Prediction of Block Height of Spinal Anesthesia

Prediction of Block Height of Spinal Anesthesia Via Machine Learning Approach

Spinal anesthesia is one of the most used techniques for surgery. Anesthesiologists usually check the block height (dermatome) of spinal anesthesia before surgery start. More than 20 factors have been postulated to alter spinal anesthetic block height. We would like to use machine learning to comprehensively consider various factors such as physiological parameters and different drug characteristics to establish a predictive model to evaluate the sensory blockade of spinal anesthesia.

Study Overview

• Status: Recruiting
• Conditions: Anesthesia; Reaction
• Intervention / Treatment: Other: Machine learning methods

Detailed Description

This is an observational study of the retrospective collection of patient data.

The investigators retrospectively collected the electronic medical record of patients receiving spinal anesthesia from July 1, 2018, to Dec 31, 2018. Anesthesia-related factors such as anesthesiologist's expertise, injection site, patient position, the dosage of local anesthetics, needle size, the direction of needle bevel, and basic demographic information of the patients were used for data analysis. Patients less than 18 years old were excluded from this study. Twenty percent of the dataset was used as a testing dataset, and the remaining were used for model training. The investigators will utilize four machine learning algorithms as XGBoost (Extreme Gradient Boosting), AdaBoost (Adaptive Boosting), Random Forest (RF), and support vector machine (SVM). Model performances were evaluated visually with a confusion matrix.

• Study Type: Observational
• Enrollment (Anticipated): 3000

Contacts and Locations

• Study Contact: Name: Hung-Wei Cheng, MD; Phone Number: 886-2-28757549; Email: hwc1127@gmail.com

Study Locations

• Taiwan
  • Taipei, Taiwan, 112
    • Recruiting
    • Department of Anesthesiology, Taipei Veterans General Hospital
    • Contact: Hung-Wei Cheng, MD; Phone Number: +886938593113; Email: hwc1127@gmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Patients receiving spinal anesthesia due to the need for surgical intervention with available electronic medical records.

Description

Inclusion Criteria:

• Patients receiving spinal anesthesia from July 1, 2018, to Dec 31, 2018, with available electronic medical records.

Exclusion Criteria:

• Age <18 years

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Spinal anesthesia; The investigators retrospectively collected the electronic medical record of patients receiving spinal anesthesia from July 1, 2018, to Dec 31, 2018. Patients less than 18 years old were excluded from this study.

Other: Machine learning methods; This is an observational study of the retrospective collection of patient data. Anesthesia-related factors such as anesthesiologist's expertise, injection site, patient position, the dosage of local anesthetics, needle size, the direction of needle bevel, and basic demographic information of the patients were used for data analysis. Patients less than 18 years old were excluded from this study. Twenty percent of the dataset was used as a testing dataset, and the remaining were used for model training. The investigators will utilize four machine learning algorithms as XGBoost (Extreme Gradient Boosting), AdaBoost (Adaptive Boosting), Random Forest (RF), and support vector machine (SVM). Model performances were evaluated visually with a confusion matrix.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensory blockade height of spinal anesthesia	The record of sensory blockade level was extracted from retrospective electronic medical records as the primary outcome. The investigators would like to use machine learning methods to consider various factors such as physiological parameters of patients, different drug characteristics, and different anesthesia providers to establish a predictive model to evaluate the sensory blockade of spinal anesthesia.	From time of starting spinal anesthesia until the time of testing blockage height, assessed up to 10 minutes

Collaborators and Investigators

• Sponsor: Taipei Veterans General Hospital, Taiwan

Publications and helpful links

General Publications

• Fanning N, Arzola C, Balki M, Carvalho JC. Lumbar dural sac dimensions determined by ultrasound helps predict sensory block extent during combined spinal-epidural analgesia for labor. Reg Anesth Pain Med. 2012 May-Jun;37(3):283-8. doi: 10.1097/AAP.0b013e31824b30d2.
• Heng Sia AT, Tan KH, Sng BL, Lim Y, Chan ESY, Siddiqui FJ. Hyperbaric versus plain bupivacaine for spinal anesthesia for cesarean delivery. Anesth Analg. 2015 Jan;120(1):132-140. doi: 10.1213/ANE.0000000000000443.
• Greene NM. Distribution of local anesthetic solutions within the subarachnoid space. Anesth Analg. 1985 Jul;64(7):715-30. No abstract available.
• Horstman DJ, Riley ET, Carvalho B. A randomized trial of maximum cephalad sensory blockade with single-shot spinal compared with combined spinal-epidural techniques for cesarean delivery. Anesth Analg. 2009 Jan;108(1):240-5. doi: 10.1213/ane.0b013e31818e0fa6.
• Kozanhan B, Bardak O, Sami Tutar M, Ozler S, Yildiz M, Solak I. The influence of Body Roundness Index on sensorial block level of spinal anaesthesia for elective caesarean section: an observational study. J Obstet Gynaecol. 2020 Aug;40(6):772-778. doi: 10.1080/01443615.2019.1647523. Epub 2019 Aug 30.
• Kuok CH, Huang CH, Tsai PS, Ko YP, Lee WS, Hsu YW, Hung FY. Preoperative measurement of maternal abdominal circumference relates the initial sensory block level of spinal anesthesia for cesarean section: An observational study. Taiwan J Obstet Gynecol. 2016 Dec;55(6):810-814. doi: 10.1016/j.tjog.2015.04.009.

Study record dates

Study Major Dates

• Study Start (ACTUAL): October 1, 2020
• Primary Completion (ANTICIPATED): July 1, 2022
• Study Completion (ANTICIPATED): July 1, 2022

Study Registration Dates

• First Submitted: August 22, 2021
• First Submitted That Met QC Criteria: August 26, 2021
• First Posted (ACTUAL): August 27, 2021

Study Record Updates

• Last Update Posted (ACTUAL): August 27, 2021
• Last Update Submitted That Met QC Criteria: August 26, 2021
• Last Verified: August 1, 2021

More Information

Terms related to this study

• Keywords: Spinal anesthesia, Machine learning, Sensory blockade
• Other Study ID Numbers: 2020-01-004CC

Plan for Individual participant data (IPD)

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

Drug and device information, study documents

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