Clinical trial · Observational
Machine Learning to Predict Postoperative Pneumonia in Brain Tumor Patients
An Interpretable and Clinically Deployable Machine Learning Model for Predicting Early Postoperative Pneumonia of Brain Tumor: a Multicenter Diagnostic Study
- Source
- ClinicalTrials.gov
- Retrieved
- Sep 8, 2026
- Layer
- normalized (units and labels harmonized; values unchanged)
- Run
- ING-CLINICALTRIALS-20260908-000001
Summary
Brief summary (as posted)
Postoperative pneumonia (POP) is a common and serious complication after elective craniotomy for brain tumor resection. POP often develops within the first week after surgery and may lead to prolonged hospitalization, higher medical costs, and increased risk of severe illness. Because symptoms can be subtle in neurosurgical patients, POP may be detected late, limiting timely prevention and treatment. This study will evaluate whether a machine-learning-based clinical decision support tool can help clinicians identify patients at high risk for POP early and improve perioperative preventive care. The tool uses routinely collected clinical information to estimate an individual patient's POP risk and provides an easy-to-understand explanation of key risk drivers. Based on the predicted risk level (low, moderate, high, or very high), the system suggests standardized preventive care pathways (e.g., perioperative airway management, targeted antibiotic strategies per local practice, and nutritional support), while allowing clinicians to override recommendations at any time. Participants will be adults undergoing their first elective craniotomy for brain tumor resection at participating neurosurgical centers. The primary outcome is the occurrence of POP within 7 days after surgery, defined using CDC/NHSN criteria. Secondary outcomes include antibiotic use intensity, length of hospital stay, direct medical cost, and clinician decision confidence. Participants will be followed at postoperative days 1, 3, and 7 using electronic medical record review and phone confirmation when needed. The goal of this study is to determine whether integrating an explainable AI risk prediction tool into routine care can reduce POP and improve the quality and efficiency of perioperative management after brain tumor surgery.
Conditions
Conditions (2)
Free-text conditions as registered, with the CancerIndex entity they were reconciled to and the match type.
| Condition (as posted) | Mapped entity | Match | Confidence |
|---|---|---|---|
| Brain Tumors | Brain Neoplasm | ALIAS | 0.90 |
| Postoperative Pneumonia | — | UNRESOLVED | — |
Interventions
Interventions (0)
Data not yet available
Design
Arms and outcomes
Arms (5)
- label
- Retrospective model development cohort (CAMS/PUMC, 2022-2024)
- description
- Retrospective cohort collected at the Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College (CAMS/PUMC) between Jan 1, 2022 and Oct 31, 2024. Adult patients undergoing elective craniotomy for intracranial brain tumor resection were included. This cohort was used for model development, comparison of candidate algorithms, and internal validation; it was randomly split 8:2 into a training set (n=609) and an internal validation set (n=152). Early postoperative pneumonia (POP) was defined by CDC criteria within 7 days postoperatively. No study-mandated intervention was applied; routine perioperative care was provided.
- label
- Prospective internal validation cohort (Test P, CAMS/PUMC)
- description
- Prospective cohort enrolled at CAMS/PUMC between Nov 1, 2024 and Apr 30, 2025 (Test P; n=224). Adult patients undergoing elective craniotomy for brain tumor resection were included. This cohort prospectively validated the finalized interpretable prediction model for early POP using routinely available perioperative EMR variables. Early POP was defined per CDC criteria within 7 postoperative days. Clinical management followed standard-of-care without any study-assigned intervention.
- label
- Prospective external validation cohort (Test A, Anhui Medical Univ)
- description
- Prospective external validation cohort recruited at the First Affiliated Hospital of Anhui Medical University from Aug 1, 2024 to Apr 30, 2025 (Test A; n=329). Adult patients undergoing elective craniotomy for brain tumor resection were included. The cohort independently validated the finalized POP prediction model using routine perioperative data. Early POP was defined by CDC criteria within 7 days after surgery. No investigational intervention was administered; all care followed local standard practice.
Eligibility
Eligibility (as posted)
- Sex
- All
- Minimum age
- 18 Years
Show eligibility criteria text
Inclusion Criteria: * Age ≥ 18 years. * Undergoing elective craniotomy for intracranial brain tumor resection. * Perioperative clinical data available in the electronic medical record to derive required predictors. * Expected postoperative survival ≥ 7 days. Exclusion Criteria: * Evidence of active infection (including pneumonia) prior to surgery. * Thoracic surgery or severe chest trauma within 30 days prior to craniotomy. * Spinal tumors or extracranial peripheral nerve tumors. * Pregnancy or lactation. * Hospice care, expected survival \< 7 days, or insufficient data completeness for model calculation.
References
Publications (16)
- BACKGROUNDLundberg SM, Lee S-I. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. 2017;30
- BACKGROUNDAzodi CB, Tang J, Shiu SH. Opening the Black Box: Interpretable Machine Learning for Geneticists. Trends Genet. 2020 Jun;36(6):442-455. doi: 10.1016/j.tig.2020.03.005. Epub 2020 Apr 17. PMID 32396837
- BACKGROUNDHan J, Yao T, Gao L, Gao H, Chen Y, Wang Y, Cao Y, Liu C, Qiu F, Jia K, Huang H. Development and validation of a risk prediction model related to inflammatory and nutritional indexes for postoperative pulmonary infection after radical colorectal cancer surgery. BMJ Open. 2025 Jan 8;15(1):e087426. doi: 10.1136/bmjopen-2024-087426. PMID 39779267
- BACKGROUNDZhao C, Xiang B, Zhang J, Yang P, Liu Q, Wang S. Predicting postoperative pulmonary infection risk in patients with diabetes using machine learning. Front Physiol. 2024 Dec 4;15:1501854. doi: 10.3389/fphys.2024.1501854. eCollection 2024. PMID 39697615
- BACKGROUNDChen Y, Ma M, Qu D, Xu C. Machine learning and transformer models for prediction of postoperative pneumonia risk in patients with lower limb fractures. Sci Rep. 2025 Jul 1;15(1):22409. doi: 10.1038/s41598-025-04623-y. PMID 40595785
- BACKGROUNDChurpek MM, Carey KA, Edelson DP, Singh T, Astor BC, Gilbert ER, Winslow C, Shah N, Afshar M, Koyner JL. Internal and External Validation of a Machine Learning Risk Score for Acute Kidney Injury. JAMA Netw Open. 2020 Aug 3;3(8):e2012892. doi: 10.1001/jamanetworkopen.2020.12892. PMID 32780123
- BACKGROUNDKoyner JL, Adhikari R, Edelson DP, Churpek MM. Development of a Multicenter Ward-Based AKI Prediction Model. Clin J Am Soc Nephrol. 2016 Nov 7;11(11):1935-1943. doi: 10.2215/CJN.00280116. Epub 2016 Sep 15. PMID 27633727