Linda Johnson
@lsjMD
Followers
232
Following
163
Statuses
246
MD and diagnostic specialist. Associate Professor at Lund University, Sweden, and consulting CSO of MEDICALgorithmics. Believes in quality diagnostics
Joined April 2017
Everyone with an interest in AI, ECGs, or cardiology should read our paper out in Nature Medicine today! The DRAI MARTINI study tested the performance of DeepRhythmAI from #MEDICALgorithmics for direct-to-physician reporting of ambulatory ECGs. The results overwhelmingly favour the AI, with 14 times fewer missed diagnoses of critical arrhytmias. Read it here: Here's the study in brief: 🏥 >200,000 days of ECGs from >14,000 patients 🩺 >50 experts provided 3-cardiologist beat-to-beat consensus panel annotations of >5,000 ECG events 🖥️ Innovative study design provides absolute rates of missed diagnoses of AF or SVT ≥30s, 3rd degree block, 3.5s asystole or >10s VT Results: 🫀Missed diagnoses in 3.2/1000 patients by DeepRhythm and 44.3/1000 patients by techs 🫀Superior sensitivity (98.6% vs 80.3%) 🫀NPV >99.9% for DeepRhythmAI. This study is the result of an awesome collaboration with true leaders in the field who not only gave their scientific expertise but also committed many hours of their own time doing beat-to-beat annotations of >5,300 ECG events, with consensus annotation on every single beat. This resulted in an impressive author list including @EmmaSvennberg @SZDiederichsen @DrJasonAndrade @WFMMD @AlexanderPBenz @EPjeff17 @PlatonovPyotr @StavrosStavrak1 @Cardiaficionado @Dominik_Linz @JuanBenezet @PhilippKrisai @SanjeevBhavnani @AlirezaOraii @ManningerMartin and many more!
8
24
101
Our annotation panel was awesome - and we were sometimes more right than @EPjeff17 !
Proud to be part of an inspiring international team led by @lsjMD Performance of #DeepRhythmAI in direct-to-physician reporting of ambulatory ECGs Link:
0
0
2
This is worth a trip to blue sky for. Martin Ugander is brilliant and his calculations are highly relevant and very interesting! They strengthen the case for our study conclusions and I’m glad to get to see the work from a different, clever angle. @PHRIresearch @lunduniversity @NatureMedicine
Welcome over to see my post on "How to report methodological superiority of a diagnostic test."
0
1
4
Equipe Madrid FTW - world record for ECG consensus panel annotations!
Buenas noticias!!!📢📢📢 Ante la temida pregunta….”¿quién revisa los holters hoy???”🧟♂️ Por fin una luz de esperanza gracias a la IA💫✨ leed nuestro artículo en @NatureMedicine 🔝🔝🔝@lsjMD
@ritmo_SEC @secardiologia @SIAC_cardio @UICARdiologia @quironsalud @Hospital_LaLuz
0
0
8
¡No habríamos podido completar este proyecto sin el equipo de Madrid!🍸 ¡@JuanBenezet, Angelo y Alvaro son superhombres en la lectura de ECG! Estoy muy contento de haber trabajado con ustedes en esto. Ahora pongámonos a trabajar para cambiar la práctica y hacer que esto beneficie a nuestros pacientes.
0
0
3
@JuanBenezet @ritmo_SEC @secardiologia @quironsalud @UICARdiologia @SIAC_cardio @Hospital_LaLuz Team Madrid for the win!!
0
0
1
RT @PHRIresearch: New study finds AI outperforms human technicians in detecting critical heart rhythm issues on ambulatory ECGs, with 98.6%…
0
2
0
RT @DrJasonAndrade: I’m happy to have been a (small) part of this project. I’m even happier to see it published. Congratulations to @ls…
0
2
0
@DrJasonAndrade Not a small part Jason! It was great to work with you and team Vancouver/Montreal. Hope to do lots more in future.
1
0
4
@siemionowkris @EurekAlert @lunduniversity With our fantastic senior scientist Jeff Healey @EPjeff17 from @PHRIresearch on pic here.
0
0
1
@InsiderTakes The patterns and morphologies are not simple… But obviously I agree, DeepRhythm is good at this. Better than humans. Simpler models that only use features or time series components are not good enough.
0
0
0
Fantastic collaboration between @lunduniversity and @PHRIresearch, along with many other institutions worldwide
0
0
0