Survival Prediction After Neurosurgical Resection of Brain Metastases: A Machine Learning Approach

Hulsbergen, Alexander; Lo, Yu Tung; Awakimjan, Ilia; Kavouridis, Vasileios K.; Phillips, John G.; Smith, Timothy R.; Verhoeff, Joost J.C.; Yu, Kun‐Hsing; Broekman, Marike L D; Arnaout, Omar

doi:10.1227/neu.0000000000002037

Cited by 5 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of NSCLC-BMs, J.P. Agarwal and colleagues conducted survival prognosis for patients following WBRT [23]. Regarding survival prediction for postsurgery BMs patients, Hulsbergen AFC built a model to predict 6-month survival after BM resection [24]. However, there is currently a lack of relevant models for predicting long-term survival.…”

Section: Predictive Modelmentioning

confidence: 99%

Prognostic factors in postoperative brain metastases derive from non-small cell lung cancer：a retrospective analysis

Chen,

Sun,

Yang

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Brain metastases are crucial in cancer progression, requiring focused efforts on the screening, early detection, and treatment. However, accurately forecasting the postoperative prognosis of patients with non-small cell lung cancer brain metastasis remains a challenge. This retrospective study aims to discern the factors that influence the prognosis of such patients. Patients and materials: A total of 151 cases from Zhejiang Cancer Hospital were collected. Univariate analysis was conducted using Kaplan-Meier and Log-rank test, while multivariate analysis was performed using Cox proportional hazards regression model. Student’s t-test and chi-square test were employed to examine the differences between the long-term survival and the short-term survival groups. Ultimately, a predictive model was constructed by using R 4.2.1. Results: Univariate analysis identified 12 factors as prognostic factors, showing statistical significance. In multivariate analysis, the primary contributing factors to survival were identified as age, chemotherapy of brain metastases, pathology, surgery of non-small cell lung cancer, targeted drugs, and GPA score. Compared long-term and short-term groups, age, pathology, surgery of lung, targeted therapy, and radiotherapy of brain metastases were statistically differentiating factors. Based on multivariate analysis, we established a clinical predictive model predicting 2-year, 3-year, and 5-year survival rates. Conclusion: Younger age, receiving chemotherapy for brain metastases, adenocarcinoma pathology, lung cancer surgery, targeted therapy, and a high GPA score are associated with longer survival. This model predicts the survival period for patients with non-small cell lung cancer brain metastasis after surgery and helps in selecting more effective treatment plans.

show abstract

Section: Predictive Modelmentioning

confidence: 99%

Prognostic factors in postoperative brain metastases derive from non-small cell lung cancer：a retrospective analysis

Chen,

Sun,

Yang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…[41][42][43]. Hulsbergen et al sought to develop a predictive model for estimating 6-month survival after surgical resection of brain metastasis [44]. The current reliance on radiotherapy-based approaches for brain metastasis prediction prompted the need for an alternative approach.…”

Section: Tumormentioning

confidence: 99%

“…Using various ML algorithms, Tewarie et al examined the risk factors for leptomeningeal disease (LMD) in brain metastasis patients [40]. Hulsbergen et al developed a predictive model for estimating 6-month survival after surgical resection of brain metastasis [44]. Senders et al developed an online survival calculator and conducted a comprehensive review of ML techniques in neuro-oncological care, highlighting their broad impact in different areas of patient management [49,53].…”

Section: Current Challengesmentioning

confidence: 99%

Artificial Intelligence in Neurosurgery: A State-of-the-Art Review from Past to Future

Tangsrivimol,

Schonfeld,

Zhang

et al. 2023

Diagnostics

Self Cite

View full text Add to dashboard Cite

In recent years, there has been a significant surge in discussions surrounding artificial intelligence (AI), along with a corresponding increase in its practical applications in various facets of everyday life, including the medical industry. Notably, even in the highly specialized realm of neurosurgery, AI has been utilized for differential diagnosis, pre-operative evaluation, and improving surgical precision. Many of these applications have begun to mitigate risks of intraoperative and postoperative complications and post-operative care. This article aims to present an overview of the principal published papers on the significant themes of tumor, spine, epilepsy, and vascular issues, wherein AI has been applied to assess its potential applications within neurosurgery. The method involved identifying high-cited seminal papers using PubMed and Google Scholar, conducting a comprehensive review of various study types, and summarizing machine learning applications to enhance understanding among clinicians for future utilization. Recent studies demonstrate that machine learning (ML) holds significant potential in neuro-oncological care, spine surgery, epilepsy management, and other neurosurgical applications. ML techniques have proven effective in tumor identification, surgical outcomes prediction, seizure outcome prediction, aneurysm prediction, and more, highlighting its broad impact and potential in improving patient management and outcomes in neurosurgery. This review will encompass the current state of research, as well as predictions for the future of AI within neurosurgery.

show abstract

“…[ 11 ] In recent years, logistic regression, Cox regression, nomograms, least absolute shrinkage and selection operator (LASSO) regression, machine learning, and other methods have been widely applied. [ 12 , 13 ] The nomogram prediction model has great application value in the diagnosis, treatment selection, and assessment of prognosis in several diseases, including prostate cancer, [ 14 ] colorectal cancer, [ 15 ] and SCI. [ 16 ] It has positively affected the prediction of different diseases and conditions in clinical settings.…”

Section: Introductionmentioning

confidence: 99%

Development and validation of a prediction model for hypoproteinemia after traumatic spinal cord injury: A multicenter retrospective clinical study

Tan,

Wu,

et al. 2024

Medicine

View full text Add to dashboard Cite

A multicenter retrospective analysis of conventionally collected data. To identify the potential causes of hypoproteinemia after traumatic spinal cord injury (TSCI) and provide a diagnostic model for predicting an individual likelihood of developing hypoproteinemia. Hypoproteinemia is a complication of spinal cord injury (SCI), an independent risk factor for respiratory failure in elderly patients with SCI, and a predictor of outcomes in patients with cervical SCI. Few nomogram-based studies have used clinical indicators to predict the likelihood of hypoproteinemia following TSCI. This multicenter retrospective clinical analysis included patients with TSCI admitted to the First Affiliated Hospital of Guangxi Medical University, Wuzhou GongRen Hospital, and Dahua Yao Autonomous County People Hospital between 2016 and 2020. The data of patients from the First Affiliated Hospital of Guangxi Medical University were used as the training set, and those from the other 2 hospitals were used as the validation set. All patient histories, diagnostic procedures, and imaging findings were recorded. To predict whether patients with TSCI may develop hypoproteinemia, a least absolute shrinkage and selection operator regression analysis was conducted to create a nomogram. The model was validated by analyzing the consequences using decision curve analysis, calibration curves, the C-index, and receiver operating characteristic curves. After excluding patients with missing data, 534 patients were included in this study. Male/female sex, age ≥ 60 years, cervical SCI, pneumonia, pleural effusion, urinary tract infection (UTI), hyponatremia, fever, hypotension, and tracheostomy were identified as independent risk factors of hypoalbuminemia. A simple and easy-to-replicate clinical prediction nomogram was constructed using these factors. The area under the curve was 0.728 in the training set and 0.881 in the validation set. The predictive power of the nomogram was satisfactory. Hypoalbuminemia after TSCI may be predicted using the risk factors of male/female sex, age ≥ 60 years, cervical SCI, pneumonia, pleural effusion, UTI, hyponatremia, fever, hypotension, and tracheostomy.

show abstract

Survival Prediction After Neurosurgical Resection of Brain Metastases: A Machine Learning Approach

Cited by 5 publications

References 35 publications

Prognostic factors in postoperative brain metastases derive from non-small cell lung cancer：a retrospective analysis

Prognostic factors in postoperative brain metastases derive from non-small cell lung cancer：a retrospective analysis

Artificial Intelligence in Neurosurgery: A State-of-the-Art Review from Past to Future

Development and validation of a prediction model for hypoproteinemia after traumatic spinal cord injury: A multicenter retrospective clinical study

Contact Info

Product

Resources

About