Longitudinally tracking personal physiomes for precision management of childhood epilepsy
Our current understanding of human physiology and activities is largely derived from sparse and discrete individual clinical measurements. To achieve precise, proactive, and effective health management of an individual, longitudinal, and dense tracking of personal physiomes and activities is require...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-12-01
|
| Series: | PLOS Digital Health |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931296/?tool=EBI |
| _version_ | 1797704070870335488 |
|---|---|
| author | Peifang Jiang Feng Gao Sixing Liu Sai Zhang Xicheng Zhang Zhezhi Xia Weiqin Zhang Tiejia Jiang Jason L. Zhu Zhaolei Zhang Qiang Shu Michael Snyder Jingjing Li |
| author_facet | Peifang Jiang Feng Gao Sixing Liu Sai Zhang Xicheng Zhang Zhezhi Xia Weiqin Zhang Tiejia Jiang Jason L. Zhu Zhaolei Zhang Qiang Shu Michael Snyder Jingjing Li |
| author_sort | Peifang Jiang |
| collection | DOAJ |
| description | Our current understanding of human physiology and activities is largely derived from sparse and discrete individual clinical measurements. To achieve precise, proactive, and effective health management of an individual, longitudinal, and dense tracking of personal physiomes and activities is required, which is only feasible by utilizing wearable biosensors. As a pilot study, we implemented a cloud computing infrastructure to integrate wearable sensors, mobile computing, digital signal processing, and machine learning to improve early detection of seizure onsets in children. We recruited 99 children diagnosed with epilepsy and longitudinally tracked them at single-second resolution using a wearable wristband, and prospectively acquired more than one billion data points. This unique dataset offered us an opportunity to quantify physiological dynamics (e.g., heart rate, stress response) across age groups and to identify physiological irregularities upon epilepsy onset. The high-dimensional personal physiome and activity profiles displayed a clustering pattern anchored by patient age groups. These signatory patterns included strong age and sex-specific effects on varying circadian rhythms and stress responses across major childhood developmental stages. For each patient, we further compared the physiological and activity profiles associated with seizure onsets with the personal baseline and developed a machine learning framework to accurately capture these onset moments. The performance of this framework was further replicated in another independent patient cohort. We next referenced our predictions with the electroencephalogram (EEG) signals on selected patients and demonstrated that our approach could detect subtle seizures not recognized by humans and could detect seizures prior to clinical onset. Our work demonstrated the feasibility of a real-time mobile infrastructure in a clinical setting, which has the potential to be valuable in caring for epileptic patients. Extension of such a system has the potential to be leveraged as a health management device or longitudinal phenotyping tool in clinical cohort studies. Author summary Epilepsy is the most common childhood neurological condition, affecting 0.5–1% of children worldwide. Affected individuals often have unpredictable seizure events, which, if not timely monitored or treated, can have debilitating or life-threatening consequences. We have developed an early alert system, which is based on wearable devices (e.g., wristband) connected to an adjacent cell phone via Bluetooth. The wearable devices have multiple sensors to collect physiological measurements including heart rate, body movement, and skin responses. These real-time measurements are transmitted via the cell phone to a remote cloud-based computing infrastructure and are compared to the individual’s baseline data. If an abnormal event such as seizure is detected, a message is then pushed to alert the caregiver. In a pilot study tracking 99 epileptic children, we demonstrated that our system was able to detect the onset of seizure events at a high accuracy, often before being noticed by caregivers. Our work demonstrated the feasibility of a real-time mobile infrastructure in a clinical setting, which is valuable in caring for epileptic patients. Extension of such a system has the potential to be leveraged as a health management device or precision phenotyping tool in clinical studies. |
| first_indexed | 2024-03-12T05:14:54Z |
| format | Article |
| id | doaj.art-a783ce4d0940499f9b68605f8cdd8f69 |
| institution | Directory Open Access Journal |
| issn | 2767-3170 |
| language | English |
| last_indexed | 2024-03-12T05:14:54Z |
| publishDate | 2022-12-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Digital Health |
| spelling | doaj.art-a783ce4d0940499f9b68605f8cdd8f692023-09-03T08:17:57ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702022-12-01112Longitudinally tracking personal physiomes for precision management of childhood epilepsyPeifang JiangFeng GaoSixing LiuSai ZhangXicheng ZhangZhezhi XiaWeiqin ZhangTiejia JiangJason L. ZhuZhaolei ZhangQiang ShuMichael SnyderJingjing LiOur current understanding of human physiology and activities is largely derived from sparse and discrete individual clinical measurements. To achieve precise, proactive, and effective health management of an individual, longitudinal, and dense tracking of personal physiomes and activities is required, which is only feasible by utilizing wearable biosensors. As a pilot study, we implemented a cloud computing infrastructure to integrate wearable sensors, mobile computing, digital signal processing, and machine learning to improve early detection of seizure onsets in children. We recruited 99 children diagnosed with epilepsy and longitudinally tracked them at single-second resolution using a wearable wristband, and prospectively acquired more than one billion data points. This unique dataset offered us an opportunity to quantify physiological dynamics (e.g., heart rate, stress response) across age groups and to identify physiological irregularities upon epilepsy onset. The high-dimensional personal physiome and activity profiles displayed a clustering pattern anchored by patient age groups. These signatory patterns included strong age and sex-specific effects on varying circadian rhythms and stress responses across major childhood developmental stages. For each patient, we further compared the physiological and activity profiles associated with seizure onsets with the personal baseline and developed a machine learning framework to accurately capture these onset moments. The performance of this framework was further replicated in another independent patient cohort. We next referenced our predictions with the electroencephalogram (EEG) signals on selected patients and demonstrated that our approach could detect subtle seizures not recognized by humans and could detect seizures prior to clinical onset. Our work demonstrated the feasibility of a real-time mobile infrastructure in a clinical setting, which has the potential to be valuable in caring for epileptic patients. Extension of such a system has the potential to be leveraged as a health management device or longitudinal phenotyping tool in clinical cohort studies. Author summary Epilepsy is the most common childhood neurological condition, affecting 0.5–1% of children worldwide. Affected individuals often have unpredictable seizure events, which, if not timely monitored or treated, can have debilitating or life-threatening consequences. We have developed an early alert system, which is based on wearable devices (e.g., wristband) connected to an adjacent cell phone via Bluetooth. The wearable devices have multiple sensors to collect physiological measurements including heart rate, body movement, and skin responses. These real-time measurements are transmitted via the cell phone to a remote cloud-based computing infrastructure and are compared to the individual’s baseline data. If an abnormal event such as seizure is detected, a message is then pushed to alert the caregiver. In a pilot study tracking 99 epileptic children, we demonstrated that our system was able to detect the onset of seizure events at a high accuracy, often before being noticed by caregivers. Our work demonstrated the feasibility of a real-time mobile infrastructure in a clinical setting, which is valuable in caring for epileptic patients. Extension of such a system has the potential to be leveraged as a health management device or precision phenotyping tool in clinical studies.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931296/?tool=EBI |
| spellingShingle | Peifang Jiang Feng Gao Sixing Liu Sai Zhang Xicheng Zhang Zhezhi Xia Weiqin Zhang Tiejia Jiang Jason L. Zhu Zhaolei Zhang Qiang Shu Michael Snyder Jingjing Li Longitudinally tracking personal physiomes for precision management of childhood epilepsy PLOS Digital Health |
| title | Longitudinally tracking personal physiomes for precision management of childhood epilepsy |
| title_full | Longitudinally tracking personal physiomes for precision management of childhood epilepsy |
| title_fullStr | Longitudinally tracking personal physiomes for precision management of childhood epilepsy |
| title_full_unstemmed | Longitudinally tracking personal physiomes for precision management of childhood epilepsy |
| title_short | Longitudinally tracking personal physiomes for precision management of childhood epilepsy |
| title_sort | longitudinally tracking personal physiomes for precision management of childhood epilepsy |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931296/?tool=EBI |
| work_keys_str_mv | AT peifangjiang longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT fenggao longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT sixingliu longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT saizhang longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT xichengzhang longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT zhezhixia longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT weiqinzhang longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT tiejiajiang longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT jasonlzhu longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT zhaoleizhang longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT qiangshu longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT michaelsnyder longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy AT jingjingli longitudinallytrackingpersonalphysiomesforprecisionmanagementofchildhoodepilepsy |