Artificial Intelligence for Automated Clinical Data Exploration From Electronic Medical Records (CardioMining-AI)

NCT05176769 | Recruiting

• 1 other identifier: 545/19.11.2021
• Study Type: observational
• Target: 60,000
• Locations: 1 country
• Sites: 9

Brief Summary

The purpose of this study is to highlight the usefulness of artificial intelligence and machine learning to develop computer algorithms that will achieve with great reliability, speed and accuracy the automatic extraction and processing of large volumes of raw and unstructured clinical data from electronic medical files.

Conditions

Artificial Intelligence; Machine Learning; Electronic Medical Records

Keywords

artificial intelligence; machine learning; medical records; digital health

Outcome Measures

Primary Outcomes (1)

• Accuracy of artificial intelligence to automatically extract clinical data from patients' medical records compared with traditional manual data extraction methods

  Rate of accurate extraction of clinical data (medical history, discharge diagnoses, medication, etc.) from unstructured clinical notes using automated artificial intelligence methods compared with traditional methods of manual data extraction

  1 year

Secondary Outcomes (5)

• Time to all-cause mortality

  up to 8 years (from hospital discharge until study primary completion date)

• Time to incident major cardiovascular diseases

  up to 8 years (from hospital discharge until study primary completion date)

• Time to rehospitalization for cardiovascular reasons

  up to 8 years (from hospital discharge until study primary completion date)

• Time to stroke or systemic embolism

  up to 8 years (from hospital discharge until study primary completion date)

• Time to acute coronary syndrome

  up to 8 years (from hospital discharge until study primary completion date)

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

All patients who were hospitalized in the Cardiology ward of tertiary hospitals and have available electronically-stored clinical notes/hospitalization documents will be included in the study .

You may qualify if:

• Hospitalised patients in Cardiology Departments in Greece
• Patients whose medical records are electronically stored in each hospital's computer/information systems

You may not qualify if:

• Patients that died during hospitalization, and thus no discharge letter was issued

Sponsors & Collaborators

• AHEPA University Hospital: lead
• Hippokration Hospital Athens: collaborator
• General Hospital of Larissa: collaborator
• University Hospital, Alexandroupolis: collaborator
• University General Hospital of Patras: collaborator
• University General Hospital of Heraklion: collaborator
• George Papanicolaou Hospital: collaborator
• Ippokrateio General Hospital of Thessaloniki: collaborator

Study Sites (9)

University Cardiology Clinic, Democritus University of Thrace

Alexandroupoli, Greece

NOT YET RECRUITING

1st Department of Cardiology, Hippokration General Hospital

Athens, Greece

RECRUITING

Department of Cardiology, Heraklion University Hospital

Heraklion, Greece

NOT YET RECRUITING

University General Hospital of Larissa, University of Thessaly

Larissa, Greece

RECRUITING

Department of Cardiology, University of Patras Medical School

Pátrai, Greece

RECRUITING

1st Cardiology Department, AHEPA University Hospital

Thessaloniki, 54636, Greece

RECRUITING

3rd Cardiology Department, Hippokration Hospital

Thessaloniki, Greece

NOT YET RECRUITING

Cardiology Department, George Papanikolaou General Hospital

Thessaloniki, Greece

RECRUITING

Laboratory of Medical Physics, Aristotle University of Thessaloniki

Thessaloniki, Greece

RECRUITING

Related Publications (7)

• Johnson KW, Torres Soto J, Glicksberg BS, Shameer K, Miotto R, Ali M, Ashley E, Dudley JT. Artificial Intelligence in Cardiology. J Am Coll Cardiol. 2018 Jun 12;71(23):2668-2679. doi: 10.1016/j.jacc.2018.03.521.

  PMID: 29880128 BACKGROUND

• Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T. Artificial Intelligence in Precision Cardiovascular Medicine. J Am Coll Cardiol. 2017 May 30;69(21):2657-2664. doi: 10.1016/j.jacc.2017.03.571.

  PMID: 28545640 BACKGROUND

• Madani A, Arnaout R, Mofrad M, Arnaout R. Fast and accurate view classification of echocardiograms using deep learning. NPJ Digit Med. 2018;1:6. doi: 10.1038/s41746-017-0013-1. Epub 2018 Mar 21.

  PMID: 30828647 BACKGROUND

• Boag W, Doss D, Naumann T, Szolovits P. What's in a Note? Unpacking Predictive Value in Clinical Note Representations. AMIA Jt Summits Transl Sci Proc. 2018 May 18;2017:26-34. eCollection 2018.

  PMID: 29888035 BACKGROUND

• Hashir M, Sawhney R. Towards unstructured mortality prediction with free-text clinical notes. J Biomed Inform. 2020 Aug;108:103489. doi: 10.1016/j.jbi.2020.103489. Epub 2020 Jun 25.

  PMID: 32592755 BACKGROUND

• Diller GP, Kempny A, Babu-Narayan SV, Henrichs M, Brida M, Uebing A, Lammers AE, Baumgartner H, Li W, Wort SJ, Dimopoulos K, Gatzoulis MA. Machine learning algorithms estimating prognosis and guiding therapy in adult congenital heart disease: data from a single tertiary centre including 10 019 patients. Eur Heart J. 2019 Apr 1;40(13):1069-1077. doi: 10.1093/eurheartj/ehy915.

  PMID: 30689812 BACKGROUND

• Samaras A, Bekiaridou A, Papazoglou AS, Moysidis DV, Tsoumakas G, Bamidis P, Tsigkas G, Lazaros G, Kassimis G, Fragakis N, Vassilikos V, Zarifis I, Tziakas DN, Tsioufis K, Davlouros P, Giannakoulas G; CardioMining Study Group. Artificial intelligence-based mining of electronic health record data to accelerate the digital transformation of the national cardiovascular ecosystem: design protocol of the CardioMining study. BMJ Open. 2023 Apr 3;13(4):e068698. doi: 10.1136/bmjopen-2022-068698.

  PMID: 37012018 DERIVED

Central Study Contacts

George Giannakoulas, MD, PhD

CONTACT

2310994830; ggiannakoulas@auth.gr

Athanasios Samaras, MD

CONTACT

2310994830; ath.samaras.as@gmail.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor in Cardiology

Study Record Dates

• First Submitted: November 24, 2021
• First Posted: January 4, 2022
• Study Start: January 14, 2022
• Primary Completion: December 1, 2025
• Study Completion: March 1, 2026
• Last Updated: January 29, 2025

Record last verified: 2025-01

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ANALYTIC CODE

Locations

GR (9)