Connectomic disturbances underlying insomnia disorder and predictors of treatment response
ObjectiveDespite its prevalence, insomnia disorder (ID) remains poorly understood. In this study, we used machine learning to analyze the functional connectivity (FC) disturbances underlying ID, and identify potential predictors of treatment response through recurrent transcranial magnetic stimulati...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2022.960350/full |
| _version_ | 1828149724447768576 |
|---|---|
| author | Qian Lu Wentong Zhang Hailang Yan Negar Mansouri Onur Tanglay Karol Osipowicz Angus W. Joyce Isabella M. Young Xia Zhang Xia Zhang Stephane Doyen Michael E. Sughrue Michael E. Sughrue Chuan He |
| author_facet | Qian Lu Wentong Zhang Hailang Yan Negar Mansouri Onur Tanglay Karol Osipowicz Angus W. Joyce Isabella M. Young Xia Zhang Xia Zhang Stephane Doyen Michael E. Sughrue Michael E. Sughrue Chuan He |
| author_sort | Qian Lu |
| collection | DOAJ |
| description | ObjectiveDespite its prevalence, insomnia disorder (ID) remains poorly understood. In this study, we used machine learning to analyze the functional connectivity (FC) disturbances underlying ID, and identify potential predictors of treatment response through recurrent transcranial magnetic stimulation (rTMS) and pharmacotherapy.Materials and methods51 adult patients with chronic insomnia and 42 healthy age and education matched controls underwent baseline anatomical T1 magnetic resonance imaging (MRI), resting-stage functional MRI (rsfMRI), and diffusion weighted imaging (DWI). Imaging was repeated for 24 ID patients following four weeks of treatment with pharmacotherapy, with or without rTMS. A recently developed machine learning technique, Hollow Tree Super (HoTS) was used to classify subjects into ID and control groups based on their FC, and derive network and parcel-based FC features contributing to each model. The number of FC anomalies within each network was also compared between responders and non-responders using median absolute deviation at baseline and follow-up.ResultsSubjects were classified into ID and control with an area under the receiver operating characteristic curve (AUC-ROC) of 0.828. Baseline FC anomaly counts were higher in responders than non-responders. Response as measured by the Insomnia Severity Index (ISI) was associated with a decrease in anomaly counts across all networks, while all networks showed an increase in anomaly counts when response was measured using the Pittsburgh Sleep Quality Index. Overall, responders also showed greater change in all networks, with the Default Mode Network demonstrating the greatest change.ConclusionMachine learning analysis into the functional connectome in ID may provide useful insight into diagnostic and therapeutic targets. |
| first_indexed | 2024-04-11T21:33:30Z |
| format | Article |
| id | doaj.art-eb90fc462f474ba89d8bf26336b9f1f9 |
| institution | Directory Open Access Journal |
| issn | 1662-5161 |
| language | English |
| last_indexed | 2024-04-11T21:33:30Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj.art-eb90fc462f474ba89d8bf26336b9f1f92022-12-22T04:01:50ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612022-08-011610.3389/fnhum.2022.960350960350Connectomic disturbances underlying insomnia disorder and predictors of treatment responseQian Lu0Wentong Zhang1Hailang Yan2Negar Mansouri3Onur Tanglay4Karol Osipowicz5Angus W. Joyce6Isabella M. Young7Xia Zhang8Xia Zhang9Stephane Doyen10Michael E. Sughrue11Michael E. Sughrue12Chuan He13Department of Rehabilitation Medicine, The Affiliated Jiangsu Shengze Hospital of Nanjing Medical University, Suzhou, ChinaDepartment of Rehabilitation Medicine, The Affiliated Jiangsu Shengze Hospital of Nanjing Medical University, Suzhou, ChinaDepartment of Radiology, The Affiliated Jiangsu Shengze Hospital of Nanjing Medical University, Suzhou, ChinaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaInternational Joint Research Center on Precision Brain Medicine, XD Group Hospital, Xi’an, ChinaShenzhen Xijia Medical Technology Company, Shenzhen, ChinaOmniscient Neurotechnology, Sydney, NSW, AustraliaOmniscient Neurotechnology, Sydney, NSW, AustraliaInternational Joint Research Center on Precision Brain Medicine, XD Group Hospital, Xi’an, ChinaDepartment of Rehabilitation Medicine, The Affiliated Jiangsu Shengze Hospital of Nanjing Medical University, Suzhou, ChinaObjectiveDespite its prevalence, insomnia disorder (ID) remains poorly understood. In this study, we used machine learning to analyze the functional connectivity (FC) disturbances underlying ID, and identify potential predictors of treatment response through recurrent transcranial magnetic stimulation (rTMS) and pharmacotherapy.Materials and methods51 adult patients with chronic insomnia and 42 healthy age and education matched controls underwent baseline anatomical T1 magnetic resonance imaging (MRI), resting-stage functional MRI (rsfMRI), and diffusion weighted imaging (DWI). Imaging was repeated for 24 ID patients following four weeks of treatment with pharmacotherapy, with or without rTMS. A recently developed machine learning technique, Hollow Tree Super (HoTS) was used to classify subjects into ID and control groups based on their FC, and derive network and parcel-based FC features contributing to each model. The number of FC anomalies within each network was also compared between responders and non-responders using median absolute deviation at baseline and follow-up.ResultsSubjects were classified into ID and control with an area under the receiver operating characteristic curve (AUC-ROC) of 0.828. Baseline FC anomaly counts were higher in responders than non-responders. Response as measured by the Insomnia Severity Index (ISI) was associated with a decrease in anomaly counts across all networks, while all networks showed an increase in anomaly counts when response was measured using the Pittsburgh Sleep Quality Index. Overall, responders also showed greater change in all networks, with the Default Mode Network demonstrating the greatest change.ConclusionMachine learning analysis into the functional connectome in ID may provide useful insight into diagnostic and therapeutic targets.https://www.frontiersin.org/articles/10.3389/fnhum.2022.960350/fullInsomniamachine learningfunctional connectivityrTMStreatment response |
| spellingShingle | Qian Lu Wentong Zhang Hailang Yan Negar Mansouri Onur Tanglay Karol Osipowicz Angus W. Joyce Isabella M. Young Xia Zhang Xia Zhang Stephane Doyen Michael E. Sughrue Michael E. Sughrue Chuan He Connectomic disturbances underlying insomnia disorder and predictors of treatment response Frontiers in Human Neuroscience Insomnia machine learning functional connectivity rTMS treatment response |
| title | Connectomic disturbances underlying insomnia disorder and predictors of treatment response |
| title_full | Connectomic disturbances underlying insomnia disorder and predictors of treatment response |
| title_fullStr | Connectomic disturbances underlying insomnia disorder and predictors of treatment response |
| title_full_unstemmed | Connectomic disturbances underlying insomnia disorder and predictors of treatment response |
| title_short | Connectomic disturbances underlying insomnia disorder and predictors of treatment response |
| title_sort | connectomic disturbances underlying insomnia disorder and predictors of treatment response |
| topic | Insomnia machine learning functional connectivity rTMS treatment response |
| url | https://www.frontiersin.org/articles/10.3389/fnhum.2022.960350/full |
| work_keys_str_mv | AT qianlu connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT wentongzhang connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT hailangyan connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT negarmansouri connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT onurtanglay connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT karolosipowicz connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT anguswjoyce connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT isabellamyoung connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT xiazhang connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT xiazhang connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT stephanedoyen connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT michaelesughrue connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT michaelesughrue connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse AT chuanhe connectomicdisturbancesunderlyinginsomniadisorderandpredictorsoftreatmentresponse |