Continuous body temperature as a window into adolescent development

Grant, Azure D.; Kriegsfeld, Lance J.

doi:10.1016/j.dcn.2023.101221

Cited by 2 publications

(6 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our model was formalized as a non-linear approximator F : Y k = F ( T k , θ) + δ. Given the input sequence of daily temperatures, T k = { T k −1 , T k −2 , T k −3 … T 1 } starting from the k th day of gestation where T k is a sequence of aggregate 5-minute temperatures for that day, our model is represented by a set of trainable parameters θ, and predicts a value Y k that indicates number of days until labor relative to current gestational age k . δ represents the parameters of regularization employed to avoid model over-fitting.…”

Section: Methodsmentioning

confidence: 99%

“…Pre-Processing and Cleaning: data ingestion (A) and pre-processing pipelines (B). A): De-identified biomarker data from Ouraring, including high fidelity temperature and IBI are ingested into a campus secure Amazon Web Services (AWS) S3 bucket indicated by (1). Data is then parsed to generate structured schema, table meta-data in AWS glue, and participant partitions (to accelerate querying of per minute temperature data).…”

Section: Supplemental Figuresmentioning

confidence: 99%

“…Body temperature reflects female mammalian reproductive status from adolescence 1 through adult fertility 2–4 and menopause. 3,5 Body temperature monitoring is also of increasing interest in human pregnancy, 6 as temperature change predicts parturition in a variety of species 7–10 ( Table 1 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Model Using Continuous Skin Temperature Data Predicts Labor Onset

Basavaraj,

Grant,

Aras

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Background. Changes in body temperature anticipate labor onset in numerous mammals, yet this concept has not been explored in humans. Methods. We evaluated patterns in continuous skin temperature data in 91 pregnant women using a wearable smart ring. Additionally, we collected daily steroid hormone samples leading up to labor in a subset of 28 pregnancies and analyzed relationships among hormones and body temperature trajectory. Finally, we developed a novel autoencoder long-short-term-memory (AE LSTM) deep learning model to provide a daily estimation of days until labor onset. Results. Features of temperature change leading up to labor were associated with urinary hormones and labor type. Spontaneous labors exhibited greater estriol to a pregnanediol ratio, as well as lower body temperature and more stable circadian rhythms compared to pregnancies that did not undergo spontaneous labor. Skin temperature data from 54 pregnancies that underwent spontaneous labor between 34 and 42 weeks of gestation were included in training the AE LSTM model, and an additional 40 pregnancies that underwent artificial induction of labor or Cesarean without labor were used for further testing. The model was trained only on aggregate 5 minute skin temperature data starting at a gestational age of 240 until labor onset. During cross-validation AE LSTM average error (true minus predicted) dropped below 2 days at 8 days before labor, independent of gestational age. Labor onset windows were calculated from the AE-LSTM output using a probabilistic distribution of model error. For these windows AE LSTM correctly predicted labor start for 79% of the spontaneous labors within a 4.6-day window at 7 days before true labor, and 7.4-day window at 10 days before true labor. Conclusion: Continuous skin temperature reflects progression toward labor and hormonal status during pregnancy. Deep learning using continuous temperature may provide clinically valuable tools for pregnancy care.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Supplemental Figuresmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Model Using Continuous Skin Temperature Data Predicts Labor Onset

Basavaraj,

Grant,

Aras

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The mechanisms underlying these conserved patterns still require investigation, but one hypothesis is hormone levels directly influence body temperature. This is supported by the observation of temperature changes coinciding with the start and cessation of menses in a lifetime, monthly menstrual cycles, and use of daily hormonal contraception [ 7 ]. Emerging around menarche (first menses), females have monthly circadian temperature cycles, with a peak of +0.6°C at ovulation [ 50 ].…”

Section: Introductionmentioning

confidence: 93%

“…This modest difference may be physiologically relevant given that sweating can be induced with a +0.4°C increase in core body temperature [ 6 ], and may warrant reassessment of fever thresholds. Around the mean, body temperature varies significantly and systematically with factors such as age, sex, and time of day [ 2 , 4 , 5 , 7–11 ], the same factors seen to correlate with differences in immune response and disease disparity [ 12–17 ]. Even controlling for this variability, a longitudinal study of over 20 000 patients found a +1°C increase in temperature correlated with 3.5% higher mortality after one year [ 18 ], making the clinical implications of temperature–immune interactions clear.…”

Section: Introductionmentioning

confidence: 99%

Deciphering the relationship between temperature and immunity

Maloney,

Duffy

2024

Discovery Immunology

View full text Add to dashboard Cite

Fever is a hallmark symptom of disease across the animal kingdom. Yet despite the evidence linking temperature fluctuation and immune response, much remains to be discovered about the molecular mechanisms governing these interactions. In patients with rheumatoid arthritis for instance, it is clinically accepted that joint temperature can predict disease progression. But it was only recently demonstrated that the mitochondria of stimulated T cells can rise to an extreme 50°C, potentially indicating a cellular source of these localized “fevers”. A challenge to dissecting these mechanisms is bidirectional interplay between temperature and immunity. Heat shock response is found in virtually all organisms, activating protective pathways when cells are exposed to elevated temperatures. However, the temperature threshold that activates these pathways can vary within the same organism, with human immune cells in particular demonstrating differential sensitivity to heat. Such inter-cellular variation may be clinically relevant given the small but significant temperature differences seen between tissues, ages, and sexes. Greater understanding of how such small temperature perturbations mediate immune responses may provide new explanations for persistent questions in disease such as sex disparity in disease prevalence. Notably, the prevalence and severity of many maladies are rising with climate change, suggesting temperature fluctuations can interact with disease on multiple levels. As global temperatures are rising, and our body temperatures are falling, questions regarding temperature-immune interactions are increasingly critical. Here we review this aspect of environmental interplay to better understand temperature’s role in immune variation and subsequent risk of disease.

show abstract

Continuous body temperature as a window into adolescent development

Cited by 2 publications

References 97 publications

Deep Learning Model Using Continuous Skin Temperature Data Predicts Labor Onset

Deep Learning Model Using Continuous Skin Temperature Data Predicts Labor Onset

Deciphering the relationship between temperature and immunity

Contact Info

Product

Resources

About