Applying machine learning to smartphone based cognitive and sleep assessments in schizophrenia
© 2021 The Authors. Published by Elsevier Inc..
BACKGROUND: Cognitive impairment in schizophrenia remains a chief source of functional disability and impairment, despite the potential for effective interventions. This is in part related to a lack of practical and easy to administer screening strategies that can identify and help triage cognitive impairment. This study explores how smartphone-based assessments may help address this need.
METHODS: In this study, data was analyzed from 25 subjects with schizophrenia and 30 controls who engaged with a gamified mobile phone version of the Trails-B cognitive assessment in their everyday life over 90 days and complete a clinical neurocognitive testing battery at the beginning and end of the study. Machine learning was applied to the resulting dataset to predict disease status and neurocognitive function and understand which features were most important for accurate prediction.
RESULTS: The generated models predicted disease status with high accuracy using static features alone (AUC = 0.94), with the total number of items collected and the total duration of interaction with the application most predictive. The addition of temporal data statistically significantly improved performance (AUC = 0.95), with the amount of idle time a significant new predictor. Correlates of sleep dysfunction were also predicted (AUC = 0.80), with similar feature importance.
DISCUSSION: Machine learning enabled the highly accurate identification of subjects with schizophrenia versus healthy controls, and the accurate prediction of neurocognitive function. The addition of temporal data significantly improved the performance of these models, underscoring the value of smartphone-based assessments of cognition as a practical tool for assessing cognition.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:27 |
|---|---|
| Enthalten in: |
Schizophrenia research. Cognition - 27(2022) vom: 17. März, Seite 100216 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Kalinich, Mark [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Digital psychiatry |
|---|
| Anmerkungen: |
Date Revised 29.04.2022 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1016/j.scog.2021.100216 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM334706270 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM334706270 | ||
| 003 | DE-627 | ||
| 005 | 20231225224300.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.scog.2021.100216 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1115.xml |
| 035 | |a (DE-627)NLM334706270 | ||
| 035 | |a (NLM)34934638 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Kalinich, Mark |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Applying machine learning to smartphone based cognitive and sleep assessments in schizophrenia |
| 264 | 1 | |c 2022 | |
| 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 Revised 29.04.2022 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © 2021 The Authors. Published by Elsevier Inc. | ||
| 520 | |a BACKGROUND: Cognitive impairment in schizophrenia remains a chief source of functional disability and impairment, despite the potential for effective interventions. This is in part related to a lack of practical and easy to administer screening strategies that can identify and help triage cognitive impairment. This study explores how smartphone-based assessments may help address this need | ||
| 520 | |a METHODS: In this study, data was analyzed from 25 subjects with schizophrenia and 30 controls who engaged with a gamified mobile phone version of the Trails-B cognitive assessment in their everyday life over 90 days and complete a clinical neurocognitive testing battery at the beginning and end of the study. Machine learning was applied to the resulting dataset to predict disease status and neurocognitive function and understand which features were most important for accurate prediction | ||
| 520 | |a RESULTS: The generated models predicted disease status with high accuracy using static features alone (AUC = 0.94), with the total number of items collected and the total duration of interaction with the application most predictive. The addition of temporal data statistically significantly improved performance (AUC = 0.95), with the amount of idle time a significant new predictor. Correlates of sleep dysfunction were also predicted (AUC = 0.80), with similar feature importance | ||
| 520 | |a DISCUSSION: Machine learning enabled the highly accurate identification of subjects with schizophrenia versus healthy controls, and the accurate prediction of neurocognitive function. The addition of temporal data significantly improved the performance of these models, underscoring the value of smartphone-based assessments of cognition as a practical tool for assessing cognition | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Digital psychiatry | |
| 650 | 4 | |a Gamification | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Schizophrenia | |
| 700 | 1 | |a Ebrahim, Senan |e verfasserin |4 aut | |
| 700 | 1 | |a Hays, Ryan |e verfasserin |4 aut | |
| 700 | 1 | |a Melcher, Jennifer |e verfasserin |4 aut | |
| 700 | 1 | |a Vaidyam, Aditya |e verfasserin |4 aut | |
| 700 | 1 | |a Torous, John |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Schizophrenia research. Cognition |d 2014 |g 27(2022) vom: 17. März, Seite 100216 |w (DE-627)NLM240266854 |x 2215-0013 |7 nnns |
| 773 | 1 | 8 | |g volume:27 |g year:2022 |g day:17 |g month:03 |g pages:100216 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.scog.2021.100216 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 27 |j 2022 |b 17 |c 03 |h 100216 | ||