Clinical Data-Driven AI Model for Mortality Prediction After Hip Fracture

Development of an AI Model Based on Clinical Data to Predict 30-Day and 1-Year Mortality Rates After Hip Fracture Surgery: A Retrospective Cohort Study

Hip fractures are a major cause of morbidity and mortality, particularly in elderly patients. Accurate prediction of postoperative mortality is critical for risk stratification and clinical decision-making. Traditional scoring systems, such as the Nottingham Hip Fracture Score, have limitations in capturing complex, non-linear relationships among clinical variables.

This retrospective cohort study aims to develop and validate an artificial intelligence-based model to predict 30-day mortality in patients undergoing hip fracture surgery. Clinical and laboratory data of approximately 1000 patients operated between January 1, 2022 and December 1, 2025 will be extracted from electronic health records. Variables include demographic characteristics, comorbidities, laboratory parameters, perioperative data, and postoperative complications.

The performance of the artificial intelligence model will be evaluated and compared with conventional risk scoring systems. The study seeks to determine whether AI-based approaches can provide improved predictive accuracy for postoperative mortality in hip fracture patients.

Study Overview

• Status: Completed
• Conditions: Hip Fracture , Postoperative Mortality

• Study Type: Observational
• Enrollment (Actual): 1000

Contacts and Locations

Study Locations

• Turkey (Türkiye)
  • Ankara, Turkey (Türkiye), 06200
    • Dr. Abdurrahman Yurtaslan Ankara Oncology Training And Research Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

This study population consists of adult patients who underwent surgical treatment for hip fractures at a tertiary care oncology training and research hospital between January 1, 2022 and December 1, 2025. The cohort is derived retrospectively from electronic health records and includes approximately 1000 patients.

The population includes individuals with varying demographic characteristics, comorbidities, and perioperative risk profiles. Clinical data encompass demographic information, baseline functional and cognitive status, comorbid conditions, laboratory parameters, intraoperative variables, and postoperative complications.

Patients with malignancy and those undergoing revision surgery are excluded. The study population represents a real-world clinical cohort used to develop and validate an artificial intelligence-based model for predicting 30-day postoperative mortality following hip fracture surgery.

Description

Inclusion Criteria:

Patients who underwent surgical treatment for hip fracture between January 1, 2022 and December 1, 2025 Age ≥18 years Availability of complete demographic, clinical, and laboratory data in the electronic health record system Documented 30-day follow-up or mortality status

Exclusion Criteria:

Patients with malignancy Patients undergoing revision hip surgery Patients with missing or incomplete key clinical or laboratory data required for analysis Patients with unavailable or undocumented 30-day mortality status

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
30-Day Postoperative Mortality	All-cause mortality occurring within 30 days following hip fracture surgery, determined from hospital records and electronic health data.	30 days after surgery and 1 year later

Collaborators and Investigators

• Sponsor: Dr Abdurrahman Yurtaslan Ankara Oncology Training and Research Hospital

Publications and helpful links

General Publications

• Ju M, Lee S, Marvich HM, Lin S. Accessing Alkoxy Radicals via Frustrated Radical Pairs: Diverse Oxidative Functionalizations of Tertiary Alcohols. J Am Chem Soc. 2024 Jul 24;146(29):19696-19703. doi: 10.1021/jacs.4c07125. Epub 2024 Jul 16.
• Wanchaijiraboon P, Sainamthip P, Teeyapun N, Luangdilok S, Poovorawan Y, Wanlapakorn N, Tanasanvimon S, Sriuranpong V, Susiriwatananont T, Zungsontiporn N, Pakvisal N. Safety Following COVID-19 Booster Vaccine with BNT162b2 Compared to mRNA-1273 in Solid Cancer Patients Previously Vaccinated with ChAdOx1 or CoronaVac. Vaccines (Basel). 2023 Feb 3;11(2):356. doi: 10.3390/vaccines11020356.
• Gonzalez Martinez J, Chen JJ, Aung T, Constantine T, Gonzalez-Martinez JA. Comparative Feasibility and Complication Analyses of Extraoperative (Bedside) Removal of Stereo-Electroencephalography Electrodes. Stereotact Funct Neurosurg. 2025;103(5):302-311. doi: 10.1159/000545984. Epub 2025 Apr 23.

Study record dates

Study Major Dates

• Study Start (Actual): December 1, 2025
• Primary Completion (Actual): March 10, 2026
• Study Completion (Actual): March 20, 2026

Study Registration Dates

• First Submitted: March 21, 2026
• First Submitted That Met QC Criteria: March 21, 2026
• First Posted (Actual): March 27, 2026

Study Record Updates

• Last Update Posted (Actual): March 27, 2026
• Last Update Submitted That Met QC Criteria: March 21, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Wounds and Injuries; Leg Injuries; Fractures, Bone; Femoral Fractures; Hip Injuries; Hip Fractures
• Other Study ID Numbers: 2025-12/209

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data will not be shared due to the retrospective nature of the study and the inclusion of sensitive patient information obtained from electronic health records. All data will be analyzed in an anonymized form, and data sharing is restricted in accordance with institutional policies and ethical regulations

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No