The Use of Smart Devices in Capturing Digital Biomarkers in Eating Disorders

A Novel Pilot Study Examining the Potential of Smartphones to Capture New Types of Data That Can Accurately Assess the Physiological and Psychological Health Status of an Individual With an Eating Disorder

This study aims to explore how smart devices can be used to monitor the health of individuals with eating disorders. Eating disorders are serious mental health conditions that impact both mental and physical health. Effective monitoring is crucial for developing treatment plans and ensuring the safety of individuals both in hospitals and at home. Currently, healthcare professionals use manual methods to measure important health indicators like heart rate, blood pressure, and BMI. These methods can be time-consuming and may not always accurately reflect a patient's health due to the possibility of patients concealing the severity of their condition. Furthermore, monitoring at home is challenging due to the lack of professional equipment and training for caregivers. With advancements in digital technology, smartphones and smartwatches now have the potential to collect and analyse health data in real-time. These devices can capture data on heart rate, blood pressure, respiratory rate, and other vital signs through non-invasive methods like analysing facial and fingertip blood volume, namely the photoplethysmography technology. Additionally, video recordings from smartphone cameras can be used to assess physical and mental health by analysing facial expressions, voice patterns, and physical movements. By utilising these digital tools, combined with validated questionnaires and tasks to assess participants' psychological status and the severity of disorders, this study expects to create a more efficient and accessible way for individuals with eating disorders to monitor their health at home. The study will collect data from participants both in hospital settings and during outpatient care to ensure the reliability and effectiveness of these digital methods across participants with different levels of severity. This comprehensive approach aims to improve early detection of health issues, optimise treatment plans, and ultimately enhance the quality of life for individuals with eating disorders.

Study Overview

• Status: Recruiting
• Conditions: Eating Disorders
• Intervention / Treatment: Device: UH100

Detailed Description

Eating disorders are complex mental health conditions characterised by abnormal eating habits and distressing thoughts about body weight and shape, significantly impacting both mental and physical health. According to the International Classification of Diseases, 11th Revision, feeding and eating disorders include several subtypes such as anorexia nervosa (AN), bulimia nervosa (BN), and binge eating disorder (BED). These subtypes often involve patterns of restrictive or excessive food intake, leading to severe health issues and impairments in daily functioning.

Given the rising incidence and profound impacts of eating disorders in recent years, including high mortality rates and significant economic burdens, there is an urgent need for innovative management strategies and more efficient triage and monitoring systems for early intervention and home-based care.

For the care of individuals with eating disorders, comprehensive and continuous assessment of physical and psychiatric conditions is essential. As recommended by the UK's National Institute for Health and Care Excellence (NICE) and the Royal College of Psychiatrists, key clinical markers monitored, include weight loss, BMI, heart rate, blood pressure, temperature, hydration status, and muscular function. Monitoring these markers is crucial for early detection of medical complications, such as electrolyte imbalances, cardiac arrhythmias, and orthostatic hypotension, which pose serious health risks. Additionally, these markers help evaluate the disorder's severity, guide treatment adjustments, and ensure patient safety during recovery.

However, traditional methods used to assess these biomarkers are burdensome and time-consuming. With the advancement of technology, novel smart devices can efficiently detect traditional biomarkers such as heart rate and blood pressure, while also exploring potential novel measures of the disease. Therefore, this study aims to validate and explore the potential of these technologies to provide monitoring comparable to traditional methods and to integrate collected data to generate sophisticated insights into the health status of individuals with eating disorders.

According to previous research, the analysis of facial information, including static features and dynamic movements, combined with advanced algorithms and machine learning, can estimate body weight, BMI, parotid gland size, and skin condition. When voice pattern analysis is integrated with facial dynamics during the video diary entry phase and the image response task, where participants share their thoughts on specific images, it is expected to further assess physical and psychological states, particularly when discussing sensitive topics or images, such as high-calorie foods. These estimations can be used to interpret the health status of individuals with eating disorders. Additionally, photoplethysmography (PPG) using smart devices can detect subtle changes in the colour spectrum induced by blood volume dynamics in facial and fingertip areas, allowing for the estimation of heart rate (HR), blood pressure (BP), respiratory rate (RR), blood oxygen level, blood glucose, and body temperature. This technology, which has been validated in healthy subjects, shows significant potential for application in patients with eating disorders, who are prone to cardiovascular and respiratory issues due to physiological stress and nutritional imbalances. This approach provides essential insights into their physical health status, particularly given the significant impairments in muscle strength often observed in individuals with eating disorders.

In addition to physical health, this study will also examine psychological traits that may improve the accuracy of identifying eating disorder status. This will include questionnaire-based assessments and a computerised task to measure psychological processes. Specifically, the 7-item Generalised Anxiety Disorder Questionnaire (GAD-7) and the 9-item Patient Health Questionnaire (PHQ-9) will assess anxiety and depression severity, respectively, while the Eating Disorder Examination Questionnaire (EDE-Q) will evaluate eating disorder traits, including eating restraint, eating concern, shape concern, and weight concern. Adolescent versions of these questionnaires will be used for younger participants. Moreover, since impulsivity and cognitive control are often altered in individuals with eating disorders, this study will assess these cognitive functions using an adapted Stop Signal Task (SST) that incorporates sensitive cues, such as high-calorie food cues (food-specific SST, FSST). This task will aid in monitoring cognitive control related to the progression of eating disorders and potentially improve the accuracy of health status assessments in these individuals.

This study aims to validate the aforementioned biomarkers and models captured by the smart device and to explore changes in these biomarkers and psychological status across different stages and severities of eating disorders. Data will be collected over 16 weeks from both hospitalised patients and outpatients. Most data, including vital and physical biomarkers, facial information, and self-reported anxiety and depression measures, will be collected weekly, either once or twice a week, with adjustments for those with less frequent visits. Whereas the EDE-Q, the FSST task, and the patient acceptance questionnaire, which assesses patients' acceptance of the data collection procedures, will be conducted three times during the study, in weeks 1, 8, and 16. By conducting this study, the investigators expect to enhance the usability and acceptance of non-invasive monitoring tools, providing valuable insights into the health status of individuals with eating disorders.

• Study Type: Observational
• Enrollment (Estimated): 130

Contacts and Locations

• Study Contact: Name: Richard Andrews, BSc; Phone Number: +441488892853; Email: research@univa.health
• Study Contact Backup: Name: Peter Sheng Yao Hsu, PhD; Email: peter@univa.health

Study Locations

• United Kingdom
  • Liverpool, United Kingdom, L69 3GF
    • Recruiting
    • University of Liverpool
    • Contact: Daniel Joyce, MRCPsych; Phone Number: +441517950139; Email: D.Joyce@liverpool.ac.uk

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Participants will be identified and recruited from child and adult eating disorder hospital wards and specialist secondary care child and adult eating disorder outpatient treatment teams.

Description

Inclusion Criteria:

• All participants must be aged 10 years or older.
• Diagnosed with an eating disorder by a clinician as per the World Health Organization's ICD-10 (F50.0 through F50.9) or ICD-11 (6B80 - 6B85; 6B8Y, 6B8Z) classification
• Must have a minimum once weekly in-person clinic physical assessment as part of their current treatment plan at the start of the study participation
• Fluent in English
• Capable of reading and understanding the information sheets and consent forms to provide written informed consent.
• For participants aged between 10 and 16 years, parental consent is required first before offering the opportunity to the child. A parent or legal guardian must also be able to read and understand the information sheets and consent forms to provide written informed consent on behalf of the child under 16 years of age.

Exclusion Criteria:

• Active substance use such as drug or alcohol misuse

  • For alcohol consumption of more than 21 units of alcohol per week (1 unit is equivalent to half a pint of beer (285ml), 25ml of spirits, or one glass of wine)
  • Diagnostic coding for current mental and behavioural disorders due to substances (ICD10: F10 through F19; ICD11: QE10 through QE1Z and 6C40 through 6C4H)
• A diagnosis of a neurological disorder, including but not limited to cerebrovascular diseases, either currently or in the past or where the eating disorder for which the participant is being treated is considered aetiologically-secondary to a neurological disorder (e.g. pica secondary to a brain injury).
• A diagnosis of schizophrenia or related psychotic disorder.
• Pregnancy.
• A diagnosis of developmental learning disorder (ICD10 F80.0 through F81.9: ICD11: 6A03) or intellectual disorders (ICD10: F70.0 through F79.9; ICD11 6A00).

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Group of eating disorder patients aged above 10; This is a cohort study in which all participants are diagnosed with eating disorders and undertake the same set of assessments and tasks, although the frequency of these assessments and tasks is subject to their current care plan.

Device: UH100; This is a non-interventional pilot study. Given the within-subject and longitudinal design used in this study, traditional intervention settings are not applicable. All participants will receive weekly and tri-point assessments,; Weekly (twice per week) Assessments: Physical vitals such as BMI, Blood Pressure, Heart Rate; Weekly (once per week) Assessments: Sit-Up-Squat-Stand Test, Video diary entries, GAD-7, and PHQ-9.; Tri-point (week 1, 8, 6) assessments: EDE-Q, Patient Acceptance Questionnaire and the Food-specific Stop Signal Task.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Height and Weight - traditional measurement	Height (cm) and weight (kg) will be measured using standard clinical techniques. These two measurements will be used independently or to calculate the body mass index (BMI).	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Height and Weight - PPG estimation and facial analysis	Height (cm) and weight (kg) will be estimated using independent or combined facial and fingertip photoplethysmogram (PPG) technology and facial feature analysis. These facial features will be identified and quantified using machine learning algorithms. These two measurements will be used independently or to calculate the body mass index (BMI).	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Heart Rate - traditional measurement	Heart rate (bpm) will be measured by a sphygmomanometer in both sitting and standing postures.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Heart Rate - PPG estimation	Heart rate (bpm) will be estimated using facial and fingertip photoplethysmogram (PPG) technology in both sitting and standing postures.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Pressure - traditional measurement	Temperature (°C) will be separately measured using a thermometer and estimated using independent or combined facial and fingertip photoplethysmogram (PPG) technology and facial feature analysis. These facial features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Pressure - PPG estimation	Systolic and diastolic blood pressure (mmHg) will be measured using facial and fingertip photoplethysmogram (PPG) technology in both sitting and standing postures.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Respiratory Rate - traditional measurement	Respiratory rate (breaths per minute) will be measured by counting the number per minute manually.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Respiratory Rate - PPG estimation and facial analysis	Respiratory rate (breaths per minute) will be estimated using independent or combined facial and fingertip photoplethysmogram (PPG) technology and facial feature analysis. These facial features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Temperature - traditional measurement	Temperature (°C) will be measured using a thermometer.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Temperature - PPG estimation and facial analysis	Temperature (°C) will be estimated using independent or combined facial and fingertip photoplethysmogram (PPG) technology and facial feature analysis. These facial features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Oxygen Level - traditional measurement	Blood oxygen level (SpO2) will be measured using a saturation meter	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Oxygen Level - PPG estimation and facial analysis	Blood oxygen level (SpO2) will be estimated using independent or combined facial and fingertip photoplethysmogram (PPG) technology and facial feature analysis. These facial features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Glucose Level - traditional measurement	Blood glucose level (mmol/L or mg/dL) will be measured through blood tests.	A maximum of two sessions per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Glucose Level - PPG estimation and facial analysis	Blood glucose level (mmol/L or mg/dL) will be estimated using independent or combined facial and fingertip photoplethysmogram (PPG) technology and facial feature analysis. These facial features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Hydration Level - traditional measurement	Hydration level will be assessed through the number and type of dehydration symptoms.	A maximum of two sessions per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Hydration Level - PPG estimation and facial analysis	Hydration level will be estimated using independent or combined facial and fingertip photoplethysmogram (PPG) technology and facial feature analysis. These facial features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Rating of Skin Conditions - traditional measurement	Skin conditions will be assessed through the number and type of skin conditions.	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Rating of Skin Conditions - PPG estimation and facial analysis	Skin conditions will be estimated using facial feature analysis. These facial features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Sit-Up-Squat-Stand Test - traditional measurement	Participants' core strength, flexibility, and balance will be assessed using the Sit-Up-Squat-Stand Test with a 4-point scale to separately rate Sit-Up and the Squat-Stand performance.	A maximum of two sessions per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Sit-Up-Squat-Stand Test - PPG estimation and facial and body movement analysis	Participants' core strength, flexibility, and balance will be estimated by using independent or combined facial photoplethysmogram (PPG) technology and the analysis of changes in body movements and facial features. These movements and features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Single Anxiety and Depression Questions	Participants' anxiety and depression (mood) status on the day of the assessment session will be evaluated using two single-item questions, each with a 100-point visual analogue scale.	A maximum of two sessions per week, with two tests conducted after each set of readings, will be carried out from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
The Size of The Parotid Glands - traditional measurement	The size of the parotid glands will be assessed by clinicians or professionals to determine if it is normal.	A maximum of two sessions per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
The Size of The Parotid Glands - PPG estimation and facial and body movement analysis	The size of the parotid glands will be estimated using facial feature analysis. These facial features will be identified and quantified using machine learning algorithms.	A maximum of two sessions per week, with two readings per session, will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (full blood count)	The blood test is used to assess electrolyte balance, including the result of full blood count.	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (Haemoglobin)	The blood test is used to assess electrolyte balance, including the result of Haemoglobin (g/dL or g/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (Platelets)	The blood test is used to assess electrolyte balance, including the result of Platelets (10^3/μL or 10^9/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (white cell counts)	The blood test is used to assess electrolyte balance, including the result of white cell counts (10^3/μL or 10^9/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (potassium (K+))	The blood test is used to assess electrolyte balance, including the result of potassium (K+) (mEq/L or mmol/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (sodium (Na+))	The blood test is used to assess electrolyte balance, including the result of sodium (Na+) (mEq/L or mmol/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (magnesium (Mg++))	The blood test is used to assess electrolyte balance, including the result of magnesium (Mg++) (mEq/L, mg/dL, or mmol/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (phosphorous (PO4))	The blood test is used to assess electrolyte balance, including the result of phosphorous (PO4) (mEq/L, mg/dL, or mmol/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (urea)	The blood test is used to assess electrolyte balance, including the result of urea (mEq/L, mg/dL, or mmol/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (creatine kinase)	The blood test is used to assess electrolyte balance, including the result of creatine kinase (U/L or µkat/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (albumin)	The blood test is used to assess electrolyte balance, including the result of albumin (g/dL).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (alkaline phosphatase (ALP))	The blood test is used to assess electrolyte balance, including the result of alkaline phosphatase (ALP) (U/L or µkat/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (aspartate transaminase (AST))	The blood test is used to assess electrolyte balance, including the result of aspartate transaminase (AST) (U/L or µkat/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (alanine transaminase (ALT))	The blood test is used to assess electrolyte balance, including the result of alanine transaminase (ALT) (U/L or µkat/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (gamma-glutamyl transferase (GGT))	The blood test is used to assess electrolyte balance, including the result of gamma-glutamyl transferase (GGT) (U/L or µkat/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (bilirubin)	The blood test is used to assess electrolyte balance, including the result of bilirubin (mg/dL or μmol/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Blood Tests (glucose)	The blood test is used to assess electrolyte balance, including the result of glucose (mg/dL or mmol/L).	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Video Diary Entry	When participants are asked to record their thoughts on diary questions, changes in their aforementioned facial PPG-related biomarkers, facial features, and voice patterns, along with their qualitative responses, will be recorded and analysed. The facial features and voice patterns will be identified and quantified using machine learning algorithms.	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Image Response Task	When participants are asked to record their thoughts on high-calorie food, low-calorie food, neutral, and positive images, changes in their aforementioned facial PPG-related biomarkers, facial features, and voice patterns, along with their qualitative responses, will be recorded and analysed. The facial features and voice patterns will be identified and quantified using machine learning algorithms.	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
Generalised Anxiety Disorder (GAD-7) and Patient Health (PHQ-9) Questionnaires	Participants' overall anxiety and depression levels will be assessed using the 7-item GAD-7 and the 9-item PHQ-9, respectively. Both scales are rated on a 4-point scale from 0 to 3. Adolescents will use the adolescent version of the PHQ-9 (PHQ-A), which employs the same scaling and scoring system, allowing for direct comparison with adults.	A maximum of one session per week will be conducted from week 1 to week 16. The frequency may be adjusted to align with participants' clinical visits, but the maximum duration will remain 16 weeks.
The Eating Disorder Examination Questionnaire (EDE-Q)	Participants' eating disorder traits, including eating restraint, eating concern, weight concern, and shape concern, along with qualitative responses regarding the frequency of eating disorder behaviours, will be assessed using the 28-item EDE-Q. This questionnaire is rated on a 7-point scale from 0 to 6. Adolescents will use the adolescent version of the EDE-Q (EDE-A). While this adolescent version contains 36 items, 28 of them capture the same domains as the adult version.	Three times throughout the study: in Weeks 1, 8, and 16-or-at early discharge, or when care plans change and no further visits to clinical sites are scheduled before Week 16.
The Food-specific Stop Signal Task	Three variables are generated by this task to assess participants' inhibitory control related to food. These variables include stop signal reaction time (SSRT), go reaction time (GORT), and the proportion of successful stops or error rates. SSRT, measured in milliseconds, assesses the latency of inhibition and reflects an individual's ability to suppress an automatic response. GORT, also measured in milliseconds, evaluates the speed of responses to go signals, providing insight into baseline response times and overall task performance. The proportion of successful stops or error rates indicates the percentage of trials where participants successfully inhibit their responses.	Three times throughout the study: in Weeks 1, 8, and 16-or-at early discharge, or when care plans change and no further visits to clinical sites are scheduled before Week 16.
Patient Acceptance Questionnaire	Participants' comfort with conducting the procedures of this study, such as recording their faces, will be assessed using an 8-item self-developed questionnaire with a 6-point rating scale, such as from 'Very comfortable' to 'Very uncomfortable'.	Three times throughout the study: in Weeks 1, 8, and 16-or-at early discharge, or when care plans change and no further visits to clinical sites are scheduled before Week 16.

Collaborators and Investigators

• Sponsor: Univa Health
• Investigators: Principal Investigator: Daniel Joyce, MRCPsych, University of Liverpool

Publications and helpful links

General Publications

• Kroenke K, Spitzer RL, Williams JB. The PHQ-9: validity of a brief depression severity measure. J Gen Intern Med. 2001 Sep;16(9):606-13. doi: 10.1046/j.1525-1497.2001.016009606.x.
• Spitzer RL, Kroenke K, Williams JB, Lowe B. A brief measure for assessing generalized anxiety disorder: the GAD-7. Arch Intern Med. 2006 May 22;166(10):1092-7. doi: 10.1001/archinte.166.10.1092.
• Arcelus J, Mitchell AJ, Wales J, Nielsen S. Mortality rates in patients with anorexia nervosa and other eating disorders. A meta-analysis of 36 studies. Arch Gen Psychiatry. 2011 Jul;68(7):724-31. doi: 10.1001/archgenpsychiatry.2011.74.
• Low DM, Bentley KH, Ghosh SS. Automated assessment of psychiatric disorders using speech: A systematic review. Laryngoscope Investig Otolaryngol. 2020 Jan 31;5(1):96-116. doi: 10.1002/lio2.354. eCollection 2020 Feb.
• Verkruysse W, Svaasand LO, Nelson JS. Remote plethysmographic imaging using ambient light. Opt Express. 2008 Dec 22;16(26):21434-45. doi: 10.1364/oe.16.021434.
• Fagherazzi G, Fischer A, Ismael M, Despotovic V. Voice for Health: The Use of Vocal Biomarkers from Research to Clinical Practice. Digit Biomark. 2021 Apr 16;5(1):78-88. doi: 10.1159/000515346. eCollection 2021 Jan-Apr.
• Rose JS, Vaewsorn A, Rosselli-Navarra F, Wilson GT, Weissman RS. Test-retest reliability of the eating disorder examination-questionnaire (EDE-Q) in a college sample. J Eat Disord. 2013 Nov 20;1:42. doi: 10.1186/2050-2974-1-42. eCollection 2013.
• Pham C, Poorzargar K, Nagappa M, Saripella A, Parotto M, Englesakis M, Lee K, Chung F. Effectiveness of consumer-grade contactless vital signs monitors: a systematic review and meta-analysis. J Clin Monit Comput. 2022 Feb;36(1):41-54. doi: 10.1007/s10877-021-00734-9. Epub 2021 Jul 9.
• Johnson JG, Cohen P, Kasen S, Brook JS. Eating disorders during adolescence and the risk for physical and mental disorders during early adulthood. Arch Gen Psychiatry. 2002 Jun;59(6):545-52. doi: 10.1001/archpsyc.59.6.545.
• Engel SG, Adair CE, Las Hayas C, Abraham S. Health-related quality of life and eating disorders: a review and update. Int J Eat Disord. 2009 Mar;42(2):179-87. doi: 10.1002/eat.20602.
• The Hearts Minds and Genes Coalition (2021). The Cost of Eating Disorders in the UK 2019 and 2020. The Hearts Minds and Genes Coalition. https://www.yumpu.com/en/document/view/65877873/the-cost-of-eating-disorders-in-the-uk-2019-and-2020-with-annex
• Jenkins PE. Cost-of-illness for non-underweight binge-eating disorders. Eat Weight Disord. 2022 May;27(4):1377-1384. doi: 10.1007/s40519-021-01277-3. Epub 2021 Jul 30.
• The Royal College of Psychiatrists (2023). Medical Emergencies in Eating Disorders: Guidance on Recognition and Management. The Royal College of Psychiatrists. https://www.rcpsych.ac.uk/docs/default-source/improving-care/better-mh-policy/college-reports/college-report-cr233-medical-emergencies-in-eating-disorders-(meed)-guidance.pdf?sfvrsn=2d327483_63
• Eating disorders: recognition and treatment. London: National Institute for Health and Care Excellence (NICE); 2020 Dec 16. Available from http://www.ncbi.nlm.nih.gov/books/NBK568394/
• NHS England (2021). Hospital admissions for eating disorders. NHS England. https://digital.nhs.uk/supplementary-information/2021/hospital-admissions-for-eating-disorders-2015-2021
• Dantcheva, A., Bremond, F., & Bilinski, P. (2018). Show me your face and I will tell you your height, weight and body mass index. In 2018 24th International Conference on Pattern Recognition (ICPR) (pp. 3555-3560). IEEE.
• Pascali MA, Giorgi D, Bastiani L, Buzzigoli E, Henriquez P, Matuszewski BJ, Morales MA, Colantonio S. Face morphology: Can it tell us something about body weight and fat? Comput Biol Med. 2016 Sep 1;76:238-49. doi: 10.1016/j.compbiomed.2016.06.006. Epub 2016 Jun 14.
• Hasan S, Ahmed S, Panigrahi R, Chaudhary P, Vyas V, Saeed S. Oral cavity and eating disorders: An insight to holistic health. J Family Med Prim Care. 2020 Aug 25;9(8):3890-3897. doi: 10.4103/jfmpc.jfmpc_608_20. eCollection 2020 Aug.
• Bozzato A, Burger P, Zenk J, Uter W, Iro H. Salivary gland biometry in female patients with eating disorders. Eur Arch Otorhinolaryngol. 2008 Sep;265(9):1095-102. doi: 10.1007/s00405-008-0598-8. Epub 2008 Feb 6.
• Colella G, Lo Giudice G, De Luca R, Troiano A, Lo Faro C, Santillo V, Tartaro G. Interventional sialendoscopy in parotidomegaly related to eating disorders. J Eat Disord. 2021 Feb 17;9(1):25. doi: 10.1186/s40337-021-00378-9.
• Opladen V, Tanck JA, Baur J, Hartmann AS, Svaldi J, Vocks S. Body exposure and vocal analysis: validation of fundamental frequency as a correlate of emotional arousal and valence. Front Psychiatry. 2023 May 24;14:1087548. doi: 10.3389/fpsyt.2023.1087548. eCollection 2023.
• Despotovic, V., Elbeji, A., Fuenfgeld, K., Pizzimenti, M., Ayadi, H., Nazarov, P. V., & Fagherazzi, G. (2023). Digital Voice-Based Biomarker for Monitoring Respiratory Quality of Life: Findings from the Colive Voice Study. medRxiv, 2023-11.
• Tracey B, Patel S, Zhang Y, Chappie K, Volfson D, Parisi F, Adans-Dester C, Bertacchi F, Bonato P, Wacnik P. Voice Biomarkers of Recovery From Acute Respiratory Illness. IEEE J Biomed Health Inform. 2022 Jun;26(6):2787-2795. doi: 10.1109/JBHI.2021.3137050. Epub 2022 Jun 3.
• Mather JD, Hayes LD, Mair JL, Sculthorpe NF. Validity of resting heart rate derived from contact-based smartphone photoplethysmography compared with electrocardiography: a scoping review and checklist for optimal acquisition and reporting. Front Digit Health. 2024 Feb 29;6:1326511. doi: 10.3389/fdgth.2024.1326511. eCollection 2024.
• Winston, A. P. (2008). Management of physical aspects and complications of eating disorders. Psychiatry, 7(4), 174-178.
• Wood, D., & Knight, C. (2015). Anorexia nervosa in adolescence. Paediatrics and Child Health, 25(9), 428-432.
• Haugg F, Elgendi M, Menon C. Effectiveness of Remote PPG Construction Methods: A Preliminary Analysis. Bioengineering (Basel). 2022 Sep 20;9(10):485. doi: 10.3390/bioengineering9100485.
• Kumar M, Veeraraghavan A, Sabharwal A. DistancePPG: Robust non-contact vital signs monitoring using a camera. Biomed Opt Express. 2015 Apr 6;6(5):1565-88. doi: 10.1364/BOE.6.001565. eCollection 2015 May 1.
• El Ghoch M, Soave F, Calugi S, Dalle Grave R. Eating disorders, physical fitness and sport performance: a systematic review. Nutrients. 2013 Dec 16;5(12):5140-60. doi: 10.3390/nu5125140.
• Lavender, J. M., & Mitchell, J. E. (2015). Eating disorders and their relationship to impulsivity. Current Treatment Options in Psychiatry, 2, 394-401.
• Claes L, Nederkoorn C, Vandereycken W, Guerrieri R, Vertommen H. Impulsiveness and lack of inhibitory control in eating disorders. Eat Behav. 2006 Aug;7(3):196-203. doi: 10.1016/j.eatbeh.2006.05.001. Epub 2006 Jun 21.
• Logan, G. D., & Burkell, J. (1986). Dependence and independence in responding to double stimulation: A comparison of stop, change, and dual-task paradigms. Journal of Experimental Psychology: Human Perception and Performance, 12(4), 549.
• Svaldi J, Naumann E, Trentowska M, Schmitz F. General and food-specific inhibitory deficits in binge eating disorder. Int J Eat Disord. 2014 Jul;47(5):534-42. doi: 10.1002/eat.22260. Epub 2014 Feb 26.
• Weinbach N, Lock J, Bohon C. Superior response inhibition to high-calorie foods in adolescents with anorexia nervosa. Behav Res Ther. 2020 Jan;124:103441. doi: 10.1016/j.brat.2019.103441. Epub 2019 Jul 22.
• World Health Organization. (2022). ICD-11: International classification of diseases (11th revision). https://icd.who.int/
• Prabha, A., Yadav, J., Rani, A., & Singh, V. (2022). Intelligent estimation of blood glucose level using wristband PPG signal and physiological parameters. Biomedical Signal Processing and Control, 78, 103876.
• Shuzan MNI, Chowdhury MH, Chowdhury MEH, Murugappan M, Hoque Bhuiyan E, Arslane Ayari M, Khandakar A. Machine Learning-Based Respiration Rate and Blood Oxygen Saturation Estimation Using Photoplethysmogram Signals. Bioengineering (Basel). 2023 Jan 28;10(2):167. doi: 10.3390/bioengineering10020167.
• Mond JM, Hay PJ, Rodgers B, Owen C, Beumont PJ. Validity of the Eating Disorder Examination Questionnaire (EDE-Q) in screening for eating disorders in community samples. Behav Res Ther. 2004 May;42(5):551-67. doi: 10.1016/S0005-7967(03)00161-X.
• Li, B., Zhang, P., Peng, J., & Fu, H. (2023). Non-contact PPG signal and heart rate estimation with multi-hierarchical convolutional network. Pattern Recognition, 139, 109421.
• Lin WH, Li X, Li Y, Li G, Chen F. Investigating the physiological mechanisms of the photoplethysmogram features for blood pressure estimation. Physiol Meas. 2020 May 7;41(4):044003. doi: 10.1088/1361-6579/ab7d78.
• Rizk M, Mattar L, Kern L, Berthoz S, Duclos J, Viltart O, Godart N. Physical Activity in Eating Disorders: A Systematic Review. Nutrients. 2020 Jan 9;12(1):183. doi: 10.3390/nu12010183.

Study record dates

Study Major Dates

• Study Start (Actual): November 1, 2024
• Primary Completion (Estimated): April 1, 2025
• Study Completion (Estimated): September 1, 2025

Study Registration Dates

• First Submitted: July 16, 2024
• First Submitted That Met QC Criteria: August 5, 2024
• First Posted (Actual): August 9, 2024

Study Record Updates

• Last Update Posted (Estimated): December 6, 2024
• Last Update Submitted That Met QC Criteria: December 3, 2024
• Last Verified: December 1, 2024

More Information

Terms related to this study

• Keywords: Biomarkers; Photoplethysmography; Eating Disorders; Vital Signs; Physical Signs
• Additional Relevant MeSH Terms: Mental Disorders; Feeding and Eating Disorders
• Other Study ID Numbers: ST001

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No