CClinicalTrials.gg
Not yet recruitingNCT07816003Updated Sep 25, 2026

Machine Learning Prediction of Spinal Anaesthesia Block Duration

An observational study in Anesthesia, Spinal, Nerve Block and Anesthesia Recovery Period, sponsored by Specialized Medical Center (SMC). Not yet recruiting. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-09-25.

Sponsored by Specialized Medical Center (SMC) · Observational

Study type
Observational
Model
Cohort
Time perspective
Prospective
Enrollment
255
Ages
18 Years and older
Sex
All
01

Study summary

The duration of sensory and motor block after spinal anaesthesia varies widely between patients given the same dose of local anaesthetic. Much of this variability is explained by differences in lumbosacral cerebrospinal fluid volume, which cannot be measured routinely in clinical practice but is related to simple body measurements such as abdominal circumference and vertebral column length. This prospective observational study will develop and internally validate prediction models for the duration of sensory and motor block following spinal anaesthesia in adults undergoing elective surgery. Preoperative clinical and anthropometric variables will be recorded, and block regression will be assessed serially after intrathecal injection. Machine learning methods (lasso regression, ridge regression, random forest, extreme gradient boosting, and support vector regression) will be developed and compared against multivariable linear regression as the reference model. The aim is a practical tool that helps anaesthetists anticipate how long a spinal block will last in an individual patient, supporting decisions about case scheduling, supplementation, and discharge planning.

Read the detailed description

Background. Spinal anaesthesia produces block of unpredictable duration. Cerebrospinal fluid volume in the lumbosacral region is the dominant determinant of block spread and regression, and correlates inversely with abdominal circumference and directly with vertebral column length. Existing single-variable rules perform poorly, and no validated multivariable model is in routine clinical use. Objectives. The primary objective is to develop and internally validate models predicting the duration of sensory block and the duration of motor block after single-shot spinal anaesthesia. The secondary objective is to compare the predictive performance of machine learning approaches with conventional multivariable linear regression. Design. Single-centre prospective observational cohort study. No study-directed intervention is applied; anaesthetic technique, drug, and dose are determined by the attending anaesthetist according to routine practice and are recorded as candidate predictors. Assessments. Sensory block level is assessed bilaterally by pinprick with a 25-gauge needle along the mid-clavicular line, over dermatomes T4 to S1. Motor block is assessed using the modified Bromage scale (0-3). Assessments are performed at fixed intervals from intrathecal injection until complete regression of sensory and motor block. Candidate predictors. Age, sex, height, weight, body mass index, abdominal circumference, vertebral column length, ASA physical status, local anaesthetic dose and baricity, and adjuvant use. Sample size. A target of 255 participants was derived using the Riley criteria for continuous-outcome prediction models (pmsampsize), assuming 9 candidate predictors, an outcome standard deviation of 40 minutes, anticipated R-squared of 0.35, shrinkage of at least 0.90, and a multiplicative margin of error of 1.10. The four criteria yielded 183, 183, 234, and 246; the largest requirement of 246 was inflated by approximately 4 per cent for attrition. Analysis. Model development will use nested repeated 10-fold cross-validation with bootstrap optimism correction. Performance will be reported as R-squared, root mean squared error, and mean absolute error, with calibration plots. SHAP values will be used to describe predictor contributions. Reporting will follow TRIPOD+AI.

02

Conditions studied

  • Anesthesia, Spinal
  • Nerve Block
  • Anesthesia Recovery Period

Keywords

  • spinal anaesthesia
  • sensory block duration
  • motor block duration
  • abdominal circumference
  • vertebral column length
  • machine learning
  • prediction model
  • TRIPOD+AI
03

Who can participate

Ages eligible
18 Years and older
Sexes eligible
All
Accepts healthy volunteers
No
Sampling method
Non-probability sample

Study population

Consecutive adults scheduled for elective surgery under single-shot spinal anaesthesia at Specialized Medical Center, King Fahad campus, Riyadh.

Inclusion criteria

  • Adults scheduled for elective surgery under single-shot spinal anaesthesia
  • ASA physical status I to III
  • Written informed consent obtained

Exclusion criteria

Exclusion Criteria:

  • Contraindication to neuraxial anaesthesia (coagulopathy, local or systemic infection, raised intracranial pressure, patient refusal)
  • Failed or incomplete block requiring conversion to general anaesthesia
  • Repeated or top-up intrathecal injection
  • Pregnancy
  • Known spinal deformity or previous spine surgery
  • Pre-existing neurological or neuromuscular disease affecting sensory or motor assessment
  • Inability to cooperate with sensory and motor assessment
04

Study design

Observational model
Cohort
Time perspective
Prospective
Enrollment
255 participants (estimated)
Patient registry
No
05

What researchers measure

Primary outcomes

  1. Duration of sensory block

    Time from completion of intrathecal injection to regression of sensory block to the S1 dermatome, assessed bilaterally by pinprick with a 25-gauge needle along the mid-clavicular line

    Time frame: Up to 8 hours after intrathecal injection

  2. Duration of motor block

    Time from completion of intrathecal injection to return to modified Bromage score 0 (full ability to flex knee and ankle)

    Time frame: Up to 8 hours after intrathecal injection

Secondary outcomes

  1. Predictive performance of machine learning models

    R-squared, root mean squared error, mean absolute error, and calibration slope for lasso regression, ridge regression, random forest, extreme gradient boosting, and support vector regression, each compared with multivariable linear regression as the reference model

    Time frame: Through study completion, an average of 20 months

  2. Time to peak sensory block level

    Time from intrathecal injection to the highest dermatomal level of sensory block, assessed by pinprick

    Time frame: Up to 30 minutes after intrathecal injection

06

Study locations

No study locations are listed for this record.

07

References and documents

Individual participant data

Plan to share: Yes — De-identified individual participant data underlying published results, together with the data dictionary and model code, will be made available to researchers whose proposed use has been approved by an independent review committee. Requests should be directed to the principal investigator. Data will be available from 6 months to 36 months after publication of the primary results.

Supporting information: Study protocol, Sap, Icf, Analytic code

No publications or documents are linked to this record.

08

Registry details

Key details

Study ID
NCT07816003
Lead sponsor
Specialized Medical Center (SMC)
Responsible party
SalahEldin Ahmed Abdelaziz Ahmed (Anesthesia registrar, Specialized Medical Center (SMC)) — Principal investigator
First posted
Sep 11, 2026
Start date
Dec 1, 2026 (estimated)
Primary completion
Jul 1, 2028 (estimated)
Completion
Sep 1, 2028 (estimated)
Last update
Sep 25, 2026

Study contacts

Salaheldin A Abdelaziz Ahmed
Contact
saladin28.sa@gmail.com
+966508818713
Salaheldin A abdelaziz Ahmed
principal investigator · Specialized Medical Center

Oversight

Data monitoring committee
No
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Not currently enrolling

This study is not yet recruiting, as verified in Sep 2026. You cannot join it, but the record below documents what was studied.

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion