Machine Learning for Predicting Spinal Anesthesia Duration

Comparative Evaluation of Machine Learning Algorithms for Predicting Spinal Anesthesia Termination Time

Spinal anesthesia provides significant advantages over general anesthesia in knee arthroplasty, including reduced blood loss, faster recovery, and fewer complications. However, predicting its duration is critical for patient safety and effective postoperative management. This study evaluates the usability of machine learning (ML) algorithms to predict the termination time of spinal anesthesia and the patient's readiness for mobilization. Using demographic, surgical, and anesthetic variables, ML models were trained to estimate anesthesia duration. Accurate predictions may improve intraoperative planning, optimize postoperative care, and enhance patient outcomes. Integrating ML-based predictive systems into anesthesia practice can contribute to safer, more efficient, and personalized perioperative management.

Study Overview

• Status: Recruiting
• Conditions: Spinal Anesthesia; Knee Arthroplasty, Total; Postoperative Care; Machine Learning; Spinal Anesthesia Duration; Postoperative Acute Pain
• Intervention / Treatment: Procedure: Spinal Anesthesia (bupivacaine)

Detailed Description

Abstract

Spinal anesthesia offers several advantages over general anesthesia in total knee arthroplasty, including reduced intraoperative blood loss, less postoperative pain, faster recovery, and shorter hospital stays. It also minimizes anesthesia-related complications and facilitates early mobilization, making it a preferred technique for many orthopedic procedures. However, predicting the exact duration of spinal anesthesia remains challenging and is clinically significant for ensuring patient safety, optimizing postoperative pain control, and preventing anesthesia-related complications.

Accurate estimation of anesthesia duration allows for more effective surgical planning, timely analgesia administration, and improved patient satisfaction. Unexpectedly prolonged anesthesia may increase the risk of adverse effects, whereas premature termination can result in inadequate pain management.

Machine learning (ML) technologies offer promising tools for predicting clinical outcomes in anesthesia practice by analyzing complex, multidimensional datasets. Previous research has demonstrated the potential of ML algorithms to predict perioperative events such as hypotension, blood transfusion requirements, and postoperative complications.

In this study, the usability and effectiveness of ML models in predicting the time of termination of spinal anesthesia and the patient's readiness for mobilization were investigated. By incorporating multiple clinical variables-such as patient demographics, anesthetic drug dosages, and surgical factors-our model aims to provide accurate, data-driven predictions. These predictive insights can support anesthesiologists in tailoring perioperative management, reducing complication risks, and improving overall patient outcomes. Ultimately, integrating ML-based prediction systems into anesthesia practice may enhance the safety, efficiency, and personalization of perioperative care.

• Study Type: Observational
• Enrollment (Estimated): 140

Contacts and Locations

• Study Contact: Name: Ahmet Yüksek, MD; Phone Number: +905326580351; Email: mdayuksek@hotmail.com
• Study Contact Backup: Name: Sıddık Varolgüneş, MD; Phone Number: +905319179657; Email: varolgunes1235@gmail.com

Study Locations

• Turkey (Türkiye)
  • İzmit
    • Kocaeli, İzmit, Turkey (Türkiye), 41000
      • Recruiting
      • Kocaeli City Hospital
      • Contact: Ahmet Yüksek, MD; Phone Number: +905326580351; Email: mdayuksek@hotmail.com

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

This study will include adult patients undergoing elective total knee arthroplasty (TKA) under spinal anesthesia at Kocaeli City Hospital Operating Theaters between November 2025 and March 2026.

All participants will receive spinal anesthesia using 0.5% hyperbaric bupivacaine, and intraoperative monitoring will be conducted in accordance with institutional anesthesia standards. The study population represents a homogeneous surgical group in which spinal anesthesia is routinely applied, allowing for standardized anesthesia protocols and reliable measurement of anesthesia duration.

Eligible patients will be classified as ASA Physical Status I or II and aged 18 years or older.

Description

Inclusion Criteria:

1. Patients scheduled to undergo total knee arthroplasty between November 2025 and March 2026 at the Kocaeli City Hospital Operating Theaters.
2. Patients who have provided written informed consent to participate in the study.
3. Patients whose surgery is planned under spinal anesthesia.
4. Patients for whom complete clinical data can be obtained during the study period.
5. Adults aged 18 years or older, classified as American Society of Anesthesiologist's (ASA) Physical Status I or II.

Exclusion Criteria:

1. Patients who were converted to general anesthesia during surgery or initially operated under general anesthesia.
2. Patients who required postoperative intensive care unit (ICU) admission following anesthesia.
3. Patients who developed surgical complications and for whom postoperative mobilization could not be planned.
4. Patients with cognitive impairment preventing them from completing pain assessment scales in the postoperative period.
5. Patients with neuropathic pain, multiple sclerosis, or other neuromotor disorders will be excluded from the study.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Knee Arthroplasty Group; The group of patients who will undergo knee replacement surgery under spinal anesthesia

Procedure: Spinal Anesthesia (bupivacaine); Before being placed on the operating table, the patient is positioned comfortably and prepared for the procedure. Standardized monitoring is initiated, including five-lead electrocardiography (ECG), non-invasive blood pressure (NIBP), and pulse oximetry (SpO₂). Baseline measurements of heart rate, systolic and diastolic blood pressure, mean arterial pressure (MAP), and oxygen saturation are recorded. An 18- or 20-gauge intravenous line is inserted, and an appropriate crystalloid preload is administered. After ensuring aseptic conditions, the patient is positioned in the sitting posture, and spinal puncture is performed at the L3-L4 or L4-L5 intervertebral space using a 25 Gauge Whitacre needle. Following free flow of cerebrospinal fluid, 0.5% hyperbaric bupivacaine (10-15 mg) is slowly injected. The completion of the injection is

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Predictive performance of machine learning	The primary outcome of this study is the predictive performance of machine learning (ML) algorithms in estimating the duration of spinal anesthesia (in minutes) based on preoperative and intraoperative variables. in: R² (Coefficient of Determination). Dimensionless (no unit)	From the end of intrathecal injection (T₀) to complete motor recovery (T_end), expected within 6 hours post-injection.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
spinal anesthesia termination time	It is the period of time from the moment of completion of spinal anesthesia until the complete resolution of motor blockade in the patient's lower extremities.	From the end of intrathecal injection (T₀) to complete motor recovery (T_end), expected within 6 hours post-injection.
Visual Analogue Scale	A tool used to help a person rate the intensity of certain sensations and feelings, such as pain. The visual analog scale for pain is a straight line with one end meaning no pain and the other end meaning the worst pain imaginable. A patient marks a point on the line that matches the amount of pain he or she feels. It may be used to help choose the right dose of pain medicine.	From the end of intrathecal injection (T₀) to complete motor recovery (T_end), expected within 6 hours post-injection.

Collaborators and Investigators

• Sponsor: Kocaeli City Hospital
• Investigators: Study Director: Ahmet Yüksek, MD, Kocaeli City Hospital

Publications and helpful links

General Publications

• Bellini V, Russo M, Domenichetti T, Panizzi M, Allai S, Bignami EG. Artificial Intelligence in Operating Room Management. J Med Syst. 2024 Feb 14;48(1):19. doi: 10.1007/s10916-024-02038-2.
• Cao Y, Wang Y, Liu H, Wu L. Artificial intelligence revolutionizing anesthesia management: advances and prospects in intelligent anesthesia technology. Front Med (Lausanne). 2025 Aug 6;12:1571725. doi: 10.3389/fmed.2025.1571725. eCollection 2025.
• Magdic Turkovic T, Sabo G, Babic S, Sostaric S. SPINAL ANESTHESIA IN DAY SURGERY - EARLY EXPERIENCES. Acta Clin Croat. 2022 Sep;61(Suppl 2):160-164. doi: 10.20471/acc.2022.61.s2.22.
• Boublik J, Gupta R, Bhar S, Atchabahian A. Prilocaine spinal anesthesia for ambulatory surgery: A review of the available studies. Anaesth Crit Care Pain Med. 2016 Dec;35(6):417-421. doi: 10.1016/j.accpm.2016.03.005. Epub 2016 Jun 21.
• Schubert AK, Wiesmann T, Wulf H, Dinges HC. Spinal anesthesia in ambulatory surgery. Best Pract Res Clin Anaesthesiol. 2023 Jun;37(2):109-121. doi: 10.1016/j.bpa.2023.04.002. Epub 2023 Apr 15.

Study record dates

Study Major Dates

• Study Start (Actual): October 31, 2025
• Primary Completion (Estimated): February 14, 2026
• Study Completion (Estimated): March 1, 2026

Study Registration Dates

• First Submitted: November 20, 2025
• First Submitted That Met QC Criteria: November 20, 2025
• First Posted (Estimated): December 1, 2025

Study Record Updates

• Last Update Posted (Actual): December 8, 2025
• Last Update Submitted That Met QC Criteria: December 1, 2025
• Last Verified: December 1, 2025

More Information

Terms related to this study

• Keywords: machine learning; spinal anesthesia; Acute postoperative pain; Knee arthroplasty; spinal anesthesia duration
• Additional Relevant MeSH Terms: Pain; Neurologic Manifestations; Postoperative Complications; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Signs and Symptoms; Pain, Postoperative; Organic Chemicals; Anilides; Amides; Aniline Compounds; Amines; Anesthesia and Analgesia; Anesthesia, Conduction; Anesthesia; Bupivacaine; Anesthesia, Spinal
• Other Study ID Numbers: KSH_SVG_1

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED