# myTrainingForecast

> Science-based running injury prevention web app that estimates your 7-day risk of overuse injury after every run, using Acute:Chronic Ratio (ACR) methodology and a multivariate Cox proportional hazards regression model. Used by 24,000+ runners worldwide. Integrates with Strava.

myTrainingForecast (myTF) helps runners avoid doing too much too soon, the leading cause of overuse injuries such as runner's knee, shin splints, stress fractures, plantar fasciitis, ITBS, and Achilles tendonitis. After each activity, myTF analyses training load across multiple dimensions and notifies the runner if their injury risk has changed.

The app includes a multi-week planner where runners schedule future runs and immediately see how each session affects their predicted injury risk and ACR zones. Runners aim to keep their training consistently in the green zone (ACR 80-130%) for the safest progression.

myTF is built and operated by Scitracs Ltd (London, UK). It is independent, ad-free, and funded entirely by Premium subscriptions. No data is sold to third parties.

## Core pages

- [Home](https://mytrainingforecast.run/): Overview, sign-up, pricing, and testimonials
- [Help and FAQ](https://mytrainingforecast.run/help): How injury risk is calculated, ACR zones explained, the science behind myTF, injury prevention guides (shin splints, runner's knee, overtraining, returning from injury), account management
- [Privacy policy](https://mytrainingforecast.run/privacy): Data collection, Strava integration, GDPR compliance
- [Cookie policy](https://mytrainingforecast.run/cookie-policy): Cookie usage details
- [Contact](https://mytrainingforecast.run/contact): Get in touch
- [Full documentation](https://mytrainingforecast.run/llms-full.txt): Complete content for all key pages in a single file

## Blog

- [Blog home](https://mytrainingforecast.run/blog/): Running injury prevention articles grounded in sports science
- [Why extended rest days can increase injury risk for runners](https://mytrainingforecast.run/blog/why-extended-rest-can-increase-injury-risk-for-runners/): The counterintuitive relationship between training breaks and tissue vulnerability, explaining why the detraining zone predicts future injury
- [Introducing myTrainingForecast: a science-based injury prevention web app](https://mytrainingforecast.run/blog/intro/): Origin story and how ACR-based injury prediction works

## How it works

Runners connect their Strava account. myTF imports their activity history, calculates training load metrics, and generates a personalised injury risk forecast. The core methodology is the Acute:Chronic Workload Ratio (Blanch & Gabbett, 2015), where the acute (7-day) training load is compared against the chronic (28-day average) training load.

The Premium model extends this with a multivariate Cox proportional hazards regression incorporating multiple ACR dimensions (distance, longest run, elevation gain) and individual risk factors (age, sex, running experience, injury history, baseline mileage).

Five ACR zones guide training decisions: purple (<50%, severe detraining), blue (50-80%, detraining risk), green (80-130%, lowest injury risk), orange (130-150%, elevated risk), red (>150%, high injury risk).

## Features

### Free tier
- Basic ACR-based injury risk model
- 1-week run planner
- 1-month history charts
- Email alerts when risk changes

### Premium tier
- Personalised multivariate injury risk model (Cox proportional hazards regression)
- 12-week planner for runs, rides, and swims
- 5-year history charts
- Multi-sport training health tracking (running, cycling, swimming)
- Charts for running risk, cumulative overload, distance, elevation gain, longest run, cadence, weekly run frequency, with ACR zone overlays
- Personalised risk and ACR email alerts
- Air quality near you
- 7-day free trial included

## Integrations

- Strava (OAuth, activity sync, webhook events, description enrichment)
- Stripe (Premium subscription payments, Apple Pay supported)

## Key scientific references

- Blanch, P. & Gabbett, T.J. (2015). Has the athlete trained enough to return to play safely? The acute:chronic workload ratio permits clinicians to quantify a player's risk of subsequent injury.
- Gabbett, T.J. (2016). The training-injury prevention paradox: should athletes be training smarter and harder?
- Buist, I. et al. (2008). No effect of a graded training program on the number of running-related injuries: a randomized controlled trial (challenges the 10% rule).
- Smith, B.E. et al. (2018). Incidence and prevalence of patellofemoral pain: A systematic review and meta-analysis. PLoS ONE 13(1): e0190892.
- Bhusari, N. & Deshmukh, M. (2023). Shin Splint: A Review. Cureus 15(1): e33905.
- Deshmukh, N.S. & Phansopkar, P. (2022). Medial Tibial Stress Syndrome: A Review Article. Cureus 14(7): e26641.
- Kakouris, N. et al. (2021). A systematic review of running-related musculoskeletal injuries. Journal of Sport and Health Science.
- Taberner, M. et al. (2019). Interchangeability of position tracking technologies; can we merge the data? Science and Medicine in Football.

## Optional

- [Strava club](https://www.strava.com/clubs/myTrainingForecast)
- [Instagram](https://www.instagram.com/mytrainingforecast)
- [Facebook](https://www.facebook.com/myTrainingForecast.run)
- [X / Twitter](https://x.com/myTF_run)