General feature selection technique supporting sex-debiasing in chronic illness algorithms validated using wearable device data

Abstract In tasks involving human health condition data, feature selection is heavily affected by data types, the complexity of the condition manifestation, and the variability in physiological presentation. One type of variability often overlooked or oversimplified is the effect of biological sex....

Full description

Saved in:
Bibliographic Details
Main Authors: Jamison H. Burks, Lauryn Keeler Bruce, Patrick Kasl, Severine Soltani, Varun Viswanath, Wendy Hartogensis, Stephan Dilchert, Frederick M. Hecht, Subhasis Dasgupta, Ilkay Altintas, Amarnath Gupta, Ashley E. Mason, Benjamin L. Smarr
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:npj Women's Health
Online Access:https://doi.org/10.1038/s44294-024-00041-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846111977308422144
author Jamison H. Burks
Lauryn Keeler Bruce
Patrick Kasl
Severine Soltani
Varun Viswanath
Wendy Hartogensis
Stephan Dilchert
Frederick M. Hecht
Subhasis Dasgupta
Ilkay Altintas
Amarnath Gupta
Ashley E. Mason
Benjamin L. Smarr
author_facet Jamison H. Burks
Lauryn Keeler Bruce
Patrick Kasl
Severine Soltani
Varun Viswanath
Wendy Hartogensis
Stephan Dilchert
Frederick M. Hecht
Subhasis Dasgupta
Ilkay Altintas
Amarnath Gupta
Ashley E. Mason
Benjamin L. Smarr
author_sort Jamison H. Burks
collection DOAJ
description Abstract In tasks involving human health condition data, feature selection is heavily affected by data types, the complexity of the condition manifestation, and the variability in physiological presentation. One type of variability often overlooked or oversimplified is the effect of biological sex. As females have been chronically underrepresented in clinical research, we know less about how conditions manifest in females. Innovations in wearable technology have enabled individuals to generate high temporal resolution data for extended periods of time. With millions of days of data now available, additional feature selection pipelines should be developed to systematically identify sex-dependent variability in data, along with the effects of how many per-person data are included in analysis. Here we present a set of statistical approaches as a technique for identifying sex-dependent physiological and behavioral manifestations of complex diseases starting from longitudinal data, which are evaluated on diabetes, hypertension, and their comorbidity.
format Article
id doaj-art-6a7b0d1ab11c40dca1dceca18e560650
institution Kabale University
issn 2948-1716
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series npj Women's Health
spelling doaj-art-6a7b0d1ab11c40dca1dceca18e5606502024-12-22T12:56:33ZengNature Portfolionpj Women's Health2948-17162024-11-012111110.1038/s44294-024-00041-zGeneral feature selection technique supporting sex-debiasing in chronic illness algorithms validated using wearable device dataJamison H. Burks0Lauryn Keeler Bruce1Patrick Kasl2Severine Soltani3Varun Viswanath4Wendy Hartogensis5Stephan Dilchert6Frederick M. Hecht7Subhasis Dasgupta8Ilkay Altintas9Amarnath Gupta10Ashley E. Mason11Benjamin L. Smarr12Shu Chien-Gene Lay Department of Bioengineering, University of California San DiegoUC San Diego Health Department of Biomedical Informatics, University of California San DiegoShu Chien-Gene Lay Department of Bioengineering, University of California San DiegoBioinformatics and Systems Biology, University of California San DiegoDepartment of Electrical and Computer Engineering, University of California San DiegoOsher Center for Integrative Health, University of California San FranciscoDepartment of Management, Zicklin School of Business, Baruch College, The City University of New YorkOsher Center for Integrative Health, University of California San FranciscoSan Diego Supercomputer Center, University of California San DiegoSan Diego Supercomputer Center, University of California San DiegoSan Diego Supercomputer Center, University of California San DiegoOsher Center for Integrative Health, University of California San FranciscoShu Chien-Gene Lay Department of Bioengineering, University of California San DiegoAbstract In tasks involving human health condition data, feature selection is heavily affected by data types, the complexity of the condition manifestation, and the variability in physiological presentation. One type of variability often overlooked or oversimplified is the effect of biological sex. As females have been chronically underrepresented in clinical research, we know less about how conditions manifest in females. Innovations in wearable technology have enabled individuals to generate high temporal resolution data for extended periods of time. With millions of days of data now available, additional feature selection pipelines should be developed to systematically identify sex-dependent variability in data, along with the effects of how many per-person data are included in analysis. Here we present a set of statistical approaches as a technique for identifying sex-dependent physiological and behavioral manifestations of complex diseases starting from longitudinal data, which are evaluated on diabetes, hypertension, and their comorbidity.https://doi.org/10.1038/s44294-024-00041-z
spellingShingle Jamison H. Burks
Lauryn Keeler Bruce
Patrick Kasl
Severine Soltani
Varun Viswanath
Wendy Hartogensis
Stephan Dilchert
Frederick M. Hecht
Subhasis Dasgupta
Ilkay Altintas
Amarnath Gupta
Ashley E. Mason
Benjamin L. Smarr
General feature selection technique supporting sex-debiasing in chronic illness algorithms validated using wearable device data
npj Women's Health
title General feature selection technique supporting sex-debiasing in chronic illness algorithms validated using wearable device data
title_full General feature selection technique supporting sex-debiasing in chronic illness algorithms validated using wearable device data
title_fullStr General feature selection technique supporting sex-debiasing in chronic illness algorithms validated using wearable device data
title_full_unstemmed General feature selection technique supporting sex-debiasing in chronic illness algorithms validated using wearable device data
title_short General feature selection technique supporting sex-debiasing in chronic illness algorithms validated using wearable device data
title_sort general feature selection technique supporting sex debiasing in chronic illness algorithms validated using wearable device data
url https://doi.org/10.1038/s44294-024-00041-z
work_keys_str_mv AT jamisonhburks generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT laurynkeelerbruce generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT patrickkasl generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT severinesoltani generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT varunviswanath generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT wendyhartogensis generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT stephandilchert generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT frederickmhecht generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT subhasisdasgupta generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT ilkayaltintas generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT amarnathgupta generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT ashleyemason generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata
AT benjaminlsmarr generalfeatureselectiontechniquesupportingsexdebiasinginchronicillnessalgorithmsvalidatedusingwearabledevicedata