The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index; 3 of the 16 sources its claims cite were checked for support.
DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction
Open accessAbstract
We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298). We compare two semi-supervised training methods, semi-supervised sequence learning and heuristic pretraining, and show they outperform hand-engineered biomarkers from the medical literature. We believe our work suggests a new approach to patient risk stratification based on cardiovascular risk scores derived from popular wearables such as Fitbit, Apple Watch, or Android Wear.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
DeepHeart trains a semi-supervised, multi-task LSTM on wearable heart-rate and step-count data from 14,011 participants, detecting diabetes, high cholesterol, high blood pressure, and sleep apnea with c-statistics up to 0.8451. Semi-supervised sequence learning and heuristic pretraining outperform hand-engineered biomarker baselines, though the paper notes confounding, deployment, interpretability, and data-scale challenges.
Key findings
- On 57,675 person-weeks, semi-supervised sequence pretraining achieved c-statistics of 0.7441 for high cholesterol, 0.8086 for high blood pressure, and 0.8298 for sleep apnea; the abstract reports diabetes at 0.8451, while Table 2 lists 0.8451 for the no-pretraining LSTM and 0.7998 for unsupervised pretraining.
- The LSTM without pretraining outperformed baselines on sleep apnea (0.80 vs 0.55–0.66), hypertension (0.80 vs 0.61–0.72), high cholesterol (0.67 vs 0.43–0.60), and diabetes (0.85 vs 0.41–0.79).
- Heuristic pretraining improved high cholesterol (0.71 vs 0.67) but significantly hurt high blood pressure (0.74 vs 0.80); semi-supervised sequence learning improved high cholesterol, high blood pressure, and sleep apnea.
- For hypertension and sleep apnea, unsupervised pretraining yielded a 10x improvement in data-efficiency: nearly the same accuracy with 10% of labeled data as with 100% and no pretraining.
Methods
- Recruited 14,011 Apple Watch app users in partnership with the UCSF Health eHeart Study, collecting 200 million unlabeled sensor measurements; after filtering, 57,675 person-weeks were split into 33,628 training, 18,555 tuning, and 12,790 validation weeks, with disjoint participants across sets.
- Model inputs were multi-channel, multi-timescale tensors for heart rate, step count, and time deltas; architecture used 3 temporal convolution layers followed by 4 bidirectional LSTM layers, with multi-task outputs for high cholesterol, hypertension, sleep apnea, diabetes, and ECG.
- Compared supervised LSTM, heuristic pretraining on heart-rate-variability metrics at 5-second, 30-second, 5-minute, and 30-minute windows, and semi-supervised sequence autoencoder pretraining; baselines used 13 hand-engineered biomarkers and standard ML algorithms, evaluated by c-statistic/AUC on the test set.
Limitations
- The paper states challenges including confounding (e.g., beta blockers affecting heart rate variability), deployment barriers, lack of interpretability in deep learning, and difficulty modeling long time-scale and high-volume data.
- The paper notes high cholesterol has the least direct physiological relationship with heart rate variability and may reflect confounders such as age, sex, or medications; diabetes has scarce labels (1,678 person-weeks).
- Evident from the text: consumer sensors have significant error and variable measurement rates, ambulatory activities like walking, exercise, stress, alcohol, or coffee may confuse simple heuristics, and the results are predictive rather than causal.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
22 Own result · 9 Own interpretation · 8 Sources not found · 3 No full text of the sources · 2 Supported · 2 Own method · 1 Partly supported · 1 No basis given · accuracy not yet measured
Every source the paper cites for this claim was checked and supports it.
In the paper
“Semi-supervised sequence learning has been shown to improve performance when presented with large amounts of unlabeled training data (Dai and Le 2015).”
What the sources say
- Supportedcites Dai and Le 2015 source
The Introduction (p. 1) says that using more unlabeled data in pretraining can improve a subsequent supervised model, citing a Rotten Tomatoes accuracy increase from 79.7% to 83.3%. Section 4.2 (p. 5) also reports lower error when the sequence autoencoder was pretrained on a larger unlabeled dataset. (LLM, conf=0.94)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We compare two semi-supervised training methods, semi-supervised sequence learning and heuristic pretraining, and show they outperform hand-engineered biomarkers from the medical literature.”
- Also stated in: § Introduction · p. 1 · plain
“Then we present experimental results showing that semisupervised deep neural networks achieve higher accuracy in detecting diabetes, sleep apnea, high blood pressure, and high cholesterol than several strong baselines derived from biomarkers in the medical literature.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Introduction · p. 1 · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When the supervised LSTM is initialized with weights from heuristic pretraining, we saw noticeable improvements for high cholesterol (0.71 vs 0.67), neutral results for sleep apnea and diabetes, and a significant loss for high blood pressure (0.74 vs 0.80).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Furthermore, we've shown high accuracy at detecting four common health conditions-diabetes, sleep apnea, hypertension, and high cholesterol-using readily available, off-the-shelf heart rate monitors.”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When the supervised LSTM is initialized with weights from heuristic pretraining, we saw noticeable improvements for high cholesterol (0.71 vs 0.67), neutral results for sleep apnea and diabetes, and a significant loss for high blood pressure (0.74 vs 0.80).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For diabetes and cholesterol, the effect is muted.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We first trained a purely-supervised LSTM without pretraining, which performed significantly better than the baselines on sleep apnea (0.80 vs 0.55-0.66), hypertension (0.80 vs 0.61-0.72), high cholesterol (0.67 vs 0.43-0.60), and diabetes (0.85 vs 0.41-0.79).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We first trained a purely-supervised LSTM without pretraining, which performed significantly better than the baselines on sleep apnea (0.80 vs 0.55-0.66), hypertension (0.80 vs 0.61-0.72), high cholesterol (0.67 vs 0.43-0.60), and diabetes (0.85 vs 0.41-0.79).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For high cholesterol, although the c-statistic is lower, there are high-precision operating points which rule out more than half of the study population.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A model trained only on heart rate timeseries performed significantly worse on diabetes and high blood pressure (decrease of 0.0653 and 0.0721 in AUC, respectively), and the same on sleep apnea and high blood pressure (within the 95% confidence interval), suggesting that heart rate is being interpreted as a response to activity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When the supervised LSTM is initialized with weights from heuristic pretraining, we saw noticeable improvements for high cholesterol (0.71 vs 0.67), neutral results for sleep apnea and diabetes, and a significant loss for high blood pressure (0.74 vs 0.80).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We first trained a purely-supervised LSTM without pretraining, which performed significantly better than the baselines on sleep apnea (0.80 vs 0.55-0.66), hypertension (0.80 vs 0.61-0.72), high cholesterol (0.67 vs 0.43-0.60), and diabetes (0.85 vs 0.41-0.79).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“We recruited 14,011 users of a popular Apple Watch app into an online, IRB-approved study run in partnership with the cardiology department of the University of California, San Francisco (Tison et al. 2017a).”
What the sources say
- Not matchedcites Tison et al. 2017a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainn = 14,011- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We first trained a purely-supervised LSTM without pretraining, which performed significantly better than the baselines on sleep apnea (0.80 vs 0.55-0.66), hypertension (0.80 vs 0.61-0.72), high cholesterol (0.67 vs 0.43-0.60), and diabetes (0.85 vs 0.41-0.79).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“First, we employ a mobile phone application to recruit 14,011 participants from across the world, collecting 200 million unlabeled sensor measurements.”
plainn = 14,011- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The gap is smallest for diabetes, with the least amount of labeled data, suggesting potential benefit from combining hand-engineered features with deep learning.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Diagnoses are derived from validated health surveys collected in partnership with the Health eHeart Study of the University of California, San Francisco.”
What the sources say
- Not matchedcites Tison et al. 2017a
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 0.83 c-statistic at detecting sleep apnea is surprising given that few participants sleep with their watch. This suggests that wearable-derived biomarkers measured during the day capture a distinct signature of sleep apnea.”
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For high cholesterol, the lack of correlation between the number of labels and accuracy of the algorithm likely confirms that high cholesterol is primarily detected through the effect of confounding variables such as age, sex, and medications.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: High cholesterol has the least direct physiological relationship with heart rate variability in the medical literature.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our work builds on top of these previous findings, and is the first to show that heart rate variability changes driven by diabetes can be detected via consumer, off-the-self wearable heart rate sensors.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The training, tuning, and testing sets contained completely disjoint sets of participants.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While we are able to detect high cholesterol with c-statistic of 0.74, it is the lowest performing prediction out of the four disease states, suggesting that much of the correlation may be a reflection of confounding variables such as age, sex, or usage of medications like beta blockers.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: High cholesterol has the least direct physiological relationship with heart rate variability in the medical literature.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For diabetes, this is due to a scarcity of labels (1,678, vs 3,662-9,220 for the other conditions).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“First, the sensors themselves have significant error (Gillinov 2016).”
What the sources say
- Not matchedcites Gillinov 2016
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For example, a person with previouslydiagnosed hypertension may be prescribed beta blockers, which affect heart rate variability, and therefore an algorithm with high prediction accuracy at identifying hypertension may be picking up signals of both the underlying disease and the treatment.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Since these four conditions are highly prevalent, commonly undiagnosed, and reduced HRV is associated with the earliest stages of disease progression (Schroeder et al. 2005; 2003), this suggests a new approach to public health screening using deep learning.”
What the sources say
- Not matchedcites Schroeder et al. 2005; 2003
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
- Probably not a substantial claim. 10
- It may state two separate claims as one. 12
Every source the paper cites for this claim was checked and supports it.
In the paper
“Previous work has applied statistical methods on beat-tobeat variability to detect heart arrhythmias (McManus et al. 2013).”
What the sources say
- Supportedcites McManus et al. 2013 source
The Methods (Approaches to Pulse Waveform Analysis) describe using two statistical techniques on beat-to-beat RR-interval variability to detect an irregular pulse associated with atrial fibrillation. The Discussion reports that the combined application distinguished pulses during AF from those during normal sinus rhythm. (LLM, conf=0.94)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Deep neural networks (LeCun, Bengio, and Hinton 2015) have shown high accuracy at pattern recognition from noisy, complex inputs, including automated detection of diabetic retinopathy from images (Gulshan et al. 2016), skin cancer from mobile phone cameras (Esteva et al. 2017), and the onset of health conditions from electronic medical records (Razavian, Marcus, and Sontag 2016; Lipton et al. 2015”
What the sources say
- Not checked — no full text of the sourcecites LeCun, Bengio, and Hinton 2015 source
- Not checked — no full text of the sourcecites Gulshan et al. 2016 source
- Partly supportedcites Esteva et al. 2017 sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This approach resulted in a significant improvement on high cholesterol, high blood pressure, and sleep apnea.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While we are able to detect high cholesterol with c-statistic of 0.74, it is the lowest performing prediction out of the four disease states, suggesting that much of the correlation may be a reflection of confounding variables such as age, sex, or usage of medications like beta blockers.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“After filtering, there were 57,675 person-weeks of data in total, divided into 33,628 for training, 18,555 for tuning, and 12,790 for validation.”
plainn = 57,675- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For hypertension and sleep apnea, unsupervised pretraining yields a 10x improvement in data-efficiency: the DNN achieves nearly the same accuracy with 10% of labeled data using unsupervised pretraining as it does with 100% of labeled data using no pretraining.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A model using only aggregate step counts achieved an AUC of 0.7011 (diabetes), 0.5811 (sleep apnea), 0.5714 (hbp), and 0.5601 (high cholesterol), suggesting that although overall physical activity plays an important role in predicting the onset of disease, the heart's response to physical activity is a more salient biomarker that can be captured using deep learning.”
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Previous work from the medical community has suggested that diabetes may impact heart rate variability through effects on the autonomic nervous system (Kudat et al. 2006).”
What the sources say
- Not checked — no full text of the sourcecites Kudat et al. 2006 source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Each participant was randomly assigned to either the training, tuning, or testing set.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We've shown that two methods, semi-supervised sequence learning and heuristic pretraining, address a key technical challenge in applying deep learning to medicine: achieving high accuracy with limited labeled data.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Sleep apnea is estimated to affect 22 million people in the US alone, over 80% of whom are undiagnosed (Young et al. 1997).”
What the sources say
- Not checked — no full text of the sourcecites Young et al. 1997 source
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Together, high blood pressure and high cholesterol account for 17.3% of global deaths (Alwan and others 2011), as they are both major risk factors for heart attacks.”
What the sources say
- Not matchedcites Alwan and others 2011
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“45.8% of diabetes cases are undiagnosed (Beagley et al. 2014).”
What the sources say
- Not checked — no full text of the sourcecites Beagley et al. 2014 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A model using only aggregate step counts achieved an AUC of 0.7011 (diabetes), 0.5811 (sleep apnea), 0.5714 (hbp), and 0.5601 (high cholesterol), suggesting that although overall physical activity plays an important role in predicting the onset of disease, the heart's response to physical activity is a more salient biomarker that can be captured using deep learning.”
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“including rich signals like resting heart rate and heart rate variability, which have been shown to correlate with health conditions as diverse as diabetes, sleep apnea, atrial fibrillation, heart failure, sudden cardiac death, and irritable bowel syndrome (Kamath, Watanabe, and Upton 2012).”
What the sources say
- Not matchedcites Kamath, Watanabe, and Upton 2012
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This suggests wearables could be used to focus diagnostic testing on a high-risk subset of the population, leading to cost-effective screening for metabolic syndrome and getting at-risk patients care sooner.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
In the paper
“Since these four conditions are highly prevalent, commonly undiagnosed, and reduced HRV is associated with the earliest stages of disease progression (Schroeder et al. 2005; 2003), this suggests a new approach to public health screening using deep learning.”
What the sources say
- Not matchedcites Schroeder et al. 2005; 2003
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
- Not matched
In the paper
“Statistical models in medicine are typically used for etiology, not just prediction, and cause (disease) and effect (treatment) may be intertwined in subtle ways within medical data sets (Shmueli and others 2010).”
What the sources say
- Not matchedcites Shmueli and others 2010
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
- Not matched
The paper relies on this without support.
No such database exists for wearable data.
“No such database exists for wearable data, and in most hospital systems, recruiting even a hundred patients into a new medical study is labor-intensive and expensive.”
The paper relies on this without support.
Recruiting even a hundred patients into a new medical study is labor-intensive and expensive.
“No such database exists for wearable data, and in most hospital systems, recruiting even a hundred patients into a new medical study is labor-intensive and expensive.”
The paper relies on this without support.
High cholesterol has the least direct physiological relationship with heart rate variability in the medical literature.
“Among all four health conditions, high cholesterol has the least direct physiological relationship with heart rate variability in the medical literature.”
The paper relies on this without support.
Purely supervised deep learning requires many labeled examples.
“However, purely supervised deep learning requires many labeled examples.”
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?
In the citing paper
“Recent advances in deep learning architectures for sequential modelling based upon wearable and mobile sensing have been used for health predictions and recommendations [141].”
From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [141]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“After filtering, there were 57,675 person-weeks of data in total, divided into 33,628 for training, 18,555 for tuning, and 12,790 for validation.”
Reported 57675 · recomputed 64973
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Ablative Analysis of Input Channels · p. 5
“A model trained only on heart rate timeseries performed significantly worse on diabetes and high blood pressure (decrease of 0.0653 and 0.0721 in AUC, respectively)”
§ Ablative Analysis of Input Channels · p. 5
“and the same on sleep apnea and high blood pressure (within the 95% confidence interval)”
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Global status report on noncommunicable diseases 2010.
Alwan, A. (2011) · Cited by 8,494
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
Cited by
Sorted by citations
Smart wearable devices in cardiovascular care: Where we are and how to move forward
Bayoumy, K., Gaber, M., Elshafeey, A., Mhaimeed, O., Dineen, E. H., Marvel, F. A., Martin, S. S., Muse, E. D., Turakhia, M. P., Tarakji, K. G., et al. (2021) · Nature Reviews Cardiology · doi:10.1038/s41569-021-00522-7 · Cited by 829
Wearables and the Medical Revolution
Dunn, J., Runge, R., & Snyder, M. (2018) · Personalized Medicine · doi:10.2217/pme-2018-0044 · Cited by 654
Hong, S., Zhou, Y., Shang, J., Xiao, C., & Sun, J. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103801 · Cited by 510
Digital biomarkers for Alzheimer’s disease: the mobile/wearable devices opportunity
Kourtis, L. C., Regele, O. B., Wright, J. M., & Jones, G. B. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0084-2 · Cited by 476
Multi-Omics Profiling for Health
Babu, M., & Snyder, M. P. (2023) · Molecular & Cellular Proteomics · doi:10.1016/j.mcpro.2023.100561 · Cited by 434
Metadata
- Authors
- Ballinger, B., Hsieh, J., Singh, A., Sohoni, N., Wang, J., Tison, G., Marcus, G., Sanchez, J., Maguire, C., Olgin, J., & Pletcher, M.
- Affiliations
- Stanford Medicine (US)
- University of California, San Francisco (US)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2018-04-26
- Volume
- 32
- Issue
- 1
- Pages
- 2079-2086
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2785925437
- Cited by
- 156
- References
- 40
- Citations by year
- 2026: 10 · 2025: 10 · 2024: 9 · 2023: 23 · 2022: 18 · 2021: 28 · 2020: 27 · 2019: 23 · 2018: 8
- FWCI
- 20.75
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- cardiovascular risk prediction, semi-supervised learning, sequence learning, LSTM, wearable heart rate sensors, diabetes detection, hypercholesterolemia, hypertension, sleep apnea, multi-task learning, risk stratification, pre-training
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.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (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
