Machine Learning to Predict Postoperative Pneumonia in Brain Tumor Patients

NCT07321262 | Completed DMC

• 2 other identifiers: NCC2025C-14262024-I2M-3-014
• Study Type: observational
• Target: 1,856
• Locations: 1 country
• Sites: 1

Brief Summary

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

Postoperative Pneumonia; Brain Tumors

Keywords

postoperative pneumonia; brain tumor surgery; perioperative management; machine learning; explainable artificial intelligence; SHAP; clinical decision support system

Outcome Measures

Primary Outcomes (1)

• Incidence of early postoperative pneumonia (POP)

  Early POP was diagnosed according to CDC criteria and recorded in the electronic medical record, assessed as a binary outcome (POP vs no POP) within 7 postoperative days.

  Within 7 days after craniotomy (postoperative day 0-7)

Secondary Outcomes (4)

• Discrimination of the finalized prediction model (AUC)

  Within 7 days after craniotomy (postoperative day 0-7)

• Calibration performance of the finalized prediction model

  Within 7 days after craniotomy (postoperative day 0-7)

• Clinical utility of the finalized prediction model (Decision Curve Analysis)

  Within 7 days after craniotomy (postoperative day 0-7)

• Classification performance of the finalized prediction model at a pre-specified cutoff

  Within 7 days after craniotomy (postoperative day 0-7)

Study Arms (5)

Retrospective model development cohort (CAMS/PUMC, 2022-2024)

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.

Prospective internal validation cohort (Test P, CAMS/PUMC)

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.

Prospective external validation cohort (Test A, Anhui Medical Univ)

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.

Prospective external validation cohort (Test S, Shandong Cancer Hospital)

Prospective external validation cohort recruited at Shandong Cancer Hospital from Aug 1, 2024 to Apr 30, 2025 (Test S; n=440). Adult patients undergoing elective craniotomy for intracranial brain tumor resection were included. This cohort was used to externally validate the finalized interpretable model for early POP prediction using routinely collected perioperative variables. Early POP was defined according to CDC criteria within 7 postoperative days. Participants received routine perioperative management per institutional standards without study-mandated interventions.

Prospective external validation cohort (Test J, Jinan Fourth People's Hospital)

Prospective external validation cohort recruited at Jinan Fourth People's Hospital from Aug 1, 2024 to Apr 30, 2025 (Test J; n=102). Adult patients undergoing elective craniotomy for brain tumor resection were included. The cohort externally validated the finalized prediction model for early POP based on routine perioperative EMR data. Early POP was defined per CDC criteria within 7 postoperative days. There was no study-assigned intervention; all patients received standard perioperative care per local protocols.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adult patients undergoing elective craniotomy for intracranial brain tumor resection at participating centers. The study includes a retrospective model-development cohort and multiple prospective validation cohorts. Routinely collected perioperative electronic medical record data are used to develop and validate an interpretable prediction model for early postoperative pneumonia (within 7 postoperative days).

You may qualify if:

• 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.

You may not qualify if:

• 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.

Sponsors & Collaborators

• Ming Yang: lead
• The First Affiliated Hospital of Anhui Medical University: collaborator
• Shandong Cancer Hospital and Institute: collaborator

Study Sites (1)

National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College

Beijing, Beijing Municipality, 100021, China

Location

Related Publications (16)

• Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. 2017;30

  BACKGROUND

• Azodi 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 BACKGROUND

• Han 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 BACKGROUND

• Zhao 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 BACKGROUND

• Chen 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 BACKGROUND

• Churpek 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 BACKGROUND

• Koyner 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 BACKGROUND

• Canet J, Gallart L, Gomar C, Paluzie G, Valles J, Castillo J, Sabate S, Mazo V, Briones Z, Sanchis J; ARISCAT Group. Prediction of postoperative pulmonary complications in a population-based surgical cohort. Anesthesiology. 2010 Dec;113(6):1338-50. doi: 10.1097/ALN.0b013e3181fc6e0a.

  PMID: 21045639 BACKGROUND

• Lan J, Wei Y, Zhu Y, Zhang Y, Zhang S, Mo L, Wei D, Lei Y. Risk Factors for Post-Operative Pulmonary Infection in Patients With Brain Tumors: A Systematic Review and Meta-Analysis. Surg Infect (Larchmt). 2023 Sep;24(7):588-597. doi: 10.1089/sur.2023.130. Epub 2023 Aug 10.

  PMID: 37582199 BACKGROUND

• Jing X, Wang X, Zhuang H, Fang X, Xu H. Multiple Machine Learning Approaches Based on Postoperative Prediction of Pulmonary Complications in Patients With Emergency Cerebral Hemorrhage Surgery. Front Surg. 2022 Jan 18;8:797872. doi: 10.3389/fsurg.2021.797872. eCollection 2021.

  PMID: 35127804 BACKGROUND

• Sughrue ME, Rutkowski MJ, Shangari G, Chang HQ, Parsa AT, Berger MS, McDermott MW. Risk factors for the development of serious medical complications after resection of meningiomas. Clinical article. J Neurosurg. 2011 Mar;114(3):697-704. doi: 10.3171/2010.6.JNS091974. Epub 2010 Jul 23.

  PMID: 20653395 BACKGROUND

• Longo M, Agarwal V. Postoperative Pulmonary Complications Following Brain Tumor Resection: A National Database Analysis. World Neurosurg. 2019 Jun;126:e1147-e1154. doi: 10.1016/j.wneu.2019.03.058. Epub 2019 Mar 15.

  PMID: 30880210 BACKGROUND

• Gonzalez-Bonet LG, Tarazona-Santabalbina FJ, Lizan Tudela L. [Neurosurgery in the elderly patient: Geriatric neurosurgery]. Neurocirugia (Astur). 2016 Jul-Aug;27(4):155-66. doi: 10.1016/j.neucir.2015.11.003. Epub 2016 Jan 4. Spanish.

  PMID: 26762658 BACKGROUND

• Karhade AV, Cote DJ, Larsen AM, Smith TR. Neurosurgical Infection Rates and Risk Factors: A National Surgical Quality Improvement Program Analysis of 132,000 Patients, 2006-2014. World Neurosurg. 2017 Jan;97:205-212. doi: 10.1016/j.wneu.2016.09.056. Epub 2016 Sep 23.

  PMID: 27671880 BACKGROUND

• Horan TC, Andrus M, Dudeck MA. CDC/NHSN surveillance definition of health care-associated infection and criteria for specific types of infections in the acute care setting. Am J Infect Control. 2008 Jun;36(5):309-32. doi: 10.1016/j.ajic.2008.03.002. No abstract available.

  PMID: 18538699 BACKGROUND

• Lan J, Liu X, Mo L, Wei D, Zhang S, Zhang Y, Zhu Y, Lei Y. Construction and validation of a risk prediction model for postoperative pulmonary infection in patients with brain tumor: a retrospective study. PeerJ. 2025 Mar 31;13:e18996. doi: 10.7717/peerj.18996. eCollection 2025.

  PMID: 40183067 BACKGROUND

MeSH Terms

Conditions

Brain Neoplasms

Condition Hierarchy (Ancestors)

Central Nervous System Neoplasms; Nervous System Neoplasms; Neoplasms by Site; Neoplasms; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: OTHER
• Target Duration: 7 Days
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Clinical Professor

Study Record Dates

• First Submitted: December 22, 2025
• First Posted: January 7, 2026
• Study Start: August 1, 2024
• Primary Completion: April 1, 2025
• Study Completion: September 1, 2025
• Last Updated: January 8, 2026

Record last verified: 2026-01

Locations

CN (1)