.

No competing interests reported.

Download PDF

Editorial decision: Revision requested
04 Oct, 2024
Editor assigned by journal
04 Oct, 2024
Submission checks completed at journal
04 Oct, 2024
First submitted to journal
04 Oct, 2024

You are reading this latest preprint version

Enhancing Perioperative Decision-Making: Utilizing Machine Learning to Predict Postoperative Stroke Following Craniotomy

Status:

Version 1

Abstract

Objection:

Methods

Results

Conclusion

Figures

1. Introduction

2. Materials and Methods

2.1 Ethics statements

2.2 Study population

2.3 Primary outcome

2.4 Data collection

2.5 Variable selection

2.6 Model training

2.7 Statistical methods

3. Results

3.1 Baseline characteristics

3.2 Feature selection

3.3 Model performance

3.4 Feature importance

4. Discussion

5. Conclusion

Declarations

References

Additional Declarations

Supplementary Files

Status:

Version 1