AnemiaWEAR-ANEMIANCT07796542
Wearable Device-Based Screening for Anemia Risk
An observational study of Anemia, run by Peking Union Medical College Hospital at 1 site in China.
Trial summary
Anemia is a common condition, but it often goes undiagnosed because confirming it requires a venous blood test. This study looks at whether a commercially available wrist-worn smartwatch can help identify people who may have anemia, without taking blood. Read more about this study
- Who is it for?
- Ages 18 to 80 yearsHealthy volunteers can take part
- Conditions the study is for
- Anemia
- How many people
- 400 participants
- Where
- 1 siteChina
- Study dates
- 5 Sep 2026to 15 Jul 2027
- Phase
- Observational
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 to 80 years
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Study population: Adults aged 18 to 80 years recruited from inpatient wards and outpatient clinics at a single tertiary care hospital in Beijing, China. The population includes both participants with a hospital-confirmed diagnosis of anemia and control participants with hemoglobin within the normal reference range. Anemia is defined according to Chinese sea-level criteria: hemoglobin below 120 g/L in adult men, below 110 g/L in non-pregnant adult women, and below 100 g/L in pregnant women. For participants with anemia, a hemoglobin result obtained within the 3 days and a diagnostic report specifying anemia severity, red blood cell size classification, and anemia type are required. Enrollment targets at least 300 participants with anemia and at least 90 participants with normal hemoglobin. Participants are enrolled consecutively as they present for routine clinical care and meet eligibility criteria.
Who may be able to join
- Age 18 to 80 years, any sex
- Willing to participate and able to provide written informed consent
- Able to comply with wearable device wear, venous blood sampling, and functional assessment (e.g., six-minute walk test)
- For participants with anemia: a hemoglobin test result obtained within 3 days before or after wearable signal acquisition and a hospital diagnostic report, including anemia severity, red blood cell size classification, and anemia type. Anemia is defined according to Chinese sea-level criteria: hemoglobin below 120 g/L in adult men, below 110 g/L in non-pregnant adult women, and below 100 g/L in pregnant women
- For control participants: hemoglobin within the normal reference range -
Who cannot join
- Axillary temperature 37.3°C or higher on the day of data collection or on the preceding day
- Acute exacerbation of a severe comorbid condition (e.g., decompensated heart failure, respiratory failure, acute infection)
- Skin breakdown, rash, deformity, amputation, or any other condition of the upper limb precluding proper wear of the device
- Refusal of, or intolerance to, invasive venous blood sampling
- Concurrent participation in another interventional clinical trial -
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
China1 site
Peking Union Medical College Hospital
Beijing, Beijing Municipality, 100730
Jian Li, Phd, 010-69155027, lijian@pumch.cn
About this study
Anemia is a common condition, but it often goes undiagnosed because confirming it requires a venous blood test. This study looks at whether a commercially available wrist-worn smartwatch can help identify people who may have anemia, without taking blood.
The watch continuously records several types of physiological signals, including photoplethysmography (a light-based measure of blood flow), movement, heart rate, blood oxygen saturation, and heart rate variability. Researchers will use these signals to build a computer model that sorts participants into two groups: likely to have anemia, or unlikely to have anemia.
Read more
About 400 adults between 18 and 80 years of age will take part at one hospital in Beijing, China. Both patients with anemia and people with normal hemoglobin levels will be included. Each participant will wear the watch and also have a standard venous blood test to measure hemoglobin, which serves as the reference for comparison.
Data from the first 250 participants will be used to develop the model. Data from the next 150 participants will be used to test how well the model works in a separate group. The main question is how accurately the watch-based result matches the blood test result.
Read the detailed description
This is a prospective, observational, diagnostic accuracy study conducted at a single tertiary care hospital in Beijing, China. The purpose is to develop and evaluate a deep learning model for non-invasive binary classification of anemia using multimodal physiological signals acquired from a commercially available consumer wrist-worn wearable device.
Study procedures. Participants will be enrolled in two sequential stages. In the first stage, 250 participants will be enrolled for algorithm development and tuning. In the second stage, an additional 150 participants will be enrolled for independent testing of the locked model and for supporting iterative optimization. All participants will undergo wearable signal acquisition and venous blood sampling for hemoglobin measurement, which serves as the reference standard.
Signal acquisition differs by care setting. Hospitalized participants will undergo 24-hour continuous wearable monitoring and paired signal acquisition before and after a six-minute walk test. Outpatient participants will undergo short-duration resting acquisition with the device worn alternately on the left and right wrist. Outpatient participants may undergo up to three additional assessments if they return for routine clinical visits; these visits are opportunistic and recorded as they occur. Hospitalized participants undergo a single acquisition without follow-up.
Reference standard. Anemia is defined according to Chinese sea-level criteria: hemoglobin below 120 g/L in adult men, below 110 g/L in non-pregnant women, and below 100 g/L in pregnant women.
Sample size. The primary endpoint is diagnostic sensitivity. Assuming an expected sensitivity of 70%, an allowable error of 6%, and a confidence level of 95%, at least 225 participants with anemia are required. Allowing for approximately 10% dropout or unusable data, the anemia group is set at 300 or more participants. At least 90 participants with normal hemoglobin will be enrolled to estimate specificity. To support deep learning model training and generalizability assessment, the total target enrollment is 400 participants.
Statistical analysis. Model performance will be reported as sensitivity and specificity. Cross-validation will be used to assess model stability, and an independent test set will be used to assess generalizability.
The wearable device is non-invasive. Study participation does not alter any aspect of the clinical management of participants.
- Conditions
- Anemia
- Keywords
- anemia screening, wearable device, smartwatch, photoplethysmography, non-invasive diagnosis
- Medical subject headings
- Anemia
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
| Study group | Role | What they receive |
|---|---|---|
| Model development cohort | First 250 participants. Wearable multimodal physiological signals and venous hemoglobin measurement are collected in parallel and used for deep learning model development and tuning. | |
| Independent validation cohort | Subsequent 150 participants. Data are used for independent testing of the model and to support iterative optimization. |
What is being measured
The primary outcome is the main question the study is designed to answer.
Sensitivity and specificity of the wearable-based deep learning model for binary anemia classification
Agreement between the model-derived anemia versus non-anemia classification and venous hemoglobin measurement as the reference standard. Venous blood sampling is performed within 3 days before or after wearable signal acquisition.Reported as sensitivity and specificity with 95% confidence intervals in the independent validation cohort.
Measured: Day 1
Secondary outcomes (4)
Model performance stability under 24-hour continuous wear
Sensitivity and specificity of the model using signals acquired during 24-hour continuous wearable monitoring in hospitalized participants.
Measured: Day 1
Effect of red blood cell size classification on model estimation accuracy
Model sensitivity and specificity stratified by red blood cell size category (microcytic, normocytic, macrocytic) based on mean corpuscular volume
Measured: Day 1
Model performance stability under exercise load
Comparison of model classification performance using signals acquired before versus after a six-minute walk test in hospitalized participants.
Measured: Day 1 (immediately before and after the six-minute walk test)
Agreement of classification results between left and right wrist placement
Concordance of the model-derived anemia classification between signals acquired with the device worn on the left wrist and on the right wrist in outpatient participants.
Measured: Day 1
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted1 Sep 2026
- Study start5 Sep 2026 (estimated)
- Primary completion30 Jun 2027 (estimated)
- Study completion15 Jul 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (5)Papers the sponsor has linked to this study.
- Other trials for AnemiaStudies of the same condition, open and under way.
- More trials run by Peking Union Medical College HospitalThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Prospective
- Enrolment
- 400 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Peking Union Medical College Hospital
- Sponsor type
- University, hospital or other
- Collaborators
- Huawei Device Co., Ltd
- Responsible party
- Principal investigator, Chen Miao, Peking Union Medical College Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07796542
- Sponsor's protocol ID
- PUMCH-WEAR-ANEMIA-2026
- Acronym
- WEAR-ANEMIA
- Status last verified
- Aug 2026
- First submitted
- 26 Aug 2026
- Last updated
- 1 Sep 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Individual participant data include continuous multimodal physiological signal recordings that are potentially identifiable and cannot be adequately de-identified. Raw data will therefore not be shared with other researchers. Aggregate study results will be reported in peer-reviewed publications and in a study summary report, without any information that could identify individual participants.
Publications
Zhu J, Sun R, Liu H, Wang T, Cai L, Chen Z, Heng B. A Non-Invasive Hemoglobin Detection Device Based on Multispectral Photoplethysmography. Biosensors (Basel). 2023 Dec 30;14(1):0. doi: 10.3390/bios14010022.
PubMed 38248399Li L, Luo R, Medina A, Rozelle S. THE PREVALENCE OF ANEMIA IN CENTRAL AND EASTERN CHINA: EVIDENCE FROM THE CHINA HEALTH AND NUTRITION SURVEY. Southeast Asian J Trop Med Public Health. 2015 Mar;46(2):306-21.
PubMed 26513934Li M, Hu Y, Mao D, Wang R, Chen J, Li W, Yang X, Piao J, Yang L. Prevalence of Anemia among Chinese Rural Residents. Nutrients. 2017 Feb 24;9(3):192. doi: 10.3390/nu9030192.
PubMed 28245576Liu X, Wang B, Man S, Bao H, Huang Y, Yu C, Lyu J, Wang L, Li L, Liu H. Variations in the Prevalence of Anemia of Varying Severity Among Urban Non-Pregnant Women - China, 2021. China CDC Wkly. 2024 Mar 8;6(10):175-180. doi: 10.46234/ccdcw2024.036.
PubMed 38523814Shwarz M. Burden of anemia in the United States from 1990 to 2019: a systematic analysis of the Global Burden of Disease Study 2019. Front Public Health. 2025 Oct 3;13:1653222. doi: 10.3389/fpubh.2025.1653222. eCollection 2025.
PubMed 41112644
Study at a glance
From the registry record, last updated by the sponsor on 1 Sep 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Wearable Device-Based Screening for Anemia Risk
- ClinicalTrials.gov ID
- NCT07796542
- Acronym / sponsor ID
- WEAR-ANEMIA / PUMCH-WEAR-ANEMIA-2026
- Conditions
- Anemia
- Keywords
- anemia screening, wearable device, smartwatch, photoplethysmography, non-invasive diagnosis
- Study type
- Observational
- Recruitment status
- Not yet recruiting
- Enrolment
- 400 participants (estimated)
- Lead sponsor
- Peking Union Medical College HospitalUniversity, hospital or other
- Collaborators
- Huawei Device Co., Ltd
- Study start
- 5 Sep 2026 (estimated)
- Primary completion
- 30 Jun 2027 (estimated)
- Study completion
- 15 Jul 2027 (estimated)
- First posted
- 1 Sep 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
Anemia is a common condition, but it often goes undiagnosed because confirming it requires a venous blood test. This study looks at whether a commercially available wrist-worn smartwatch can help identify people who may have anemia, without taking blood.
The watch continuously records several types of physiological signals, including photoplethysmography (a light-based measure of blood flow), movement, heart rate, blood oxygen saturation, and heart rate variability. Researchers will use these signals to build a computer model that sorts participants into two groups: likely to have anemia, or unlikely to have anemia.
About 400 adults between 18 and 80 years of age will take part at one hospital in Beijing, China. Both patients with anemia and people with normal hemoglobin levels will be included. Each participant will wear the watch and also have a standard venous blood test to measure hemoglobin, which serves as the reference for comparison.
Data from the first 250 participants will be used to develop the model. Data from the next 150 participants will be used to test how well the model works in a separate group. The main question is how accurately the watch-based result matches the blood test result.
Detailed description
This is a prospective, observational, diagnostic accuracy study conducted at a single tertiary care hospital in Beijing, China. The purpose is to develop and evaluate a deep learning model for non-invasive binary classification of anemia using multimodal physiological signals acquired from a commercially available consumer wrist-worn wearable device.
Study procedures. Participants will be enrolled in two sequential stages. In the first stage, 250 participants will be enrolled for algorithm development and tuning. In the second stage, an additional 150 participants will be enrolled for independent testing of the locked model and for supporting iterative optimization. All participants will undergo wearable signal acquisition and venous blood sampling for hemoglobin measurement, which serves as the reference standard.
Signal acquisition differs by care setting. Hospitalized participants will undergo 24-hour continuous wearable monitoring and paired signal acquisition before and after a six-minute walk test. Outpatient participants will undergo short-duration resting acquisition with the device worn alternately on the left and right wrist. Outpatient participants may undergo up to three additional assessments if they return for routine clinical visits; these visits are opportunistic and recorded as they occur. Hospitalized participants undergo a single acquisition without follow-up.
Reference standard. Anemia is defined according to Chinese sea-level criteria: hemoglobin below 120 g/L in adult men, below 110 g/L in non-pregnant women, and below 100 g/L in pregnant women.
Sample size. The primary endpoint is diagnostic sensitivity. Assuming an expected sensitivity of 70%, an allowable error of 6%, and a confidence level of 95%, at least 225 participants with anemia are required. Allowing for approximately 10% dropout or unusable data, the anemia group is set at 300 or more participants. At least 90 participants with normal hemoglobin will be enrolled to estimate specificity. To support deep learning model training and generalizability assessment, the total target enrollment is 400 participants.
Statistical analysis. Model performance will be reported as sensitivity and specificity. Cross-validation will be used to assess model stability, and an independent test set will be used to assess generalizability.
The wearable device is non-invasive. Study participation does not alter any aspect of the clinical management of participants.
Study design
- Observational model
- Cohort
- Time perspective
- Prospective
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| Model development cohort | – | –First 250 participants. Wearable multimodal physiological signals and venous hemoglobin measurement are collected in parallel and used for deep learning model development and tuning. |
| Independent validation cohort | – | –Subsequent 150 participants. Data are used for independent testing of the model and to support iterative optimization. |
Who may qualify
- Ages
- 18 to 80 years
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
- Study population
- Adults aged 18 to 80 years recruited from inpatient wards and outpatient clinics at a single tertiary care hospital in Beijing, China. The population includes both participants with a hospital-confirmed diagnosis of anemia and control participants with hemoglobin within the normal reference range. Anemia is defined according to Chinese sea-level criteria: hemoglobin below 120 g/L in adult men, below 110 g/L in non-pregnant adult women, and below 100 g/L in pregnant women. For participants with anemia, a hemoglobin result obtained within the 3 days and a diagnostic report specifying anemia severity, red blood cell size classification, and anemia type are required. Enrollment targets at least 300 participants with anemia and at least 90 participants with normal hemoglobin. Participants are enrolled consecutively as they present for routine clinical care and meet eligibility criteria.
Key inclusion criteria (5 listed)
- Age 18 to 80 years, any sex
- Willing to participate and able to provide written informed consent
- Able to comply with wearable device wear, venous blood sampling, and functional assessment (e.g., six-minute walk test)
- For participants with anemia: a hemoglobin test result obtained within 3 days before or after wearable signal acquisition and a hospital diagnostic report, including anemia severity, red blood cell size classification, and anemia type. Anemia is defined according to Chinese sea-level criteria: hemoglobin below 120 g/L in adult men, below 110 g/L in non-pregnant adult women, and below 100 g/L in pregnant women
- For control participants: hemoglobin within the normal reference range -
Key exclusion criteria (5 listed)
- Axillary temperature 37.3°C or higher on the day of data collection or on the preceding day
- Acute exacerbation of a severe comorbid condition (e.g., decompensated heart failure, respiratory failure, acute infection)
- Skin breakdown, rash, deformity, amputation, or any other condition of the upper limb precluding proper wear of the device
- Refusal of, or intolerance to, invasive venous blood sampling
- Concurrent participation in another interventional clinical trial -
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Primary outcome
Sensitivity and specificity of the wearable-based deep learning model for binary anemia classification
Time frame: Day 1
Agreement between the model-derived anemia versus non-anemia classification and venous hemoglobin measurement as the reference standard. Venous blood sampling is performed within 3 days before or after wearable signal acquisition.Reported as sensitivity and specificity with 95% confidence intervals in the independent validation cohort.
4 secondary outcomes
Model performance stability under 24-hour continuous wear
Time frame: Day 1
Effect of red blood cell size classification on model estimation accuracy
Time frame: Day 1
Model performance stability under exercise load
Time frame: Day 1 (immediately before and after the six-minute walk test)
Agreement of classification results between left and right wrist placement
Time frame: Day 1
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 1 Sep 2026.
- Background: PubMed 38248399Zhu J, Sun R, Liu H, Wang T, Cai L, Chen Z, Heng B. A Non-Invasive Hemoglobin Detection Device Based on Multispectral Photoplethysmography. Biosensors (Basel). 2023 Dec 30;14(1):0. doi: 10.3390/bios14010022.
- Background: PubMed 26513934Li L, Luo R, Medina A, Rozelle S. THE PREVALENCE OF ANEMIA IN CENTRAL AND EASTERN CHINA: EVIDENCE FROM THE CHINA HEALTH AND NUTRITION SURVEY. Southeast Asian J Trop Med Public Health. 2015 Mar;46(2):306-21.
- Background: PubMed 28245576Li M, Hu Y, Mao D, Wang R, Chen J, Li W, Yang X, Piao J, Yang L. Prevalence of Anemia among Chinese Rural Residents. Nutrients. 2017 Feb 24;9(3):192. doi: 10.3390/nu9030192.
- Background: PubMed 38523814Liu X, Wang B, Man S, Bao H, Huang Y, Yu C, Lyu J, Wang L, Li L, Liu H. Variations in the Prevalence of Anemia of Varying Severity Among Urban Non-Pregnant Women - China, 2021. China CDC Wkly. 2024 Mar 8;6(10):175-180. doi: 10.46234/ccdcw2024.036.
- Background: PubMed 41112644Shwarz M. Burden of anemia in the United States from 1990 to 2019: a systematic analysis of the Global Burden of Disease Study 2019. Front Public Health. 2025 Oct 3;13:1653222. doi: 10.3389/fpubh.2025.1653222. eCollection 2025.
- Individual participant dataSharing planned: No. Individual participant data include continuous multimodal physiological signal recordings that are potentially identifiable and cannot be adequately de-identified. Raw data will therefore not be shared with other researchers. Aggregate study results will be reported in peer-reviewed publications and in a study summary report, without any information that could identify individual participants.
Related trials for Anemia
Active, not recruitingObservational study
A Prospective, Non-interventional, Observational Study of Presentation, Treatment Patterns and Outcomes in Atypical Hemolytic Uremic Syndrome Patients
Atypical Hemolytic Uremic Syndrome(aHUS)
RecruitingObservational study
Blood Sampling for Research Related to Sickle Cell Disease
Sickle Cell Trait, Sickle Cell Disease
Recruiting
A Long-term Follow-up Study in Participants Who Received CS-101
Beta-Thalassemia
Active, not recruitingPhase 3
A Study Evaluating the Safety, Pharmacokinetics, and Efficacy of Crovalimab Versus Eculizumab in Participants With Paroxysmal Nocturnal Hemoglobinuria (PNH) Currently Treated With Complement Inhibitors
Paroxysmal Nocturnal Hemoglobinuria
RecruitingPhase 1/2
Pacritinib, a Kinase Inhibitor of CSF1R, IRAK1, JAK2, and FLT3, in Adults and Pediatric Participants 12 Years of Age or Older With Myelodysplastic Syndromes or Myelodysplastic/Myeloproliferative Neoplasms
Myelodysplastic Syndromes
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Anemia, run by Peking Union Medical College Hospital at 1 site in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 5 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 1 Sep 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Jian Li, PhD (010-69155027, lijian@pumch.cn), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Sensitivity and specificity of the wearable-based deep learning model for binary anemia classification (time frame: Day 1). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07796542, which also lists 5 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 1 Sep 2026.