Your browser doesn't support javascript.
loading
Evaluation of artificial intelligence systems for assisting neurologists with fast and accurate annotations of scalp electroencephalography data.
Roy, Subhrajit; Kiral, Isabell; Mirmomeni, Mahtab; Mummert, Todd; Braz, Alan; Tsay, Jason; Tang, Jianbin; Asif, Umar; Schaffter, Thomas; Ahsen, Mehmet Eren; Iwamori, Toshiya; Yanagisawa, Hiroki; Poonawala, Hasan; Madan, Piyush; Qin, Yong; Picone, Joseph; Obeid, Iyad; Marques, Bruno De Assis; Maetschke, Stefan; Khalaf, Rania; Rosen-Zvi, Michal; Stolovitzky, Gustavo; Harrer, Stefan.
  • Roy S; IBM Research, Melbourne, Australia.
  • Kiral I; IBM Research, Melbourne, Australia.
  • Mirmomeni M; IBM Research, Melbourne, Australia.
  • Mummert T; IBM Research, T. J. Watson Research Center, USA.
  • Braz A; IBM Research, T. J. Watson Research Center, USA.
  • Tsay J; IBM Research, T. J. Watson Research Center, USA.
  • Tang J; IBM Research, Melbourne, Australia.
  • Asif U; IBM Research, Melbourne, Australia.
  • Schaffter T; Sage Bionetworks, Seattle, USA.
  • Ahsen ME; Icahn School of Medicine at Mount Sinai, NY, USA.
  • Iwamori T; IBM Research, Tokyo, Japan.
  • Yanagisawa H; IBM Research, Tokyo, Japan.
  • Poonawala H; IBM Research, Singapore.
  • Madan P; IBM-MIT AI Lab, Cambridge, USA.
  • Qin Y; IBM Research, Beijing, China.
  • Picone J; College of Engineering, Temple University, Philadelphia, USA.
  • Obeid I; College of Engineering, Temple University, Philadelphia, USA.
  • Marques BA; IBM Research, Melbourne, Australia.
  • Maetschke S; IBM Research, Melbourne, Australia.
  • Khalaf R; IBM-MIT AI Lab, Cambridge, USA.
  • Rosen-Zvi M; IBM Research, Haifa, Israel.
  • Stolovitzky G; IBM Research, T. J. Watson Research Center, USA. Electronic address: gustavo@us.ibm.com.
  • Harrer S; IBM Research, Melbourne, Australia. Electronic address: stefan.harrer@dhcrc.com.
EBioMedicine ; 66: 103275, 2021 Apr.
Article en En | MEDLINE | ID: mdl-33745882
BACKGROUND: Assistive automatic seizure detection can empower human annotators to shorten patient monitoring data review times. We present a proof-of-concept for a seizure detection system that is sensitive, automated, patient-specific, and tunable to maximise sensitivity while minimizing human annotation times. The system uses custom data preparation methods, deep learning analytics and electroencephalography (EEG) data. METHODS: Scalp EEG data of 365 patients containing 171,745 s ictal and 2,185,864 s interictal samples obtained from clinical monitoring systems were analysed as part of a crowdsourced artificial intelligence (AI) challenge. Participants were tasked to develop an ictal/interictal classifier with high sensitivity and low false alarm rates. We built a challenge platform that prevented participants from downloading or directly accessing the data while allowing crowdsourced model development. FINDINGS: The automatic detection system achieved tunable sensitivities between 75.00% and 91.60% allowing a reduction in the amount of raw EEG data to be reviewed by a human annotator by factors between 142x, and 22x respectively. The algorithm enables instantaneous reviewer-managed optimization of the balance between sensitivity and the amount of raw EEG data to be reviewed. INTERPRETATION: This study demonstrates the utility of deep learning for patient-specific seizure detection in EEG data. Furthermore, deep learning in combination with a human reviewer can provide the basis for an assistive data labelling system lowering the time of manual review while maintaining human expert annotation performance. FUNDING: IBM employed all IBM Research authors. Temple University employed all Temple University authors. The Icahn School of Medicine at Mount Sinai employed Eren Ahsen. The corresponding authors Stefan Harrer and Gustavo Stolovitzky declare that they had full access to all the data in the study and that they had final responsibility for the decision to submit for publication.
Asunto(s)
Palabras clave

Texto completo: 1 Banco de datos: MEDLINE Asunto principal: Convulsiones / Encéfalo / Inteligencia Artificial / Electroencefalografía / Neurólogos Tipo de estudio: Diagnostic_studies / Guideline / Prognostic_studies Límite: Humans Idioma: En Año: 2021 Tipo del documento: Article

Texto completo: 1 Banco de datos: MEDLINE Asunto principal: Convulsiones / Encéfalo / Inteligencia Artificial / Electroencefalografía / Neurólogos Tipo de estudio: Diagnostic_studies / Guideline / Prognostic_studies Límite: Humans Idioma: En Año: 2021 Tipo del documento: Article