Comparative Assessment of Multimodal Sensor Data Quality Collected Using Android and iOS Smartphones in Real-World Settings

被引：0

作者：

Halabi, Ramzi ^{[1
]}

Selvarajan, Rahavi ^{[1
]}

Lin, Zixiong ^{[1
]}

Herd, Calvin ^{[1
]}

Li, Xueying ^{[1
]}

Kabrit, Jana ^{[1
]}

Tummalacherla, Meghasyam ^{[2
]}

Chaibub Neto, Elias ^{[2
]}

Pratap, Abhishek ^{[1
,3
,4
,5
,6
]}

机构：

[1] Centre for Addiction and Mental Health, Toronto,ON,M6J 1H4, Canada

[2] Sage Bionetworks, Seattle,WA,98121, United States

[3] Department of Psychiatry, University of Toronto, Toronto,ON,M5S 1A1, Canada

[4] Vector Institute for Artificial Intelligence, Toronto,ON,M5T 1R8, Canada

[5] Institute of Psychiatry, Psychology & Neuroscience, King’s College London, London,WC2R 2LS, United Kingdom

[6] Department of Biomedical Informatics and Medical Education, University of Washington, Seattle,WA,98195, United States

来源：

Sensors | 2024年 / 24卷 / 19期

关键词：

Healthcare researchers are increasingly utilizing smartphone sensor data as a scalable and cost-effective approach to studying individualized health-related behaviors in real-world settings. However; to develop reliable and robust digital behavioral signatures that may help in the early prediction of the individualized disease trajectory and future prognosis; there is a critical need to quantify the potential variability that may be present in the underlying sensor data due to variations in the smartphone hardware and software used by large population. Using sensor data collected in real-world settings from 3000 participants’ smartphones for up to 84 days; we compared differences in the completeness; correctness; and consistency of the three most common smartphone sensors—the accelerometer; gyroscope; and GPS— within and across Android and iOS devices. Our findings show considerable variation in sensor data quality within and across Android and iOS devices. Sensor data from iOS devices showed significantly lower levels of anomalous point density (APD) compared to Android across all sensors (p −4). iOS devices showed a considerably lower missing data ratio (MDR) for the accelerometer compared to the GPS data (p −4). Notably; the quality features derived from raw sensor data across devices alone could predict the device type (Android vs. iOS) with an up to 0.98 accuracy 95% CI [0.977; 0.982]. Such significant differences in sensor data quantity and quality gathered from iOS and Android platforms could lead to considerable variation in health-related inference derived from heterogenous consumer-owned smartphones. Our research highlights the importance of assessing; measuring; and adjusting for such critical differences in smartphone sensor-based assessments. Understanding the factors contributing to the variation in sensor data based on daily device usage will help develop reliable; standardized; inclusive; and practically applicable digital behavioral patterns that may be linked to health outcomes in real-world settings. © 2024 by the authors;

D O I：

10.3390/s24196246

中图分类号：

学科分类号：

摘要：

引用

共 50 条

[1] Using iOS for Inconspicuous Data Collection: A Real-World Assessment
Nishiyama, Yuuki
Ferreira, Denzil
Sasaki, Wataru
Okoshi, Tadashi
Nakazawa, Jin
[J]. UBICOMP/ISWC '20 ADJUNCT: PROCEEDINGS OF THE 2020 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2020 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, 2020, : 261 - 266
[2] ASSESSMENT OF REAL-WORLD DATA SOURCES AND A HYBRID APPROACH IN REAL-WORLD EVIDENCE GENERATION USING UNHARMONIZED DATA SOURCES
Toh, K. C.
Goh, C. H.
Goh, V
Dong, Z.
Dumpala, L. S.
Maity, S.
Wu, J. Y.
Kleinman, N.
Lee, Y.
[J]. VALUE IN HEALTH, 2024, 27 (06) : S407 - S407
[3] Solving data quality issues of fundus images in real-world settings by ophthalmic AI
Li, Zhongwen
Chen, Wei
[J]. CELL REPORTS MEDICINE, 2023, 4 (02)
[4] Real-world incidence and prevalence of low back pain using routinely collected data
Fatoye, Francis
Gebrye, Tadesse
Odeyemi, Isaac
[J]. RHEUMATOLOGY INTERNATIONAL, 2019, 39 (04) : 619 - 626
[5] Real-world incidence and prevalence of low back pain using routinely collected data
Francis Fatoye
Tadesse Gebrye
Isaac Odeyemi
[J]. Rheumatology International, 2019, 39 : 619 - 626
[6] Quality assessment of real-world data repositories across the data life cycle: A literature review
Liaw, Siaw-Teng
Guo, Jason Guan Nan
Ansari, Sameera
Jonnagaddala, Jitendra
Godinho, Myron Anthony
Borelli, Alder Jose
de Lusignan, Simon
Capurro, Daniel
Liyanage, Harshana
Bhattal, Navreet
Bennett, Vicki
Chan, Jaclyn
Kahn, Michael G.
[J]. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2021, 28 (07) : 1591 - 1599
[7] Using Real-World Data in Health Technology Assessment (HTA) Practice: A Comparative Study of Five HTA Agencies
Amr Makady
Ard van Veelen
Páll Jonsson
Owen Moseley
Anne D’Andon
Anthonius de Boer
Hans Hillege
Olaf Klungel
Wim Goettsch
[J]. PharmacoEconomics, 2018, 36 : 359 - 368
[8] Using Real-World Data in Health Technology Assessment (HTA) Practice: A Comparative Study of Five HTA Agencies
Makady, Amr
van Veelen, Ard
Jonsson, Pall
Moseley, Owen
D'Andon, Anne
de Boer, Anthonius
Hillege, Hans
Klungel, Olaf
Goettsch, Wim
[J]. PHARMACOECONOMICS, 2018, 36 (03) : 359 - 368
[9] "Ten Commandments" for Conducting Comparative Effectiveness Research Using "Real-World Data"
Willke, Richard J.
Mullins, C. Daniel
[J]. JOURNAL OF MANAGED CARE PHARMACY, 2011, 17 (09): : S10 - S15
[10] Strategies to improve quality improvement collaboratives data quality in real-world settings: Experience from the MAS Collaborative.
Houston, Logan Cole
Gonzalez-Guzman, Miriam
Pershad, Alisha Ria
Abud, Naomi Echeandia
Delgado, Luis
Enriquez-Chavez, Cecilia
Aristizabal, Paula
Arrieta, Jafet
Friedrich, Paola
[J]. JOURNAL OF CLINICAL ONCOLOGY, 2022, 40 (16) : E18711 - E18711

← 1 2 3 4 5 →