Model-based Systems for Professional Football Teams, Aimed at Optimizing Health and Performance (AIPROFB)

Development and Implementation of Model-based Systems for Professional Football Teams, Aimed at Optimizing Health and Performance

LIST OF PLANNED ORIGINAL PUBLICATIONS

1. T wave inversion detection with machine learning to prevent sudden death in professional football players.
2. Machine learning applied to biological parameters for control and advisory in professional football players (Machine learning applied to biological parameters for control and advisory in professional football players.)
3. Machine learning applied to sport geolocation systems for injury prevention in professional football players.

Study Overview

• Status: Active, not recruiting
• Conditions: Arrhythmias, Cardiac; Electrocardiogram
• Intervention / Treatment: Diagnostic test: Electrocardiogram

Detailed Description

1. Introduction The approach of this project arises from the concern to use intelligence systems artificial intelligence and machine learning in professional sports as assistance for the optimization of health and performance in professional soccer players. In professional sport, increasing physical, biological and physiological efforts are required and we need help tools.

In this regard, the proposal of several publications within the project has been raised:

1. Detection of T-wave inversion with machine learning to prevent sudden death in professional soccer players.

   Players undergo various pre-competitive screening tests to assess their state of health, specifically one of them is a resting 12-lead electrocardiogram. Based on the waveform findings in this complementary test, the risk of a professional athlete and the need for more complementary tests can be classified (Drezner et al., 2017). Our proposal is to reanalyze these tests and subject them to a machine learning mathematical model that is capable of detecting T wave inversions in said leads and presenting the results and recommendations in accordance with international criteria for electrocardiographic study in athletes.

2. Machine learning applied to biological parameters for control and advice in professional soccer players.

   During the season, routine analyzes are carried out to control biochemical parameters related to health and performance that fluctuate or change throughout the season: vitamin D, vitamin B12, vitamin B9, ferritin, etc. (Galan et al. ., 2012). Said data will be subjected to a machine learning procedure that can notify us of alterations in the habitual pattern of the players and that can cause alterations in performance, even generating pathologies.

3. Machine learning applied to sports geolocation systems for the prevention of injuries in professional soccer players.

The data obtained during training sessions and matches regarding physical data such as duration, distance, distance at different speeds, training density, etc. Which are provided by sports geolocation systems, are of great importance when studying the effort and performance profile of each player. Obtaining the player's performance profile standardized according to the training day, we can detect adverse situations such as: over-training or lack of physical condition. Warning and alarm systems aimed at injury prevention can be designed. (Rossi, Pappalardo, Marcello, Javier, & May, 2017).

2. Description The studies will be implemented by implementing artificial intelligence and machine learning systems on the physical, biological and physiological data collected during the routine sports and health activity of the professional football players in the 2019-20 and 2020-21, 2021-22, 2022-23 y 2023-24 seasons.

2.1 General Objectives

• Evaluate the installation of artificial intelligence systems such as automatic learning to obtain models and results in the interpretation of physical, biomedical and physiological parameters of the players.

• Develop advisory/advertising systems in the area of health and performance based on profiles.

  3. Practical application The project has great potential for practical applicability and could generate a paradigm shift, since it is based on the generation of mathematical and/or programming models that will help in health controls and sports load controls that are applied to professional soccer players. A notable aspect is the possible improvement in the calculation of the probabilistic weights of the risk factors on health and performance.

• Study Type: Observational
• Enrollment (Actual): 54

Contacts and Locations

Study Locations

• Spain
  • Palma De Mallorca, Spain, 07011
    • RCD Mallorca SAD

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Pro Football Players

Description

Inclusion Criteria

• Healthy young and professional players of legal age who play their role in professional football teams.

Exclusion criteria:

• Players who are not a regular part of these professional teams.
• Players with known pathology.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Waves Detection	Detection waves changes in the electrocardiogram from pro football players	2023-2024

Collaborators and Investigators

• Sponsor: RCD Mallorca SAD
• Investigators: Principal Investigator: Adolfo Munoz Macho, Dr., RCD Mallorca SAD

Publications and helpful links

Helpful Links

• Repository to view the dataset

Study record dates

Study Major Dates

• Study Start (Actual): July 1, 2019
• Primary Completion (Estimated): December 17, 2023
• Study Completion (Estimated): July 30, 2024

Study Registration Dates

• First Submitted: May 2, 2023
• First Submitted That Met QC Criteria: May 15, 2023
• First Posted (Actual): May 24, 2023

Study Record Updates

• Last Update Posted (Estimated): November 17, 2023
• Last Update Submitted That Met QC Criteria: November 14, 2023
• Last Verified: May 1, 2023

More Information

Terms related to this study

• Keywords: Performance; Artificial Intelligence; Pro Football Players; Sudden Death Prevention
• Additional Relevant MeSH Terms: Pathologic Processes; Heart Diseases; Cardiovascular Diseases; Arrhythmias, Cardiac
• Other Study ID Numbers: 1573N19

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: The plan is to generate an anonymous ECG, blood data and GPS Data from football players and share the dataset in XML or CSV format
• IPD Sharing Time Frame: The information will be available from June 2023 onwards
• IPD Sharing Access Criteria: Information that is public and available on request to researchers with an interest in physiological datasets
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF; ANALYTIC_CODE; CSR

Study Data/Documents

1. Individual Participant Data Set

Drug and device information, study documents

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