Symptoma, Better Diagnosis for Patients with Rare and Complex Diseases

Informazioni relative al progetto

Symptoma

ID dell’accordo di sovvenzione: 830017

DOI

10.3030/830017

Progetto chiuso

Data della firma CE 22 Ottobre 2018

Data di avvio 1 Settembre 2018

Data di completamento 28 Febbraio 2021

Finanziato da

• INDUSTRIAL LEADERSHIP - Innovation In SMEs

Costo totale

€ 2 282 000,00

Contributo UE

€ 1 597 400,00

Coordinato da

SYMPTOMA GMBH
Austria

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Demonstrators, pilots, prototypes (2)

D3.1 Spanish, Japanese, and Arabic version of Symptoma released.

D3.1 Spanish, Japanese, and Arabic version of Symptoma released.T3.1 Pre-translation engine: translating our ontology in the respective language via machine translation (aggregating results of Google, Bing, Yandex, and Deepl) and medical databases such as Orpha.net, Wikipedia, and the International Classification of Diseases.T3.2 Review process: carried out redundantly by native-speaking medical professionals. We will provide a platform to review each pre-translation within the context of the original concept. T3.3 Data mining: articles from Pubmed, eBooks, journals, and the Web for each language version. For each translation analyzing whether those phrases are being used in context of the associated concepts (e.g. are the right symptoms mentioned alongside the suggested disease name?).T3.4 Localization: of Symptoma to Spanish, Japanese, and Arabic using our new localization engine.

D2.2 Release question sequences derived from deep learning algorithms.

D2.2 Release question sequences derived from deep learning algorithms. T2.2 Train chatbot: utilizing the same case reports as in WP1. However, instead of searching with all symptoms extracted from the respective case, we start with one symptom only. Deep learning algorithms will then arrive at the best question sequence uncovering the other symptoms thus leading to the right diagnosis. Question sequences should then work for all 44,000 conditions in our database while accounting for disease incidences (a more common disease should have a higher priority than a rare one).T2.3 Test chatbot: in production. As in WP1, we will release question sequences to production, monitor search signals indicating successful questions, and continuously optimize for it.

Pubblicazioni

Non-peer reviewed articles (3)

Predicting Global Trends in COVID-19 Cases Via Online Symptom Checkers Self-Assessments

Autori: Marc Zobel, Alistair Martin, Jama Nateqi, Bernhard Knapp
Pubblicato in: SSRN Electronic Journal, 2020, ISSN 1556-5068
Editore: SSRN
DOI: 10.2139/ssrn.3729913

Querdenker-Preis

Autori: DGIM
Pubblicato in: DMW - Deutsche Medizinische Wochenschrift, Numero 144/15, 2019, Pagina/e 1085-1085, ISSN 0012-0472
Editore: Georg Thieme Verlag
DOI: 10.1055/a-0954-8989

Global review of assisted diagnosis tools using medical database and artificial intelligence methods to improve complex disease diagnosis

Autori: Anne Blériot, Franck Le Meur, Guillaume De Chamisso
Pubblicato in: Research Square, 2021, ISSN 2693-5015
Editore: Research Square
DOI: 10.21203/rs.3.rs-157785/v1

Peer reviewed articles (3)

An artificial intelligence-based first-line defence against COVID-19: digitally screening citizens for risks via a chatbot

Autori: Alistair Martin, Jama Nateqi, Stefanie Gruarin, Nicolas Munsch, Isselmou Abdarahmane, Marc Zobel, Bernhard Knapp
Pubblicato in: Scientific Reports, Numero 10/1, 2020, ISSN 2045-2322
Editore: Nature Publishing Group
DOI: 10.1038/s41598-020-75912-x

Diagnostic Accuracy of Web-Based COVID-19 Symptom Checkers: Comparison Study

Autori: Nicolas Munsch, Alistair Martin, Stefanie Gruarin, Jama Nateqi, Isselmou Abdarahmane, Rafael Weingartner-Ortner, Bernhard Knapp
Pubblicato in: Journal of Medical Internet Research, Numero 22/10, 2020, Pagina/e e21299, ISSN 1438-8871
Editore: Journal of medical Internet Research
DOI: 10.2196/21299

Vom Symptom zur Diagnose – Tauglichkeit von Symptom-Checkern

Autori: J. Nateqi, S. Lin, H. Krobath, S. Gruarin, T. Lutz, T. Dvorak, A. Gruschina, R. Ortner
Pubblicato in: HNO, Numero 67/5, 2019, Pagina/e 334-342, ISSN 0017-6192
Editore: Springer Verlag
DOI: 10.1007/s00106-019-0666-y

Other (1)

COVID-19 symptom frequency comparison: non-hospitalised positively and negatively tested persons with flu-like symptoms in Austria

Autori: Nicolas Musch, Stefanie Gruarin, Alistair Martin, Jama Nateqi, Thomas Lutz, Judith H. Aberle, Bernhard Knapp
Pubblicato in: medRxiv, 2021
Editore: medRxiv
DOI: 10.1101/2021.02.24.21252426