Impact of COMORBIDities After Radical Cystectomy Using a Predictive Method With Artificial Intelligence (COMORBID-AI)

Evaluation of the Impact of COMORBIDities on Morbidity and Mortality After Radical Cystectomy for Cancer Using a Predictive Method With Artificial Intelligence

Clinician and the multidisciplinary team meeting in oncologic urology (MMO) play a key-role in the decision making. An unexplained surgeon attributable variance, probably linked to the subjective "eyeball test" effect, was identified as a strongest factor underlying non-compliance with guide line recommendations in the management of bladder cancer. So high-quality studies that identify barriers and modulators (such as comorbidities) of provider-level adoption of guidelines and how comorbidities are associated in making therapeutic choice and their impact in bladder cancer specific survival and overall survival, are crucial. To identify patients at high risk of early death, and to improve specific guideline for treatment might be decisive.

In order to assess survival, where mortality events compete, it will be more appropriate to compute a Cumulative Incidence Function (namely CIF). The investigators will compare outcomes across patient populations to obtain information to improve clinical decision-making. Such learning will be done through the use of neural networks or by applying population-based approaches, such as Genetic Algorithms (GA), Ant Colony Systems (ACS) and Particle Swarm Optimization (PSO), using as a four-stage based approach.

First, the investigators propose a "pretopology space" in order to study a dynamic phenomenon. Second, the investigators recall that the K-means approach remains one of the most used approaches for classifying a set of elements (patients / persons / others) into K (disjunctive) clusters. Third, the investigators propose a learning pretopology space for enhancing the clustering. Such an approach can be assimilated in spirit to one applied with high success on deep learning. Fourth and last, the investigators propose a reactive method that is able to include some new elements or remove some contained elements

Study Overview

• Status: Recruiting
• Conditions: Bladder Cancer; Deep Learning; Comorbidity

• Study Type: Observational
• Enrollment (Anticipated): 500

Contacts and Locations

• Study Contact: Name: fabien saint, Pr; Phone Number: 03 22 45 59 52; Email: saint-fabien@chu-amiens.fr

Study Locations

• France
  • Picardie
    • Amiens, Picardie, France, 80054
      • Recruiting
      • CHU Amiens Picardie
      • Contact: fabien saint, Pr; Phone Number: 03 22 45 59 52; Email: saint-fabien@chu-amiens.fr

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

This is a retrospective analysis of data from patients treated by radical cystectomy in our institution from 01 January 2006 to 01 January 2021. Qualitative and quantitative standard tumour data elements will be retrieved from medical files and certified General Cancer Registry. Data collection will be conducted from 9/2021 to 9/2022. Data management and analysis will be conducted from 1/2023 to 12/2024.

Description

Inclusion Criteria:

• 18 years and older
• Patient treated by radical cystectomy for bladder cancer

Exclusion Criteria:

• Computed tomography/magnetic resonance evidence of distant metastases.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
Group A; Patient with (Group A) any Grade 3 (and over) Clavien-Dindo grading complication rate (30dC and 90dC)
Group B; Patient without (Group B) any Grade 3 (and over) Clavien-Dindo grading complication rate (30dC and 90dC)

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
bladder cancer therapeutic choice as determined with this Artificial Intelligence predictive method	After retrieving associated comorbidities, any Grade 3, and over, Clavien-Dindo grading system complication rate (30dC and 90dC), information on primary treatment for bladder cancer (urothelial type and pT1 to pT4), outcome, time and cause of death, by our technician (from medical files of specific support centers), the primary objectives will be to model incorporation of comorbidities in making therapeutic choice, to improve care for patients with bladder cancer and specific guideline for treatment.	90 days

Collaborators and Investigators

• Sponsor: Centre Hospitalier Universitaire, Amiens

Study record dates

Study Major Dates

• Study Start (ACTUAL): January 10, 2021
• Primary Completion (ANTICIPATED): January 1, 2024
• Study Completion (ANTICIPATED): January 1, 2024

Study Registration Dates

• First Submitted: January 11, 2022
• First Submitted That Met QC Criteria: January 11, 2022
• First Posted (ACTUAL): January 24, 2022

Study Record Updates

• Last Update Posted (ACTUAL): February 8, 2023
• Last Update Submitted That Met QC Criteria: February 7, 2023
• Last Verified: February 1, 2023

More Information

Terms related to this study

• Keywords: Comorbidity; Bladder Cancer; Deep learning; PSO-Particle swarm optimization
• Additional Relevant MeSH Terms: Neoplasms; Urologic Neoplasms; Urogenital Neoplasms; Neoplasms by Site; Urologic Diseases; Urinary Bladder Diseases; Urinary Bladder Neoplasms
• Other Study ID Numbers: PI2021_843_0176

Plan for Individual participant data (IPD)

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

Drug and device information, study documents

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