Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data
Open accessAbstract
OBJECTIVE: To develop a noninvasive hypoglycemia detection approach using smartwatch data. RESEARCH DESIGN AND METHODS: We prospectively collected data from two wrist-worn wearables (Garmin vivoactive 4S, Empatica E4) and continuous glucose monitoring values in adults with diabetes on insulin treatment. Using these data, we developed a machine learning (ML) approach to detect hypoglycemia (<3.9 mmol/L) noninvasively in unseen individuals and solely based on wearable data. RESULTS: Twenty-two individuals were included in the final analysis (age 54.5 ± 15.2 years, HbA1c 6.9 ± 0.6%, 16 males). Hypoglycemia was detected with an area under the receiver operating characteristic curve of 0.76 ± 0.07 solely based on wearable data. Feature analysis revealed that the ML model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia. CONCLUSIONS: Our approach may allow for noninvasive hypoglycemia detection using wearables in people with diabetes and thus complement existing methods for hypoglycemia detection and warning.
AI snapshot
Written from the paper’s full text.
TL;DR
A prospective single-center study developed a machine learning approach to detect hypoglycemia noninvasively from consumer-grade smartwatch data in adults with diabetes on insulin treatment. The model achieved an AUROC of 0.76 ± 0.07 using wearable data alone, with heart rate, heart rate variability, electrodermal activity, and time as important features.
Key findings
- Hypoglycemia (<3.9 mmol/L) was detected with an AUROC of 0.76 ± 0.07 solely based on wearable data in 19 of 22 participants who were paired during validation.
- Important feature categories were time (33.2% relative importance), cardiac features including heart rate and heart rate variability (32.8%), and electrodermal activity (27.3%); motion was less decisive (6.7%).
- The model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia, consistent with known physiological stress responses.
- Hypoglycemic events occurred most frequently between 2200 and 0200 h in this study.
Methods
- Prospective, single-center study at the University Hospital of Bern from February 2021 to March 2022, including adults with diabetes on multiple daily injection, pump, or hybrid closed-loop insulin therapy without cardiac arrhythmia, antiarrhythmic drugs, pacemaker, or implantable cardioverter defibrillator.
- Participants wore a Garmin vivoactive 4S for heart rate variability, heart rate, motion, and time data and an Empatica E4 for electrodermal activity; they used a Dexcom G6 CGM with daily fasting calibrations, collected data for 30 days with optional extension up to 90 days.
- A decision tree–based ML model used a pairing approach with training, validation, and testing stages; signals were cut into 60-s nonoverlapping sequences, generating 36 interpretable features plus time of day (37 total), with SHAP values used to explain model decisions.
Limitations
- The paper states the restricted sample size, single-center design, and male predominance limit generalizability; further studies are needed to assess different diabetes types, comorbidities such as severe neuropathy, and hypoglycemia unawareness.
- The paper notes additional research is required to determine performance and decision making at various levels of hypoglycemia, and it acknowledges a relatively low frequency of hypoglycemic events compared with other studies, though the absolute number exceeded prespecified sample size calculations.
- Evident from the text: this is a proof-of-concept pilot study, and ML performance is reported for 19 of 22 participants because only 19 were paired during validation.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
2 of 7 cited sources checked · 2 supported · 0 flagged
- Premisecitation
Hypoglycemia causes changes in physiological parameters.
“Hypoglycemia is a frequent and dangerous complication of diabetes (1), causing changes in physiological parameters (2,3).”
Quote in the paperSubstantial claim1 of 2 sources checked- cites [2] Olde Bekkink, 2019, Early detection of hypoglycemia in type 1 diabetes using heart rate variability measured by a wearable device, Diabetes Care source
- cites [3] Koeneman, 2022, Effect of hypoglycemia on heart rate variability in people with type 1 diabetes and impaired awareness of hypoglycemia, J Diabetes Sci Technol source
- Findingown data
Increased tonic electrodermal activity was associated with hypoglycemia in the ML model.
“Feature analysis revealed that the ML model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia.”
- Also stated in: § Results · plain
“For electrodermal activity, the model associated higher feature values, particularly of the tonic component, with hypoglycemia.”
Quote in the paperNot a substantial claim - Also stated in: § Results · plain
- Findingown data
Increased heart rate was associated with hypoglycemia in the ML model.
“Feature analysis revealed that the ML model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia.”
- Also stated in: § Results · plain
“Increased heart rate and decreased heart rate variability were associated with hypoglycemia.”
Quote in the paperSubstantial claim - Also stated in: § Results · plain
- Findingown data
Decreased heart rate variability was associated with hypoglycemia in the ML model.
“Feature analysis revealed that the ML model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia.”
- Also stated in: § Results · plain
“Increased heart rate and decreased heart rate variability were associated with hypoglycemia.”
Quote in the paperSubstantial claim - Also stated in: § Results · plain
- Findingown data
For the detection of hypoglycemia (<3.9 mmol/L), the ML model achieved an AUROC of 0.76 ± 0.07 solely based on wearable data.
“Hypoglycemia was detected with an area under the receiver operating characteristic curve of 0.76 ± 0.07 solely based on wearable data.”
- Also stated in: § Results · plain
“For the detection of hypoglycemia (<3.9 mmol/L), the ML model achieved an AUROC of 0.76 ± 0.07 (Fig. 2A).”
Quote in the paperSubstantial claim- Rests on an assumption: Wearable technology can measure the physiological changes associated with hypoglycemia.
- Also stated in: § Results · plain
- Study design and conductown data
The study prospectively collected data from two wrist-worn wearables and continuous glucose monitoring in adults with diabetes on insulin treatment.
“We prospectively collected data from two wrist-worn wearables (Garmin vivoactive 4S, Empatica E4) and continuous glucose monitoring values in adults with diabetes on insulin treatment.”
Quote in the paperSubstantial claim - Study design and conductown data
Of 31 included participants, 22 had two or more hypoglycemic events covered by both wearables and were included in the final analysis.
“Of 31 included participants wearing both wearables, 22 had two or more hypoglycemic events covered by both wearables and were included in the final analysis (age 54.5 ± 15.2 years, HbA1c 6.9 ± 0.6%, 16 male) (Fig. 1B and Table 1).”
Quote in the paperSubstantial claim - Interpretationcitation
Our approach uses consumer-grade smartwatches without additional inputs (e.g., insulin, meals), unlike previously proposed approaches detecting hypoglycemia from wearables.
“In contrast to previously proposed approaches detecting hypoglycemia from wearables (9–11), our approach uses consumer-grade smartwatches without additional inputs (e.g., insulin, meals), increasing usability.”
Quote in the paperSubstantial claim0 of 3 sources checked- cites [9] Ranvier, 2016, Detection of hypoglycemic events through wearable sensors
- cites [10] Dave, Detection of hypoglycemia and hyperglycemia using noninvasive wearable sensors: ECG and accelerometry, J Diabetes Sci Technol
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- cites [11] San, 2016, Deep learning framework for detection of hypoglycemic episodes in children with type 1 diabetes, Annu Int Conf IEEE Eng Med Biol Soc source
- Interpretationown data
Hypoglycemia can be detected noninvasively based on consumer-grade wearable data using ML.
“To conclude, we provide pilot results showing that hypoglycemia can be detected noninvasively based on consumer-grade wearable data using ML.”
Quote in the paperSubstantial claim- Rests on an assumption: Wearable technology can measure the physiological changes associated with hypoglycemia.
- Interpretationown data
The ML approach showed adequate performance in detecting hypoglycemia noninvasively from wearable data.
“First, our ML approach showed adequate performance in detecting hypoglycemia noninvasively from wearable data.”
Quote in the paperSubstantial claim- Rests on an assumption: Wearable technology can measure the physiological changes associated with hypoglycemia.
- Interpretationreasoning
The ML model is based on data retrieved from unobtrusive consumer-grade devices, rendering our approach scalable.
“Our ML model is based on data retrieved from unobtrusive consumer-grade devices, rendering our approach scalable.”
Quote in the paperSubstantial claim - Interpretationown data
The ML model's associations were consistent with known physiological changes in hypoglycemia.
“Second, the ML model’s associations were consistent with known physiological changes in hypoglycemia.”
Quote in the paperSubstantial claim - Study design and conductown data
The absolute number of hypoglycemic events exceeded the number prespecified in the sample size calculations.
“While we acknowledge the relatively low frequency of hypoglycemic events in our data set compared with other studies (2), the absolute number of hypoglycemic events exceeded the number prespecified in the sample size calculations (Supplementary Methods 1).”
Quote in the paperNot a substantial claim - Interpretationreasoning
The restricted sample size, single-center design, and male predominance limit generalizability of the results to other populations.
“Still, the restricted sample size, the single-center design, and the male predominance limit generalizability of our results to other populations.”
Quote in the paperSubstantial claim
- Classified as probably not a substantial claim. 8
- May combine two claims. 9
- The quote only partly states this claim. 1
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationHypoglycemia is a frequent and dangerous complication of diabetes.
“Hypoglycemia is a frequent and dangerous complication of diabetes (1), causing changes in physiological parameters (2,3).”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [1] Seaquist, 2013, Hypoglycemia and diabetes: a report of a workgroup of the American Diabetes Association and the Endocrine Society, Diabetes Care source
May combine two claims.
Findingown dataThe study gathered 95,632 CGM data points, of which 71.4% were in euglycemia (3.9-10.0 mmol/L), 2.3% in hypoglycemia (<3.9 mmol/L), and 26.3% in hyperglycemia (>10.0 mmol/L).
“We gathered 95,632 CGM data points: 71.4% in euglycemia (3.9–10.0 mmol/L), 2.3% in hypoglycemia (<3.9 mmol/L), and 26.3% in hyperglycemia (>10.0 mmol/L).”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown dataThe relative importance of feature categories for the ML model's decisions was 33.2% for time, 32.8% for cardiac features, 27.3% for electrodermal activity, and 6.7% for motion.
“Important feature categories for the ML model’s decisions were time, cardiac features (including heart rate and heart rate variability) and electrodermal activity with a relative importance of 33.2%, 32.8%, and 27.3%, respectively (Fig. 2B). Motion features were less decisive, with 6.7% relative importance on the model output.”
Quote in the paperNot a substantial claimMay combine two claims. The quote only partly states this claim.
Findingown dataThe final analysis included 22 individuals with diabetes on insulin treatment (age 54.5 ± 15.2 years, HbA1c 6.9 ± 0.6%, 16 male).
“Of 31 included participants wearing both wearables, 22 had two or more hypoglycemic events covered by both wearables and were included in the final analysis (age 54.5 ± 15.2 years, HbA1c 6.9 ± 0.6%, 16 male) (Fig. 1B and Table 1).”
Quote in the paperSubstantial claimMay combine two claims.
Findingown dataMotion decreased in hypoglycemia, but motion features were less impactful on the model output.
“Finally, the motion features were less impactful as indicated by SHAP values closer to 0, but motion decreased in hypoglycemia nonetheless.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Study design and conductreasoningParticipants performed daily fasting calibrations to enhance the accuracy of ground truth.
“Participants were fitted with a CGM system (Dexcom G6) and performed daily fasting calibrations to enhance the accuracy of ground truth.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Study design and conductown dataOf 22 participants, 19 were paired during the validation process, and ML performance is reported for 19 individuals.
“Of 22 participants, 19 were paired during the validation process. Therefore, we report the ML performance, relative importance, and SHAP values for 19 individuals.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Study design and conductown dataTwenty-one of the 22 included individuals participated for 30 days, and 1 participated for 90 days.
“Twenty-one of the 22 included individuals participated for 30 days, and 1 participated for 90 days.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Interpretationown dataThe number of hypoglycemic events recorded despite open-label CGM emphasizes the need for complementary hypoglycemia detection methods.
“Of note, the number of hypoglycemic events recorded in the current study despite the use of open-label CGM emphasizes the need for complementary hypoglycemia detection methods.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim.
Study design and conductnone givenThe study's prospective design using wearable data collected in real-life conditions in individuals with different diabetes types is a strength.
“The strength of this study is its prospective design using wearable data collected in real-life conditions in individuals with different diabetes types.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S2 (checkable). May combine two claims.
Interpretationown dataOur approach may complement existing methods to detect hypoglycemia, thereby improving self-management and care of people with diabetes.
“Our approach may complement existing methods to detect hypoglycemia, thereby improving self-management and care of people with diabetes.”
Quote in the paperNot a substantial claim- Rests on an assumption: Wearable technology can measure the physiological changes associated with hypoglycemia.
May combine two claims.
Interpretationown dataThe model's associations are consistent with known physiological changes in hypoglycemia, corroborating its robustness.
“The model’s associations are consistent with known physiological changes in hypoglycemia, corroborating its robustness.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationML-based approaches using wearable data could improve hypoglycemia prediction in CGM and closed-loop users, as shown previously.
“In CGM and closed-loop users, ML-based approaches using wearable data could improve hypoglycemia prediction, as shown previously (12).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [12] Cichosz, 2014, A novel algorithm for prediction and detection of hypoglycemia based on continuous glucose monitoring and heart rate variability in patients with type 1 diabetes, J Diabetes Sci Technol source
The paper relies on this without support.
Wearable technology can measure the physiological changes associated with hypoglycemia.
“While wearable technology can measure these changes, machine learning (ML) may be capable of associating them with hypoglycemia.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Prior work was generated from small cohorts (the largest cohort of 70 individuals), raising questions of the generalizability of their findings.
“Second, prior work was generated from small cohorts (the largest cohort of 70 individuals), that raise questions of the generalizability of their findings5,22–32.”
From Sleep and temperature data from wearable devices support noninvasive detection of diabetes mellitus in a large-scale, retrospective analysis (2026) · cites this paper as [27]
The Results table reports 22 participants, and the Conclusions say the restricted sample size limits generalizability. This paper therefore supports the claim as an example of a small-cohort study, but it does not establish that the largest cohort across the cited prior work had 70 individuals. The supplied passages have no page numbers. (LLM, conf=0.87)
Experimental — accuracy not yet measuredFeatures of heart rate, heart rate variability, movement, and electrodermal activity extracted from wearable data have been applied to detect hypoglycemic events in cohorts ranging from 1 to 36 individuals.
“Features of HR, HRV, movement, and electrodermal activity (EDA; a measure of perspiration) extracted from wearable data have been applied to detect hypoglycemic events in cohorts ranging from 1 to 36 individuals5,26–28.”
From Sleep and temperature data from wearable devices support noninvasive detection of diabetes mellitus in a large-scale, retrospective analysis (2026) · cites this paper as [27]
Prior work typically uses less than a day of input.
“First, where prior work typically uses less than a day of input5,22–32, we assess the impact of longitudinal input windows ranging up to multiple weeks and demonstrate improved sensitivity with longer windows (AUROC increases by 0.15 from 1-night to 21-night models, in balanced and imbalanced cohorts).”
From Sleep and temperature data from wearable devices support noninvasive detection of diabetes mellitus in a large-scale, retrospective analysis (2026) · cites this paper as [27]
Prior work chiefly assessed statistical aggregation functions of wearable data streams (primary features), which are nonspecific to the effects of DM within data streams that are constantly fluctuating in natural settings.
“Third, prior work chiefly assessed statistical aggregation functions of wearable data streams (primary features)5,26–32, which are nonspecific to the effects of DM within data streams that are constantly fluctuating in natural settings.”
From Sleep and temperature data from wearable devices support noninvasive detection of diabetes mellitus in a large-scale, retrospective analysis (2026) · cites this paper as [27]
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · see citing works
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623 · see citing works
Battelino, T., Danne, T., Bergenstal, R. M., Amiel, S. A., Beck, R., Biester, T., Bosi, E., Buckingham, B. A., Cefalu, W. T., Close, K. L., et al. (2019) · Diabetes Care · doi:10.2337/dci19-0028 · Cited by 4,032 · cited 1× · see citing works
“9 mmol/L (6), since early detection is clinically most relevant in enabling prompt treatment and preventing progression into more severe hypoglycemia.”
BackgroundSeaquist, E. R., Anderson, J., Childs, B., Cryer, P., Dagogo-Jack, S., Fish, L., Heller, S. R., Rodriguez, H., Rosenzweig, J., & Vigersky, R. (2013) · Diabetes Care · doi:10.2337/dc12-2480 · Cited by 1,389 · cited 1× · see citing works
“Hypoglycemia is a frequent and dangerous complication of diabetes (1), causing changes in physiological parameters (2,3).”
BackgroundCaigny, A. D., Coussement, K., & Bock, K. W. D. (2018) · European Journal of Operational Research · doi:10.1016/j.ejor.2018.02.009 · Cited by 533 · see citing works
Schwartz, N. S., Clutter, W. E., Shah, S. D., & Cryer, P. E. (1987) · Journal of Clinical Investigation · doi:10.1172/jci112884 · Cited by 394 · see citing works
Chico, A., Vidal-Ríos, P., Subirà, M., & Novials, A. (2003) · Diabetes Care · doi:10.2337/diacare.26.4.1153 · Cited by 235 · see citing works
Hepburn, D. A., Deary, I. J., Frier, B. M., Patrick, A. W., Quinn, J. D., & Fisher, B. M. (1991) · Diabetes Care · doi:10.2337/diacare.14.11.949 · Cited by 186 · see citing works
Glycemic Characteristics in Continuously Monitored Patients With Type 1 and Type 2 Diabetes
Bode, B. W., Schwartz, S., Stubbs, H. A., & Block, J. E. (2005) · Diabetes Care · doi:10.2337/diacare.28.10.2361 · Cited by 137 · see citing works
Engineering digital biomarkers of interstitial glucose from noninvasive smartwatches
Bent, B., Cho, P. J., Henriquez, M., Wittmann, A., Thacker, C., Feinglos, M. N., Crowley, M. J., & Dunn, J. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00465-w · Cited by 99 · see citing works
Cichosz, S. L., Frystyk, J., Hejlesen, O. K., Tarnow, L., & Fleischer, J. (2014) · Journal of Diabetes Science and Technology · doi:10.1177/1932296814528838 · Cited by 88 · see citing works
FLIRT: A feature generation toolkit for wearable data
Föll, S., Maritsch, M., Spinola, F., Mishra, V., Barata, F., Kowatsch, T., Fleisch, E., & Wortmann, F. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106461 · Cited by 72 · see citing works
Self-citationOlde Bekkink, M., Koeneman, M., de Galan, B. E., & Bredie, S. J. (2019) · Diabetes Care · doi:10.2337/dc18-1843 · Cited by 58 · see citing works
Deep learning framework for detection of hypoglycemic episodes in children with type 1 diabetes
San, P. P., Ling, S. H., & Nguyen, H. T. (2016) · 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7591483 · Cited by 42 · see citing works
Dave, D., Vyas, K., Branan, K. L., McKay, S. V., DeSalvo, D. J., Gutiérrez‐Osuna, R., Coté, G. L., & Erraguntla, M. (2022) · Journal of Diabetes Science and Technology · doi:10.1177/19322968221116393 · Cited by 40 · see citing works
Koeneman, M., Olde Bekkink, M., Meijel, L. V., Bredie, S., & de Galan, B. (2022) · Journal of Diabetes Science and Technology · doi:10.1177/19322968211007485 · Cited by 11 · see citing works
(2016) · ArODES (HES-SO (https://www.hes-so.ch/)) · Cited by 7 · see citing works
Time and department distribution of hypoglycemia occurrences in hospitalized diabetic patients
Yang, C.-M., Ma, Y., Kang, J. G., Jia, Z., Wang, Y.-Y., Ma, H., & Wang, J. (2015) · International Journal of Nursing Sciences · doi:10.1016/j.ijnss.2015.08.001 · Cited by 4 · see citing works
Dave, D., Vyas, K., Branan, K., et al. (2022) · Sage Journals Data · doi:10.25384/sage.c.6135149 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
The Role of Wearable Devices in Chronic Disease Monitoring and Patient Care: A Comprehensive Review
Jafleh, E. A., Alnaqbi, F. A., Almaeeni, H. A., Faqeeh, S., Alzaabi, M. A., & Al Zaman, K. (2024) · Cureus · doi:10.7759/cureus.68921 · Cited by 125 · see citing works
Mendez, C., Kaykayoglu, C. A., Bähler, T., Künzler, J., Lizoain, A., Rothenbühler, M., Schmidt, M. H., Laimer, M., & Witthauer, L. (2026) · Journal of Diabetes Science and Technology · doi:10.1177/19322968251319800 · Cited by 10 · see citing works
Piersanti, A., Littero, M., Del Giudice, L. L., Marcantoni, I., Burattini, L., Tura, A., & Morettini, M. (2025) · Sensors · doi:10.3390/s25134038 · Cited by 5 · see citing works
Viswanath, V. K., Navaneethan, S., Burks, J. H., Soltani, S., Kasl, P., Hartogensis, W., Dilchert, S., Hecht, F. M., Mason, A. E., Wang, E. J., et al. (2026) · Communications Medicine · doi:10.1038/s43856-026-01501-0
- Authors
- Lehmann, V., Föll, S., Maritsch, M., van Weenen, E., Kraus, M., Lagger, S., Odermatt, K., Albrecht, C., Fleisch, E., Zueger, T., Wortmann, F., & Stettler, C.
- Affiliations
- University of Bern (CH)
- ETH Zurich (CH)
- 2Department of Management, Technology, and Economics, ETH Zurich, Zurich, Switzerland
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- University of St.Gallen (CH)
- Corresponding author
- Stettler, Christoph
- ORCID
- Venue
- Diabetes Care
- Publisher
- American Diabetes Association
- Published
- 2023-02-17
- Volume
- 46
- Issue
- 5
- Pages
- 993-997
- ISSN
- 0149-5992 (ISSN-L)
- 1935-5548
- PMC
- PMC10154647
- OpenAlex
- W4321183071
- Semantic Scholar
- 650788332a8dbbc0af21ac9b9681fe2a4d6ca6f0
- Cited by
- 47
- References
- 19
- Citations by year
- 2026: 13 · 2025: 13 · 2024: 13 · 2023: 8
- FWCI
- 7.86
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Diabetes Care (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (submittedVersion)
- Alexandria (UniSG) (University of St.Gallen) (submittedVersion)
- Funders
- Innosuisse - Schweizerische Agentur für Innovationsförderung (46917.1 IP-LS)
- Topics
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Research
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- hypoglycemia detection, diabetes mellitus, smartwatches, wearable sensors, non-invasive monitoring, insulin-treated diabetes, heart rate, heart rate variability, electrodermal activity, continuous glucose monitoring, machine learning
- MeSH terms
- Adult, Aged, Blood Glucose, Diabetes Mellitus, Type 1, Humans, Hypoglycemia, Hypoglycemic Agents, Insulin, Male, Middle Aged, Blood Glucose Self-Monitoring
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.
Cited sources are checked by gpt-6-sol.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
