1
|
Basavaraj C, Grant AD, Aras SG, Erickson EN. Deep Learning Model Using Continuous Skin Temperature Data Predicts Labor Onset. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.02.25.24303344. [PMID: 38464102 PMCID: PMC10925356 DOI: 10.1101/2024.02.25.24303344] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/12/2024]
Abstract
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 α-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 - 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.
Collapse
Affiliation(s)
- Chinmai Basavaraj
- Department of Computer Science, The University of Arizona, Tucson, AZ, USA
| | | | - Shravan G Aras
- Center for Biomedical Informatics and Biostatistics, The University of Arizona Health Sciences, Tucson, AZ, USA
| | | |
Collapse
|
2
|
Erickson EN, Gotlieb N, Pereira LM, Myatt L, Mosquera-Lopez C, Jacobs PG. Predicting labor onset relative to the estimated date of delivery using smart ring physiological data. NPJ Digit Med 2023; 6:153. [PMID: 37598232 PMCID: PMC10439919 DOI: 10.1038/s41746-023-00902-y] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Accepted: 08/10/2023] [Indexed: 08/21/2023] Open
Abstract
The transition from pregnancy into parturition is physiologically directed by maternal, fetal and placental tissues. We hypothesize that these processes may be reflected in maternal physiological metrics. We enrolled pregnant participants in the third-trimester (n = 118) to study continuously worn smart ring devices monitoring heart rate, heart rate variability, skin temperature, sleep and physical activity from negative temperature coefficient, 3-D accelerometer and infrared photoplethysmography sensors. Weekly surveys assessed labor symptoms, pain, fatigue and mood. We estimated the association between each metric, gestational age, and the likelihood of a participant's labor beginning prior to (versus after) the clinical estimated delivery date (EDD) of 40.0 weeks with mixed effects regression. A boosted random forest was trained on the physiological metrics to predict pregnancies that naturally passed the EDD versus undergoing onset of labor prior to the EDD. Here we report that many raw sleep, activity, pain, fatigue and labor symptom metrics are correlated with gestational age. As gestational age advances, pregnant individuals have lower resting heart rate 0.357 beats/minute/week, 0.84 higher heart rate variability (milliseconds) and shorter durations of physical activity and sleep. Further, random forest predictions determine pregnancies that would pass the EDD with accuracy of 0.71 (area under the receiver operating curve). Self-reported symptoms of labor correlate with increased gestational age and not with the timing of labor (relative to EDD) or onset of spontaneous labor. The use of maternal smart ring-derived physiological data in the third-trimester may improve prediction of the natural duration of pregnancy relative to the EDD.
Collapse
Affiliation(s)
- Elise N Erickson
- College of Nursing / College of Pharmacy, The University of Arizona, Tucson, AZ, USA.
- Midwifery Division, School of Nursing, Oregon Health & Science University, Portland, OR, USA.
| | | | - Leonardo M Pereira
- Department of Obstetrics & Gynecology, School of Medicine, Oregon Health & Science University, Portland, OR, USA
| | - Leslie Myatt
- Department of Obstetrics & Gynecology, School of Medicine, Oregon Health & Science University, Portland, OR, USA
| | - Clara Mosquera-Lopez
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR, USA
| | - Peter G Jacobs
- Artificial Intelligence for Medical Systems (AIMS) Lab, Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR, USA
| |
Collapse
|
3
|
Aoki T, Shibata M, Violin G, Higaki S, Yoshioka K. Detection of foaling using a tail-attached device with a thermistor and tri-axial accelerometer in pregnant mares. PLoS One 2023; 18:e0286807. [PMID: 37267402 DOI: 10.1371/journal.pone.0286807] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2022] [Accepted: 05/23/2023] [Indexed: 06/04/2023] Open
Abstract
It is desirable to attend to the mare at the time of foaling in order to assist fetal delivery and prevent complications. The early detection of the onset of labor is an important issue for the equine industry. The purpose of this study was to examine the applicability of a sensor for foaling detection using the data of surface temperature (ST), roll angle (rotation about the y-axis) and y-axis (long axis of the tail) acceleration which were collected from a multimodal device attached to the ventral tail base of the mare. The data were collected every 3 minutes in 17 pregnant mares. Roll angle differences from the reference values and the mare's posture (standing or recumbent) confirmed by video were compared and associated. Cohen's kappa coefficient was 0.99 when the threshold was set as ± 0.3 radian in roll angle differences. This result clearly showed that the sensor data can accurately distinguish between standing and recumbent postures. The hourly sensor data with a lower ST (LST < 35.5°C), a recumbent posture determined by the roll angle, and tail-raising (TR, decline of 200 mg or more from the reference value in y-axis acceleration) was significantly higher during the last hour prepartum than 2-120 hours before parturition (P < 0.01). The accuracy of foaling detection within one hour was verified using the following three indicators: LST; lying down (LD, change from standing to recumbent posture); and TR. When LST, LD and TR were individually examined, even though all indicators showed that sensitivity was 100%, the precision was 13.1%, 8.1% and 2.8%, respectively. When the data were combined as LST+LD, LST+TR, LD+TR and LST+LD+TR, detection of foaling improved, with precisions of 100%, 32.1%, 56.7% and 100%, respectively. In conclusion, the tail-attached multimodal device examined in this present study is useful for detecting foaling.
Collapse
Affiliation(s)
- Takahiro Aoki
- Department of Veterinary Medicine, Obihiro University of Agriculture and Veterinary Medicine, Obihiro, Hokkaido, Japan
| | - Makoto Shibata
- Department of Veterinary Medicine, Obihiro University of Agriculture and Veterinary Medicine, Obihiro, Hokkaido, Japan
| | - Guilherme Violin
- Department of Veterinary Medicine, Obihiro University of Agriculture and Veterinary Medicine, Obihiro, Hokkaido, Japan
| | - Shogo Higaki
- National Institute of Animal Health, National Agriculture and Food Research Organization, Tsukuba, Ibaraki, Japan
| | - Koji Yoshioka
- Laboratory of Theriogenology, School of Veterinary Medicine, Azabu University, Sagamihara, Kanagawa, Japan
| |
Collapse
|
4
|
Grant AD, Erickson EN. Birth, love, and fear: Physiological networks from pregnancy to parenthood. COMPREHENSIVE PSYCHONEUROENDOCRINOLOGY 2022; 11:100138. [PMID: 35757173 PMCID: PMC9227990 DOI: 10.1016/j.cpnec.2022.100138] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2021] [Revised: 04/21/2022] [Accepted: 04/21/2022] [Indexed: 12/01/2022] Open
Abstract
Pregnancy and childbirth are among the most dramatic physiological and emotional transformations of a lifetime. Despite their central importance to human survival, many gaps remain in our understanding of the temporal progression of and mechanisms underlying the transition to new parenthood. The goal of this paper is to outline the physiological and emotional development of the maternal-infant dyad from late pregnancy to the postpartum period, and to provide a framework to investigate this development using non-invasive timeseries. We focus on the interaction among neuroendocrine, emotional, and autonomic outputs in the context of late pregnancy, parturition, and post-partum. We then propose that coupled dynamics in these outputs can be leveraged to map both physiologic and pathologic pregnancy, parturition, and parenthood. This approach could address gaps in our knowledge and enable early detection or prediction of problems, with both personalized depth and broad population scale. Giving birth and caring for offspring are dynamic processes that can instill both love and fear. Maternal physiology continuously integrates fetal, social, and environmental cues. The result is coupled change in hormonal, autonomic nervous, and emotional output. Coupling may allow internal state to be assessed from peripheral autonomic markers. Such markers may identify healthy or pathologic pregnancy, parturition, and parenting, and enable creation of real-world tools.
Collapse
|
5
|
Garcia Kako Rodriguez M, Correia Santos VJ, Ramirez Uscategui RA, Gomes Mariano RS, Rodrigues Simões AP, Del Aguila da Silva P, Maronezi MC, Padilha-Nakaghi LC, Lopes Avante M, M Bartlewski P, Rossi Feliciano MA. Maternal and fetal ultrasonographic characteristics, vulvar temperature, and vaginal mucous impedance as variables associated with the onset of parturition in term and induced pre-term ewes. Anim Reprod Sci 2020; 223:106647. [PMID: 33220617 DOI: 10.1016/j.anireprosci.2020.106647] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2020] [Revised: 10/27/2020] [Accepted: 10/28/2020] [Indexed: 11/28/2022]
Abstract
The aim of this study was to assess and compare ultrasonographic characteristics of maternal and fetal structures, vulvar temperatures, and vaginal mucous impedance in pregnant ewes in the term parturition group (TPG, n = 15) and induced pre-term parturition group (IPPG; n = 15). All the measurements were taken every 12 h throughout the last gestational week. Maternal and fetal structures and the fetal heart rate (HR) were assessed using ultrasonography. The vulvar temperature and vaginal mucous impedance were determined using a non-contact infrared thermometer, and an electronic estrous detector, respectively. The vulvar temperature was less in the TPG and greater in the IPPG; the end-diastolic velocities (EDVs) of the arteries of the placentome and uterus gradually increased before parturition in the IPPG (P = 0.02, P = 0.02 and P = 0.009, respectively). The placentome shear wave velocity (SWV) was greater in the ewes of the IPPG than TPG 48, 36, and 0 h before parturition (P = 0.001). The following variables were associated with the onset of parturition within the next 12 h in the ewes of the IPPG: resistance index (< 0.54) and EDV (> 0.34 cm/s) of the uterine artery; and vulvar temperature (> 37.3 °C). A fetal kidney SWV of < 1.31 m/s was associated with the onset of parturition in the next 12 h in all the ewes. Results indicate vulvar temperature and certain maternal and fetal factors detected using ultrasonograpy may aid in determining fetal maturity and/or the time of parturition in ewes.
Collapse
Affiliation(s)
- Mariana Garcia Kako Rodriguez
- Department of Animal Reproduction, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil.
| | - Victor José Correia Santos
- Department of Animal Reproduction, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil.
| | - Ricardo Andres Ramirez Uscategui
- Institute of Agricultural Sciences, Universidade Federal dos Vales do Jequitinhonha e Mucuri (UFVJM), 38610-000, Unaí, Minas Gerais, Brazil.
| | - Renata Sitta Gomes Mariano
- Department of Animal Reproduction, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil.
| | - Ana Paula Rodrigues Simões
- Department of Animal Reproduction, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil.
| | - Priscila Del Aguila da Silva
- Department of Animal Reproduction, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil.
| | - Marjury Cristina Maronezi
- Department of Veterinary Surgery, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil.
| | - Luciana Cristina Padilha-Nakaghi
- Department of Animal Reproduction, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil.
| | - Michele Lopes Avante
- Department of Veterinary Surgery, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil.
| | - Pawel M Bartlewski
- Department of Biomedical Sciences, Ontario Veterinary College, University of Guelph, N1G 2W1, Guelph, Ontario, Canada.
| | - Marcus Antônio Rossi Feliciano
- Department of Animal Reproduction, Faculdade de Ciências Agrárias e Veterinárias, Univ. Estadual Paulista "Júlio de Mesquita Filho" (FCAV/UNESP), 14884-900, Jaboticabal, São Paulo, Brazil; Department of Large Animals Clinic and Surgery, Universidade Federal de Santa Maria (UFSM), 97105-900, Santa Maria, Rio Grande do Sul, Brazil.
| |
Collapse
|
6
|
Abecia JA, María GA, Estévez-Moreno LX, Miranda-De La Lama GC. Daily rhythms of body temperature around lambing in sheep measured non-invasively. BIOL RHYTHM RES 2019. [DOI: 10.1080/09291016.2019.1592352] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
Affiliation(s)
- José A. Abecia
- Facultad de Veterinaria, Instituto Universitario de Investigación en Ciencias Ambientales de Aragón (IUCA), Universidad de Zaragoza, Zaragoza, Spain
| | - Gustavo A. María
- Facultad de Veterinaria, Instituto Agroalimentario de Aragón (IA2), Universidad de Zaragoza-CITA, Zaragoza, Spain
| | - Laura X Estévez-Moreno
- Facultad de Veterinaria, Instituto Agroalimentario de Aragón (IA2), Universidad de Zaragoza-CITA, Zaragoza, Spain
| | - Genaro C. Miranda-De La Lama
- Facultad de Veterinaria, Instituto Agroalimentario de Aragón (IA2), Universidad de Zaragoza-CITA, Zaragoza, Spain
| |
Collapse
|