Effects of Different Cardiorespiratory Training Program on Endurance Performance

NCT04357691 | Unknown

• 1 other identifier: Project CURATE
• Study Type: interventional
• Target: 20
• Locations: 1 country
• Sites: 1

Brief Summary

Conventional training methods are typically administered in a fixed progressive manner, which can lead to sub-optimal responses and injuries. Artificial intelligence (i.e. CURATE.AI) can be harnessed to personalise physical training strategies. Using a single participant training profile, a parabolic/quadratic response to the intervention can be generated to identify the training intensity needed to optimise training outcomes. Previous studies showed CURATE.AI could dynamically modulate drug dosing in oncology. Extending the utility of results to human performance, this study will adapt CURATE.AI with the goal of optimising endurance performance through individualised training regimes. Up to 20 participants will be recruited and randomised into two groups to undergo a calibration phase, which involves performing 3 sessions of exercise sessions per week over 2 weeks per intensity (low, moderate and high) in a crossover study design. Exercise sessions will be interspersed with a 2.4 km time trial, a VO2peak test and 2 weeks of wash out period. The utility phase will divide participants into two groups to undergo 3 exercise sessions per week, totalling to 12 exercise sessions. Either an AI-led training or a conventional training programme will be performed to compare the differences in training outcomes. Blood plasma will be obtained at selected time points in both phases to evaluate the effects of training on blood lipid profiles. Findings from this study can potentially optimise efficacy and efficiency of endurance performance through personalised training with AI.

Conditions

Healthy

Outcome Measures

Primary Outcomes (4)

• Changes in 2.4 km completion time following first cycle in phase 1

  Time taken to complete 2.4 km

  Baseline and Week 4 of phase 1 (phase 1 first cycle consist of 42 days)

• Changes in 2.4 km completion time following second cycle in phase 1

  Time taken to complete 2.4 km

  Baseline and Week 9 of phase 1 (phase 1 second cycle consist of 35 days)

• Changes in 2.4 km completion time following third cycle in phase 1

  Time taken to complete 2.4 km

  Baseline and Week 14 of phase 1 (phase 1 third cycle consist of 21 days)

• Changes in 2.4 km completion time following phase 2

  Time taken to complete 2.4 km

  Baseline and Week 6 of phase 2 (phase 2 consist of 49 days)

Secondary Outcomes (10)

• Changes in VO2peak following first cycle in phase 1

  Baseline and Week 4 of phase 1 (phase 1 first cycle consist of 42 days)

• Changes in VO2peak following second cycle in phase 1

  Baseline and Week 9 of phase 1 (phase 1 second cycle consist of 35 days)

• Changes in VO2peak following third cycle in phase 1

  Baseline and Week 14 of phase 1 (phase 1 third cycle consist of 21 days)

• Changes in VO2peak following phase 2

  Baseline and Week 6 of phase 2 (phase 2 consist of 49 days)

• Resting blood lipids panel (triglycerides, cholesterols, phospholipids, sphingolipids, inflammatory lipids, testosterone, cortisol, endocannabinoids) in phase 1

  Week 1 of phase 1 (phase 1 consist of 98 days)

Study Arms (3)

Healthy individuals (low-high-mod)

OTHER

Participants will undergo the calibration phase beginning with low intensity training, followed by high, and moderate intensity training. Each training intensity will be performed 3 days a week for 2 weeks

Behavioral: Conventional training; Behavioral: AI-led training

Healthy individuals (mod-high-low)

OTHER

Participants will undergo the calibration phase beginning with moderate intensity training, followed by high, and low intensity training. Each training intensity will be performed 3 days a week for 2 weeks

Behavioral: Conventional training; Behavioral: AI-led training

Healthy individuals (mod-low-high)

OTHER

Participants will undergo the calibration phase beginning with moderate intensity training, followed by low, and high intensity training. Each training intensity will be performed 3 days a week for 2 weeks.

Behavioral: Conventional training; Behavioral: AI-led training

Interventions

Conventional training BEHAVIORAL

Participants will perform a conventional training for 4 weeks, using low-moderate-high-low intensity progression training model

Healthy individuals (low-high-mod); Healthy individuals (mod-high-low); Healthy individuals (mod-low-high)

AI-led training BEHAVIORAL

Participants will perform an AI-led training for 4 weeks

Healthy individuals (low-high-mod); Healthy individuals (mod-high-low); Healthy individuals (mod-low-high)

Eligibility Criteria

• Age: 21 Years - 35 Years
• Sex: male
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64)

You may qualify if:

• Do not smoke or use tobacco products (including shisha)
• BMI \< 30
• Medically fit
• km run time of 10 to 14 minutes in the past 12 months

You may not qualify if:

• Individuals with a history of existing musculoskeletal injury or respiratory diseases

Sponsors & Collaborators

• Wang Yongtai Raymond: lead
• The N.1 Institute for Health (N.1): collaborator

Study Sites (1)

National University of Singapore

Singapore, Singapore

Location

Related Publications (2)

• Wang H, Lee DK, Chen KY, Chen JY, Zhang K, Silva A, Ho CM, Ho D. Mechanism-independent optimization of combinatorial nanodiamond and unmodified drug delivery using a phenotypically driven platform technology. ACS Nano. 2015 Mar 24;9(3):3332-44. doi: 10.1021/acsnano.5b00638. Epub 2015 Feb 23.

  PMID: 25689511 BACKGROUND

• Rashid MBMA, Toh TB, Hooi L, Silva A, Zhang Y, Tan PF, Teh AL, Karnani N, Jha S, Ho CM, Chng WJ, Ho D, Chow EK. Optimizing drug combinations against multiple myeloma using a quadratic phenotypic optimization platform (QPOP). Sci Transl Med. 2018 Aug 8;10(453):eaan0941. doi: 10.1126/scitranslmed.aan0941.

  PMID: 30089632 BACKGROUND

Study Officials

• Kai Wei, Jason Lee, PhD

  National University of Singapore

  PRINCIPAL INVESTIGATOR

• Dean Ho, PhD

  National University of Singapore

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Yongtai, Raymond Wang, MSc

CONTACT

+65 90472892; phswyr@nus.edu.sg

Cherh Chiet, Ivan Low, PhD

CONTACT

+65 6516 7679; ivanlow@nuhs.edu.sg

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Purpose: OTHER
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Research Associate

Study Record Dates

• First Submitted: April 7, 2020
• First Posted: April 22, 2020
• Study Start: May 25, 2020
• Primary Completion: December 31, 2022
• Study Completion: December 31, 2022
• Last Updated: May 4, 2020

Record last verified: 2020-04

Data Sharing

• IPD Sharing: Will not share

Locations

SG (1)