Demo mode
The app can be explored with sample data, without your own ECGs – a quick way to see the report and the trend yourself.
App Store →
For healthcare professionals
What your patients bring to their check-up
QTc Tracker is a self-monitoring diary for people taking QT-prolonging medication – above all citalopram and escitalopram. The app analyses the single-lead ECGs in Apple Health and summarises the QTc trend in a report that patients bring to their appointment.
- Single-lead ECG · 512 Hz
- Tangent method
- QTcF · QTcB · Framingham · Hodges
- Not a medical device
At a glance
The key facts
- Data source
- Single-lead ECGs from Apple Health, e.g. from an Apple Watch (Series 4 or later): 30 seconds, 512 Hz, similar to lead I.
- Measurement
- Signal-averaged beat built from the clean individual beats; QRS onset where the signal leaves the isoelectric line, T end by the tangent method.
- Correction
- QTcF (default), QTcB, Framingham and Hodges are calculated side by side; RR is the median RR interval of the recording.
- Classification
- Men 450 / 470 / 500 ms, women 460 / 480 / 500 ms. Additional flags for a rise of 30 ms and 60 ms over baseline.
- Baseline
- Mean of all usable measurements before the recorded start of therapy.
- Data protection
- All analysis runs on the iPhone only. No server, no account – patients share the report themselves.
Methodology
How a QTc value is produced
The analysis is deliberately transparent: every measurement shows the averaged beat with the measuring points that were set.
- 1
Pre-processing
Removal of baseline wander and light low-pass smoothing.
- 2
R-peak detection
Pan-Tompkins principle: derivative, squaring, moving-window integration and an adaptive threshold.
- 3
Selective averaging
Each beat is correlated with a median template. The cleanest ~80% (r ≥ 0.8) form the averaged beat – ectopic beats and artefacts drop out.
- 4
QRS onset
From the steepest QRS slope back to the stable isoelectric PR segment.
- 5
T end
Tangent at the steepest point of the descending T-wave limb; its intersection with the isoelectric line is the T end (tangent method).
- 6
Quality control
QT dispersion across individual beats (standard deviation). Recordings with a heart rate above 120 bpm or an implausible QT are flagged and excluded from trend, baseline and risk statistics.
Interactive
Try the measuring points
The averaged beat with QRS onset and T end appears in every report – here interactively, including the tangent method.
QT interval
From QRS onset to T end: the complete electrical work of the ventricles. Typical values are about 350 to 450 ms.
Report
What the PDF report contains
The report is created on the iPhone and passed on by the patient – by email, messenger or as a printout.
- Summary: median QTc with range, latest measurement, baseline, therapy period and share within the normal range
- Mean values before, during and after therapy
- QTc trend with risk zones and therapy markers, plus resting heart rate and HRV trends from Apple Health
- Averaged beat of every measurement with marked QRS onset and T end – for visual review
- Measurement table with date, heart rate, QT, QTcF, QTcB and classification
- Medications with dose and logged intakes (from Apple Health on iOS 26 or later)
- A4 in 31 languages or as an English US clinical report in Letter format
Page 1 of 3 · Tap to turn the page
Sample with made-up dataLimitations
What the app does not do
Not a medical device
The app is for self-monitoring. It does not diagnose and does not replace ECG monitoring as required by the prescribing information.
Not clinically validated
The automatic measurement has not yet been systematically validated against the 12-lead ECG. We are looking for partners to do so (see below).
A single lead
In a 12-lead ECG, QT is usually measured in the lead with the longest QT. Values from a single lead may differ, typically being shorter.
Difficult T waves
Flat, biphasic or U-wave-overlapped T waves make T-end detection harder. That is why every averaged beat is shown for review.
Rhythm and rate
In atrial fibrillation, bundle branch block or paced rhythm, QTc values are of limited value. Rate correction is meaningful between about 45 and 120 bpm.
| Classification | Men | Women |
|---|---|---|
| Normal | < 450 ms | < 460 ms |
| Borderline | 450–469 ms | 460–479 ms |
| Prolonged | 470–499 ms | 480–499 ms |
| Markedly prolonged | ≥ 500 ms | ≥ 500 ms |
In addition, a rise of more than 60 ms over baseline is considered a warning sign. Limits according to AHA/ACCF/HRS (2009) and Drew et al. (2010).
For your practice
Try it, pass it on, help validate it
Printable fact sheet
One page with methodology, report contents and limitations – for your waiting room or for colleagues.
PDF ↓Validation
We are looking for clinics and practices to accompany a comparison against the 12-lead ECG – for example as part of a doctoral thesis.
Get in touch →Collaboration and validation
Would you like to present the app in your clinic or practice, give feedback on the methodology or accompany a validation study? Please write to us.
References
Background and sources
Thresholds, correction formulas and measurement method are based on these publications:
- Rautaharju PM, Surawicz B, Gettes LS, et al. AHA/ACCF/HRS Recommendations for the Standardization and Interpretation of the Electrocardiogram: Part IV: The ST Segment, T and U Waves, and the QT Interval. Circulation. 2009;119:e241–e250.
- Drew BJ, Ackerman MJ, Funk M, et al. Prevention of Torsade de Pointes in Hospital Settings: A Scientific Statement From the American Heart Association and the American College of Cardiology Foundation. Circulation. 2010;121:1047–1060.
- ICH E14: The Clinical Evaluation of QT/QTc Interval Prolongation and Proarrhythmic Potential for Non-Antiarrhythmic Drugs. International Council for Harmonisation, 2005.
- Postema PG, De Jong JS, Van der Bilt IA, Wilde AA. Accurate electrocardiographic assessment of the QT interval: teach the tangent. Heart Rhythm. 2008;5:1015–1018.
- Strik M, Caillol T, Ramirez FD, et al. Validating QT-Interval Measurement Using the Apple Watch ECG to Enable Remote Monitoring During the COVID-19 Pandemic. Circulation. 2020;142:416–418.
- Pan J, Tompkins WJ. A Real-Time QRS Detection Algorithm. IEEE Trans Biomed Eng. 1985;32:230–236.
- Fridericia LS. Die Systolendauer im Elektrokardiogramm bei normalen Menschen und bei Herzkranken. Acta Med Scand. 1920;53:469–486.
- Bazett HC. An analysis of the time-relations of electrocardiograms. Heart. 1920;7:353–370.
- Sagie A, Larson MG, Goldberg RJ, Bengtson JR, Levy D. An improved method for adjusting the QT interval for heart rate (the Framingham Heart Study). Am J Cardiol. 1992;70:797–801.
- Hodges M, Salerno D, Erlien D. Bazett's QT correction reviewed: evidence that a linear QT correction for heart rate is better. J Am Coll Cardiol. 1983;1:694.
- U.S. Food and Drug Administration. Drug Safety Communication: Revised recommendations for Celexa (citalopram hydrobromide) related to a potential risk of abnormal heart rhythms with high doses. 2011, updated 2012.
FAQ
Questions from practice
Is QTc Tracker a medical device?
No. The app is a self-monitoring diary. It does not diagnose, gives no treatment recommendations and does not replace ECG monitoring as required by the prescribing information. Abnormal values should be checked with a 12-lead ECG as usual.
How reliable is a QT measurement from an Apple Watch?
With manual measurement, studies show good agreement between Apple Watch QT intervals and the 12-lead ECG (e.g. Strik et al., Circulation 2020). This app's automatic measurement is not clinically validated; that is why the averaged beat with its measuring points is shown in the report for visual review.
Which correction formula is used?
The default is Fridericia (QTcF), which is also preferred by the ICH E14 guideline. Bazett, Framingham and Hodges are calculated in parallel; the report shows QTcF and QTcB side by side.
How does the report reach me?
The patient creates the PDF in the app and shares it themselves – by email, messenger or as a printout. The developer runs no server and receives no health data.
Which patients benefit?
Above all people starting citalopram, escitalopram or other QT-prolonging drugs, or changing their dose, who already wear an Apple Watch with the ECG feature. A baseline recording before the start of therapy is ideal.