Early detection of late-onset neonatal sepsis from noninvasive biosignals using deep learning: A multicenter prospective development and validation study.

BACKGROUND: Neonatal sepsis is responsible for significant morbidity and mortality worldwide. Its accurate and timely diagnosis is hindered by vague symptoms and the urgent necessity for early antibiotic intervention. The gold standard for diagnosing the condition is the identification of a pathogenic organism from normally sterile sites via laboratory testing. However, this method is resource-intensive and cannot be conducted continuously. OBJECTIVE: This study aimed to predict the onset of late-onset sepsis (LOS) with good diagnostic value as early as possible using non-invasive biosignal measurements from neonatal intensive care unit (NICU) monitors. METHODS: In this prospective multicenter study, we developed a multimodal machine learning algorithm based on a convolutional neural network (CNN) structure that uses the power spectral density (PSD) of recorded biosignals to predict the onset of LOS. This approach aimed to discern LOS-related pathogenic spectral signatures without labor-intensive manual artifact removal. RESULTS: The model achieved an area under the receiver operating characteristic score of 0.810 (95 % CI 0.698-0.922) on the validation dataset. With an optimal operating point, LOS detection had 83 % sensitivity and 73 % specificity. The median early detection was 44 h before clinical suspicion. The results highlighted the additive importance of electrocardiogram and respiratory impedance (RESP) signals in improving predictive accuracy. According to a more detailed analysis, the predictive power arose from the morphology of the electrocardiogram's R-wave and sudden changes in the RESP signal. CONCLUSION: Raw biosignals from NICU monitors, in conjunction with PSD transformation, as input to the CNN, can provide state-of-the-art prediction performance for LOS without the need for artifact removal. To the knowledge of the authors, this is the first study to highlight the independent and additive predictive potential of electrocardiogram R-wave morphology and concurrent, sudden changes in the RESP waveform in predicting the onset of LOS using non-invasive biosignals.

Validity of Ultra-Short-Term HRV Analysis Using PPG-A Preliminary Study.

Continuous measurement of heart rate variability (HRV) in the short and ultra-short-term using wearable devices allows monitoring of physiological status and prevention of diseases. This study aims to evaluate the agreement of HRV features between a commercial device (Bora Band, Biosency) measuring photoplethysmography (PPG) and reference electrocardiography (ECG) and to assess the validity of ultra-short-term HRV as a surrogate for short-term HRV features. PPG and ECG recordings were acquired from 5 healthy subjects over 18 nights in total. HRV features include time-domain, frequency-domain, nonlinear, and visibility graph features and are extracted from 5 min 30 s and 1 min 30 s duration PPG recordings. The extracted features are compared with reference features of 5 min 30 s duration ECG recordings using repeated-measures correlation, Bland-Altman plots with 95% limits of agreements, Cliff's delta, and an equivalence test. Results showed agreement between PPG recordings and ECG reference recordings for 37 out of 48 HRV features in short-term durations. Sixteen of the forty-eight HRV features were valid and retained very strong correlations, negligible to small bias, with statistical equivalence in the ultra-short recordings (1 min 30 s). The current study concludes that the Bora Band provides valid and reliable measurement of HRV features in short and ultra-short duration recordings.

Impact of long-lasting moderate-intensity stage cycling event on cardiac function in young female athletes: A case study.

PURPOSE: Effects of intense and/or prolonged exercise have been studied extensively in male athletes. Nevertheless, data are scare on the effect of long duration events on cardiac function in female athletes. Our aim was to investigate the effect of a long-lasting moderate-intensity stage cycling event on cardiac function of young female athletes. METHODS: Seven well-trained female cyclists were included. They completed a cycling event of 3529 km on 23 days. All underwent an echocardiography on 6 time-points (baseline and at the arrival of day (D) 3, 7, 12, 13 and 23). Cardiac function was assessed by conventional echocardiography, tissue Doppler imaging and speckle tracking techniques. Daily exercise load was determined by heart rate (HR), power output and rate of perceived exertion data (RPE, Borg scale). RESULTS: All stages were mainly done at moderate intensity (average HR: 65% of maximal, average aerobic power output: 36% of maximal, average RPE: 4). Resting HR measured at the time of echocardiography did not vary during the event. Resting cardiac dimensions did not significantly change during the 23 days of cycling. No significant modification of cardiac function, whatever the studied cavity, were observed all along the event. CONCLUSION: The results suggest that, in the context of our case study, the long-lasting moderate-intensity stage cycling event was not associated with cardiac function alteration. Nevertheless, we must be careful in interpreting them due to the limits of an underpowered study.

Evolution of Heart Rate Complexity Indices in the Early Detection of Neonatal Sepsis.

Despite advances in prenatal health care, neonatal sepsis remains a major cause of neonatal mortality. Early diagnosis and adequate treatment are essential to reduce morbidity and mortality related to this disease. In this paper, we propose a new method to detect neonatal sepsis based on heart rate (HR) complexity measures (entropy and compression indices) that takes into consideration neonatal gestational age. First, the percentile curves were computed for all the complexity indices using data from 118 control neonates. Eight indices were computed: the sample entropy (SampEn) and three indices to quantify the multiscale entropy (MSE) curve - the sum, the slope, and the product of the previous two - and the compression ratio (CR), using the bzip2 compressor, as well as the same three indices but related to the multiscale compression (MSC) curve. Then, the corresponding percentile was estimated for 23 sepsis neonates. Results show a significant decrease in the entropy indices SampEn and MSEsum and in the MSCslope a day before the detection of sepsis by the clinicians. The indices CR and MSCsum increased before the antibiotic take. These results imply that sepsis causes a random, uncorrelated pattern on the HR signal. Future studies should include a bigger data set to calculate a compound index comprising information of other physiological signals. Clinical Relevance - Prompt and accurate diagnosis of neona-tal sepsis is essential for the successful clinical management of neonates and significantly reduce morbidity and mortality. Complexity measures applied to the HR time series appear to detect sepsis in neonates starting one day before the clinical detection.

Extraction of Premature Newborns' Spontaneous Cries in the Real Context of Neonatal Intensive Care Units.

Cry analysis is an important tool to evaluate the development of preterm infants. However, the context of Neonatal Intensive Care Units is challenging, since a wide variety of sounds can occur (e.g., alarms and adult voices). In this paper, a method to extract cries is proposed. It is based on an initial segmentation between silence and sound events, followed by feature extraction on the resulting audio segments and a cry and non-cry classification. A database of 198 cry events coming from 21 newborns and 439 non-cry events was created. Then, a set of features-including Mel-Frequency Cepstral Coefficients-issued from principal component analysis, was computed to describe each audio segment. For the first time in cry analysis, noise was handled using harmonic plus noise analysis. Several machine learning models have been compared. The K-Nearest Neighbours approach showed the best results with a precision of 92.9%. To test the approach in a monitoring application, 412 h of recordings were automatically processed. The cries automatically selected were replayed and a precision of 92.2% was obtained. The impact of errors on the fundamental frequency characterisation was also studied. Results show that despite a difficult context, automatic cry extraction for non-invasive monitoring of vocal development of preterm infants is achievable.

Cardiorespiratory alterations in a newborn ovine model of systemic viral inflammation.

BACKGROUND: Respiratory viruses can be responsible for severe apneas and bradycardias in newborn infants. The link between systemic inflammation with viral sepsis and cardiorespiratory alterations remains poorly understood. We aimed to characterize these alterations by setting up a full-term newborn lamb model of systemic inflammation using polyinosinic:polycytidylic acid (Poly I:C). METHODS: Two 6-h polysomnographic recordings were carried out in eight lambs on two consecutive days, first after an IV saline injection, then after an IV injection of 300 µg/kg Poly I:C. RESULTS: Poly I:C injection decreased locomotor activity and increased NREM sleep. It also led to a biphasic increase in rectal temperature and heart rate. The latter was associated with an overall decrease in heart-rate variability, with no change in respiratory-rate variability. Lastly, brainstem inflammation was found in the areas of the cardiorespiratory control centers 6 h after Poly I:C injection. CONCLUSIONS: The alterations in heart-rate variability induced by Poly I:C injection may be, at least partly, of central origin. Meanwhile, the absence of alterations in respiratory-rate variability is intriguing and noteworthy. Although further studies are obviously needed, this might be a way to differentiate bacterial from viral sepsis in the neonatal period. IMPACT: Provides unique observations on the cardiorespiratory consequences of injecting Poly I:C in a full-term newborn lamb to mimic a systemic inflammation secondary to a viral sepsis. Poly I:C injection led to a biphasic increase in rectal temperature and heart rate associated with an overall decrease in heart-rate variability, with no change in respiratory-rate variability. Brainstem inflammation was found in the areas of the cardiorespiratory control centers.

Functional age estimation through neonatal motion characterization using continuous video recordings.

The follow-up of the development of the premature baby is a major component of its clinical care since it has been shown that it can reveal a pathology. However, no method allowing an automated and continuous monitoring of this development has been proposed. Within the framework of the Digi-NewB European project, our team wishes to offer new clinical indices qualifying the maturation of newborns. In this study, we propose a new method to characterize motor activity from video recordings. For this purpose, we have chosen to characterize the motion temporal organization by drawing inspiration from sleep organization. Thus, we propose a fully automatic process allowing to extract motion features and to combine them to estimate a functional age. By investigating two datasets, one of 28.5 hours (manually annotated) from 33 newborns and one of 4,920 hours from 46 newborns, we show that the proposed approach is relevant for monitoring in clinical routine and that the extracted features reflect the maturation of preterm newborns. Indeed, a compact and interpretable model using gestational age and three motion features (mean duration of intervals with motion, total percentage of time spent in motion and number of intervals without motion) was designed to predict post-menstrual age of newborns and showed an admissible mean absolute error of 1.3 weeks. While the temporal organization of motion was not studied clinically due to a lack of technological means, these results open the door to new developments, new investigations and new knowledge on the evolution of motion in newborns.

Evaluation of Maturation in Preterm Infants Through an Ensemble Machine Learning Algorithm Using Physiological Signals.

This study was designed to test if heart rate variability (HRV) data from preterm and full-term infants could be used to estimate their functional maturational age (FMA), using a machine learning model. We propose that the FMA, and its deviation from the postmenstrual age (PMA) of the infants could inform physicians about the progress of the maturation of the infants. The HRV data was acquired from 50 healthy infants, born between 25 and 41 weeks of gestational age, who did not present any signs of abnormal maturation relative to their age group during the period of observation. The HRV features were used as input for a machine learning model that uses filtering and genetic algorithms for feature selection, and an ensemble machine learning (EML) algorithm, which combines linear and random forest regressions, to produce as output a FMA. Using HRV data, the FMA had a mean absolute error of 0.93 weeks, 95% CI [0.78, 1.08], compared to the PMA. These results demonstrate that HRV features of newborn infants can be used by an EML model to estimate their FMA. This method was also generalized using respiration rate variability (RRV) and bradycardia data, obtaining similar results. The FMA, predicted either by HRV, RRV or bradycardia, and its deviation from the true PMA of the infants, could be used as a surrogate measure of the maturational age of the infants, which could potentially be monitored non-invasively and in real-time in the setting of neonatal intensive care units.

Proposal for a Home Sleep Monitoring Platform Employing a Smart Glove.

The present paper proposes the design of a sleep monitoring platform. It consists of an entire sleep monitoring system based on a smart glove sensor called UpNEA worn during the night for signals acquisition, a mobile application, and a remote server called AeneA for cloud computing. UpNEA acquires a 3-axis accelerometer signal, a photoplethysmography (PPG), and a peripheral oxygen saturation (SpO2) signal from the index finger. Overnight recordings are sent from the hardware to a mobile application and then transferred to AeneA. After cloud computing, the results are shown in a web application, accessible for the user and the clinician. The AeneA sleep monitoring activity performs different tasks: sleep stages classification and oxygen desaturation assessment; heart rate and respiration rate estimation; tachycardia, bradycardia, atrial fibrillation, and premature ventricular contraction detection; and apnea and hypopnea identification and classification. The PPG breathing rate estimation algorithm showed an absolute median error of 0.5 breaths per minute for the 32 s window and 0.2 for the 64 s window. The apnea and hypopnea detection algorithm showed an accuracy (Acc) of 75.1%, by windowing the PPG in one-minute segments. The classification task revealed 92.6% Acc in separating central from obstructive apnea, 83.7% in separating central apnea from central hypopnea and 82.7% in separating obstructive apnea from obstructive hypopnea. The novelty of the integrated algorithms and the top-notch cloud computing products deployed, encourage the production of the proposed solution for home sleep monitoring.

Detection of changes in the behaviour of the elderly person.

In this paper, we propose a solution for detecting changes in the behaviour of the elderly person based on the monitoring of activities of daily living (ADL). The elderly person's daily routine is characterized by the following five indexes: 1) percentage of time lying down, 2) percentage of time sitting, 3) percentage of time standing, 4) percentage of time absent from home, and 5) number of falls during the day. In our framework, these indexes are computed using characteristics extracted from depth and thermal data. We hypothesize that elderly persons have a well-defined, regular life routine, organized around their environment, habits, and social relations. Then, given the indexes values, a day is defined as routine or non-routine day. Thus, looking for changes of day type allows to detect changes in a person's routine. The method has been tested on a database of depth and thermal images recorded in a nursing home over an 85 days period. These tests proved the reliability of the proposed method.

Interest of the minimum edit distance to detect behaviour change of the elderly person.

In this article, a solution to detect the change of behaviour of the elderly person based on the person's activities of daily living is proposed. This work is based on the hypothesis that the person attaches importance to a rhythmic sequence of days and activities per day. The day of the elderly person is described by a succession of activities, and each activity is associated to a posture (lying down, sitting, standing, absent). Postures are estimated from image analysis measured by thermal or depth cameras in order to preserve the anonymity of the person. The change in posture succession is calculated using the minimum edit distance with respect to the routine day. The number of permutations/inversions reflects the change in the person's behaviour. The method was tested on two elderly persons recorded by thermal and depth cameras during 85 days in a retirement home. It is shown that for a person with a life change behaviour, the average number of permutations and interquartile range, before and after changes, are 41 [28], [48] and 57 [55-62] respectively compared to the learned routine day. The Wilcoxon test confirmed the significant difference between these two periods.Clinical Relevance- Monitoring the daily routine provides indicators for detecting changes in the behaviour of an elderly person.

Criteria for assessing the quality of clinical practice guidelines in paediatrics and neonatology: a mixed-method study.

BACKGROUND: Evidenced-based practice is a key component of quality care. This study aims to explore users' expectations concerning paediatric local clinical practice guidelines. METHODS: A mixed method approach was applied, including material from quantitative questionnaire and semi-structured interviews. Data were analysed using descriptive statistics and qualitative content analysis. Data were analysed with constant comparative method. Qualitative data were parsed and categorized to identify themes related to decision-making. RESULTS: A total of 83 physicians answered the survey (response rate 83%). 98% of the participants wanted protocols based on international guidelines, 80% expected a therapeutic content. 24 semi-structured interviews were conducted to understand implementation processes, barriers and facilitators. Qualitative analysis revealed 5 emerging themes: improvement of local clinical practice guidelines, patterns of usage, reasons for non-implementation, alternative sources and perspectives. CONCLUSION: Some criteria should be considered for the redaction of local clinical practice guidelines: focus on therapeutic, ease of access, establish local clinical practice guidelines based on international guidelines adapted to the local setting, document references and include trainees such as residents in the redaction.

Early bradycardia detection and therapeutic interventions in preterm infant monitoring.

In very preterm infants, cardio-respiratory events and associated hypoxemia occurring during early postnatal life have been associated with risks of retinopathy, growth alteration and neurodevelopment impairment. These events are commonly detected by continuous cardio-respiratory monitoring in neonatal intensive care units (NICU), through the associated bradycardia. NICU nurse interventions are mainly triggered by these alarms. In this work, we acquired data from 52 preterm infants during NICU monitoring, in order to propose an early bradycardia detector which is based on a decentralized fusion of three detectors. The main objective is to improve automatic detection under real-life conditions without altering performance with respect to that of a monitor commonly used in NICU. We used heart rate lower than 80 bpm during at least 10 sec to define bradycardia. With this definition we observed a high rate of false alarms (64%) in real-life and that 29% of the relevant alarms were not followed by manual interventions. Concerning the proposed detection method, when compared to current monitors, it provided a significant decrease of the detection delay of 2.9 seconds, without alteration of the sensitivity (97.6% vs 95.2%) and false alarm rate (63.7% vs 64.1%). We expect that such an early detection will improve the response of the newborn to the intervention and allow for the development of new automatic therapeutic strategies which could complement manual intervention and decrease the sepsis risk.

Comparison of Activity Monitors Accuracy in Assessing Intermittent Outdoor Walking.

PURPOSE: This study aimed to determine and compare the accuracy of different activity monitors in assessing intermittent outdoor walking in both healthy and clinical populations through the development and validation of processing methodologies. METHODS: In study 1, an automated algorithm was implemented and tested for the detection of short (≤1 min) walking and stopping bouts during prescribed walking protocols performed by healthy subjects in environments with low and high levels of obstruction. The following parameters obtained from activity monitors were tested, with different recording epochs0.1s/0.033s/1s/3s/10s and wearing locationsscapula/hip/wrist/ankle: GlobalSat DG100 (GS) and Qstarz BT-Q1000XT/-Q1000eX (QS) speed; ActiGraph wGT3X+ (AG) vector magnitude (VM) raw data, VM counts, and steps; and StepWatch3 (SW) steps. Furthermore, linear mixed models were developed to estimate walking speeds and distances from the monitors parameters. Study 2 validated the performance of the activity monitors and processing methodologies in a clinical population showing profile of intermittent walking due to functional limitations during outdoor walking sessions. RESULTS: In study 1, GS1s, scapula, QS1s, scapula/wrist speed, and AG0.033s, hip VM raw data provided the highest bout detection rates (>96.7%) and the lowest root mean square errors in speed (≤0.4 km·h-1) and distance (<18 m) estimation. Using SW3s, ankle steps, the root mean square error for walking/stopping duration estimation reached 13.6 min using proprietary software and 0.98 min using our algorithm (total recording duration, 282 min). In study 2, using AG0.033s, hip VM raw data, the bout detection rate (95% confidence interval) reached 100% (99%-100%), and the mean (SD) absolute percentage errors in speed and distance estimation were 9% (6.6%) and 12.5% (7.9%), respectively. CONCLUSIONS: GPS receivers and AG demonstrated high performance in assessing intermittent outdoor walking in both healthy and clinical populations.

Preterm Newborn Presence Detection in Incubator and Open Bed Using Deep Transfer Learning.

Video-based motion analysis recently appeared to be a promising approach in neonatal intensive care units for monitoring the state of preterm newborns since it is contact-less and noninvasive. However it is important to remove periods when the newborn is absent or an adult is present from the analysis. In this paper, we propose a method for automatic detection of preterm newborn presence in incubator and open bed. We learn a specific model for each bed type as the camera placement differs a lot and the encountered situations are different between both. We break the problem down into two binary classifications based on deep transfer learning that are fused afterwards: newborn presence detection on the one hand and adult presence detection on the other hand. Moreover, we adopt a strategy of decision intervals fusion in order to take advantage of temporal consistency. We test three deep neural network that were pre-trained on ImageNet: VGG16, MobileNetV2 and InceptionV3. Two classifiers are compared: support vector machine and a small neural network. Our experiments are conducted on a database of 120 newborns. The whole method is evaluated on a subset of 25 newborns including 66 days of video recordings. In incubator, we reach a balanced accuracy of 86%. In open bed, the performance is lower because of a much wider variety of situations whereas less data are available.

Diagnosis of Neonatal Late-Onset Infection in Very Preterm Infant: Inter-Observer Agreement and International Classifications.

BACKGROUND: The definition of late-onset bacterial sepsis (LOS) in very preterm infants is not unified. The objective was to assess the concordance of LOS diagnosis between experts in neonatal infection and international classifications and to evaluate the potential impact on heart rate variability and rate of "bronchopulmonary dysplasia or death". METHODS: A retrospective (2017-2020) multicenter study including hospitalized infants born before 31 weeks of gestation with intention to treat at least 5-days with antibiotics was performed. LOS was classified as "certain or probable" or "doubtful" independently by five experts and according to four international classifications with concordance assessed by Fleiss's kappa test. RESULTS: LOS was suspected at seven days (IQR: 5-11) of life in 48 infants. Following expert classification, 36 of them (75%) were considered as "certain or probable" (kappa = 0.41). Following international classification, this number varied from 13 to 46 (kappa = -0.08). Using the expert classification, "bronchopulmonary dysplasia or death" occurred less frequently in the doubtful group (25% vs. 78%, p < 0.001). Differences existed in HRV changes between the two groups. CONCLUSION: The definition of LOS is not consensual with a low international and moderate inter-observer agreement. This affects the evaluation of associated organ dysfunction and prognosis.

Detection and Classification of Sleep Apnea and Hypopnea Using PPG and SpO 2 Signals.

In this work, a detection and classification method for sleep apnea and hypopnea, using photopletysmography (PPG) and peripheral oxygen saturation (SpO 2) signals, is proposed. The detector consists of two parts: one that detects reductions in amplitude fluctuation of PPG (DAP)and one that detects oxygen desaturations. To further differentiate among sleep disordered breathing events (SDBE), the pulse rate variability (PRV) was extracted from the PPG signal, and then used to extract features that enhance the sympatho-vagal arousals during apneas and hypopneas. A classification was performed to discriminate between central and obstructive events, apneas and hypopneas. The algorithms were tested on 96 overnight signals recorded at the UZ Leuven hospital, annotated by clinical experts, and from patients without any kind of co-morbidity. An accuracy of 75.1% for the detection of apneas and hypopneas, in one-minute segments,was reached. The classification of the detected events showed 92.6% accuracy in separating central from obstructive apnea, 83.7% for central apnea and central hypopnea and 82.7% for obstructive apnea and obstructive hypopnea. The low implementation cost showed a potential for the proposed method of being used as screening device, in ambulatory scenarios.

Early Detection of Late Onset Sepsis in Premature Infants Using Visibility Graph Analysis of Heart Rate Variability.

OBJECTIVE: This study was designed to test the diagnostic value of visibility graph features derived from the heart rate time series to predict late onset sepsis (LOS) in preterm infants using machine learning. METHODS: The heart rate variability (HRV) data was acquired from 49 premature newborns hospitalized in neonatal intensive care units (NICU). The LOS group consisted of patients who received more than five days of antibiotics, at least 72 hours after birth. The control group consisted of infants who did not receive antibiotics. HRV features in the days prior to the start of antibiotics (LOS group) or in a randomly selected period (control group) were compared against a baseline value calculated during a calibration period. After automatic feature selection, four machine learning algorithms were trained. All the tests were done using two variants of the feature set: one only included traditional HRV features, and the other additionally included visibility graph features. Performance was studied using area under the receiver operating characteristics curve (AUROC). RESULTS: The best performance for detecting LOS was obtained with logistic regression, using the feature set including visibility graph features, with AUROC of 87.7% during the six hours preceding the start of antibiotics, and with predictive potential (AUROC above 70%) as early as 42 h before start of antibiotics. CONCLUSION: These results demonstrate the usefulness of introducing visibility graph indexes in HRV analysis for sepsis prediction in newborns. SIGNIFICANCE: The method proposed the possibility of non-invasive, real-time monitoring of risk of LOS in a NICU setting.

Modeling Stress-Recovery Status Through Heart Rate Changes Along a Cycling Grand Tour.

BACKGROUND: Heart rate (HR) and HR variability (HRV) indices are established tools to detect abnormal recovery status in athletes. A low HR and vagally mediated HRV index change between supine and standing positions reflected a maladaptive training stress-recovery status. OBJECTIVES: Our study was focused on a female multistage cycling event. Its overall aim was twofold: (1) quantify the correlation between (a) the change in HR and HRV indices during an active orthostatic test and (b) subjective/objective fatigue, physical load, and training level indicators; and (2) formulate a model predicting the stress-recovery status as indexed by Δ â¢ R ⁢ R ¯ and ΔLnRMSSD (defined as the difference between standing and supine mean RR intervals and LnRMSSD, respectively), based on subjective/objective fatigue indicators, physical load, and training levels. METHODS: Ten female cyclists traveled the route of the 2017 Tour de France, comprising 21 stages of 200 km on average. From 4 days before the beginning of the event itself, and until 1 day after its completion, every morning, each cyclist was subjected to HR and HRV measurements, first at rest in a supine position and then in a standing position. The correlation between HR and HRV indices and subjective/objective fatigue, physical load, and training level indicators was then computed. Finally, several multivariable linear models were tested to analyze the relationships between HR and HRV indices, fatigue, workload, and training level indicators. RESULTS: HR changes appeared as a reliable indicator of stress-recovery status. Fatigue, training level, and Δ â¢ R ⁢ R ¯ displayed a linear relationship. Among a large number of linear models tested, the best one to predict stress-recovery status was the following: Δ â¢ R ⁢ R ¯ = 1,249.37+12.32V̇O2 max + 0.36 km⋅week-1-8.83 HR max -5.8 RPE-28.41 perceived fatigue with an adjusted R 2 = 0.322. CONCLUSION: The proposed model can help to directly assess the adaptation status of an athlete from RR measurements and thus to anticipate a decrease in performance due to fatigue, particularly during a multistage endurance event.