Optimization of a Tool for Predicting Postoperative Clinical Evolution After Lumbar Surgery (DeepSurgery)

Optimization of a Tool for Predicting Postoperative Clinical Evolution After Lumbar Surgery Multicenter Longitudinal Prospective Study on a National Cohort Clinical Evolution After Lumbar Surgery

The objective of the study is the establishment, optimization and prospective evaluation of a digital predictive platform capable of providing for each lumbar spine operated patient a clinical predictive status: Patient green (success) orange (treatment failure ), red patient (complication) in order to optimize his medical care up to 6 months.

Study Overview

• Status: Completed
• Conditions: Surgery; Spinal Fusion; Spine Degeneration; Spine Disease
• Intervention / Treatment: Diagnostic test: SuMO Patient

• Study Type: Interventional
• Enrollment (Actual): 119
• Phase: Not Applicable

Contacts and Locations

Study Locations

• France
  • Paris, France, 75005
    • Clinique Geoffroy Saint-Hilaire
  • Nouvelle Aquitaine
    • Bruges, Nouvelle Aquitaine, France, 33520
      • Polyclinique Jean Villar

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• Major patient
• Eligible for lumbar decompression surgery, instrumented or not
• Social insured
• Having given consent
• Eligible for the acts described in Protocole

Exclusion Criteria:

• Minor
• Pregnant or breastfeeding woman
• Safeguard measure or guardianship
• Arthrodesis on more than 2 levels
• Interventions linked to a traumatic or infectious context are excluded

Study Plan

How is the study designed?

Design Details

• Primary Purpose: DIAGNOSTIC
• Allocation: NA
• Interventional Model: SINGLE_GROUP
• Masking: NONE

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

EXPERIMENTAL: SuMO Patient; 92 data will be collected during the patient care episode. Among the 92 criteria, 63 are pre-operative, 29 are post-operative in order to provide an evolutionary prediction during the management of the patient. Post-operative follow-up criteria making it possible to establish the scalability or non-scalability of the quality of life after the surgical procedure. The results will be compared to the prediction proposed by the machine learning algorithm.

Diagnostic test: SuMO Patient; The current study is interventional insofar as the patient is collecting all of his socio-medical information. The analysis of the data provided by the patient makes it possible to establish a long-term prognosis for the patient but does not in itself constitute a parallel medical approach. SUMO allows the surgeon to transmit post-operative advice developed by the surgeons themselves.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Optimization of a tool for predicting the postoperative clinical course after lumbar surgery	Establishment and prospective evaluation of a predictive tool with the area under the receiver operating characteristic (AUROC) metric >= 80% Sensitivity >= 90% Specificity >= 60% in the capacity of providing for each back operated patient a clinical predictive status: green patient (success) orange (treatment failure), red patient (complication).	14 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Collection of optimized data in the patient operative long terms care	Implementation, optimization and evaluation of a digital tool for collecting patient data on the episode of care Outcome (unit) - Result expected assessment time connection means preoperatively (second/connection) - 300s time 'use and navigation (second) - 1800s number of connections made by the patient preoperatively (number) - 5 number of connections / day before operation (number) - 1 number of use (number) - 15 number of drops / connection (Ratio%) - <20% number of lost view (no connection> 20 days) (Ratio%) - <10% evaluation of average using time post-operative (second/connections) - 300 Time of use and navigation (second) - 1800 number of connections made by the patient in post -operative (number) - 5 number of connections / day after operation (number)- 1 number of uses (number) - 15 number of withdrawals (Ratio%) - <20% number of lost to follow-up (no connection> 20 days) (Ratio%) - <10% number of documents analyzed / patient (number) - 10	14 months

Collaborators and Investigators

• Sponsor: Cortexx Medical Intelligence
• Collaborators: Elsan; Ramsay Générale de Santé; Malakoff-Humanis

Publications and helpful links

General Publications

• Andre A, Peyrou B, Carpentier A, Vignaux JJ. Feasibility and Assessment of a Machine Learning-Based Predictive Model of Outcome After Lumbar Decompression Surgery. Global Spine J. 2022 Jun;12(5):894-908. doi: 10.1177/2192568220969373. Epub 2020 Nov 19.

Helpful Links

• Mobile application for collecting patient's data

Study record dates

Study Major Dates

• Study Start (ACTUAL): June 15, 2021
• Primary Completion (ACTUAL): June 30, 2022
• Study Completion (ACTUAL): December 30, 2022

Study Registration Dates

• First Submitted: November 16, 2021
• First Submitted That Met QC Criteria: December 8, 2021
• First Posted (ACTUAL): December 21, 2021

Study Record Updates

• Last Update Posted (ACTUAL): February 10, 2023
• Last Update Submitted That Met QC Criteria: February 9, 2023
• Last Verified: February 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Musculoskeletal Diseases; Bone Diseases; Spinal Diseases
• Other Study ID Numbers: DeepSurgeryMH_01

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Study Data/Documents

1. Individual Participant Data Set
   Information identifier: SUMO

Drug and device information, study documents

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