Predicting the cause of seizures using features extracted from interactions with a virtual agent
Copyright © 2023. Published by Elsevier Ltd..
OBJECTIVE: A clinical decision tool for Transient Loss of Consciousness (TLOC) could reduce currently high misdiagnosis rates and waiting times for specialist assessments. Most clinical decision tools based on patient-reported symptom inventories only distinguish between two of the three most common causes of TLOC (epilepsy, functional /dissociative seizures, and syncope) or struggle with the particularly challenging differentiation between epilepsy and FDS. Based on previous research describing differences in spoken accounts of epileptic seizures and FDS seizures, this study explored the feasibility of predicting the cause of TLOC by combining the automated analysis of patient-reported symptoms and spoken TLOC descriptions.
METHOD: Participants completed an online web application that consisted of a 34-item medical history and symptom questionnaire (iPEP) and spoken interaction with a virtual agent (VA) that asked eight questions about the most recent experience of TLOC. Support Vector Machines (SVM) were trained using different combinations of features and nested leave-one-out cross validation. The iPEP provided a baseline performance. Inspired by previous qualitative research three spoken language based feature sets were designed to assess: (1) formulation effort, (2) the proportion of words from different semantic categories, and (3) verb, adverb, and adjective usage.
RESULTS: 76 participants completed the application (Epilepsy = 24, FDS = 36, syncope = 16). Only 61 participants also completed the VA interaction (Epilepsy = 20, FDS = 29, syncope = 12). The iPEP model accurately predicted 65.8 % of all diagnoses, but the inclusion of the language features increased the accuracy to 85.5 % by improving the differential diagnosis between epilepsy and FDS.
CONCLUSION: These findings suggest that an automated analysis of TLOC descriptions collected using an online web application and VA could improve the accuracy of current clinical decisions tools for TLOC and facilitate clinical stratification processes (such as ensuring appropriate referral to cardiological versus neurological investigation and management pathways).
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:114 |
|---|---|
| Enthalten in: |
Seizure - 114(2024) vom: 27. Jan., Seite 84-89 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Pevy, Nathan [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Classification |
|---|
| Anmerkungen: |
Date Completed 23.01.2024 Date Revised 23.01.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.seizure.2023.11.022 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM365825530 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM365825530 | ||
| 003 | DE-627 | ||
| 005 | 20240123231945.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.seizure.2023.11.022 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1268.xml |
| 035 | |a (DE-627)NLM365825530 | ||
| 035 | |a (NLM)38091849 | ||
| 035 | |a (PII)S1059-1311(23)00319-9 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Pevy, Nathan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Predicting the cause of seizures using features extracted from interactions with a virtual agent |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 23.01.2024 | ||
| 500 | |a Date Revised 23.01.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2023. Published by Elsevier Ltd. | ||
| 520 | |a OBJECTIVE: A clinical decision tool for Transient Loss of Consciousness (TLOC) could reduce currently high misdiagnosis rates and waiting times for specialist assessments. Most clinical decision tools based on patient-reported symptom inventories only distinguish between two of the three most common causes of TLOC (epilepsy, functional /dissociative seizures, and syncope) or struggle with the particularly challenging differentiation between epilepsy and FDS. Based on previous research describing differences in spoken accounts of epileptic seizures and FDS seizures, this study explored the feasibility of predicting the cause of TLOC by combining the automated analysis of patient-reported symptoms and spoken TLOC descriptions | ||
| 520 | |a METHOD: Participants completed an online web application that consisted of a 34-item medical history and symptom questionnaire (iPEP) and spoken interaction with a virtual agent (VA) that asked eight questions about the most recent experience of TLOC. Support Vector Machines (SVM) were trained using different combinations of features and nested leave-one-out cross validation. The iPEP provided a baseline performance. Inspired by previous qualitative research three spoken language based feature sets were designed to assess: (1) formulation effort, (2) the proportion of words from different semantic categories, and (3) verb, adverb, and adjective usage | ||
| 520 | |a RESULTS: 76 participants completed the application (Epilepsy = 24, FDS = 36, syncope = 16). Only 61 participants also completed the VA interaction (Epilepsy = 20, FDS = 29, syncope = 12). The iPEP model accurately predicted 65.8 % of all diagnoses, but the inclusion of the language features increased the accuracy to 85.5 % by improving the differential diagnosis between epilepsy and FDS | ||
| 520 | |a CONCLUSION: These findings suggest that an automated analysis of TLOC descriptions collected using an online web application and VA could improve the accuracy of current clinical decisions tools for TLOC and facilitate clinical stratification processes (such as ensuring appropriate referral to cardiological versus neurological investigation and management pathways) | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Classification | |
| 650 | 4 | |a Epilepsy | |
| 650 | 4 | |a Functional seizures | |
| 650 | 4 | |a Natural language processing | |
| 650 | 4 | |a Speech analysis | |
| 650 | 4 | |a Transient loss of consciousness | |
| 700 | 1 | |a Christensen, Heidi |e verfasserin |4 aut | |
| 700 | 1 | |a Walker, Traci |e verfasserin |4 aut | |
| 700 | 1 | |a Reuber, Markus |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Seizure |d 1997 |g 114(2024) vom: 27. Jan., Seite 84-89 |w (DE-627)NLM013256173 |x 1532-2688 |7 nnns |
| 773 | 1 | 8 | |g volume:114 |g year:2024 |g day:27 |g month:01 |g pages:84-89 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.seizure.2023.11.022 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 114 |j 2024 |b 27 |c 01 |h 84-89 | ||