Generalisable machine learning models trained on heart rate variability data to predict mental fatigue

Next Generation Computing and Communication Hub for First Responders in Smart Cities

This paper contributes to the development of a Next Generation First Responder (NGFR) communication platform with the key goal of embedding it into a smart city technology infrastructure. The framework of this approach is a concept known as SmartHub, developed by the US Department of Homeland Security. The proposed embedding methodology complies with the standard categories and indicators of smart city performance. This paper offers two practice-centered extensions of the NGFR hub, which are also the main results: first, a cognitive workload monitoring of first responders as a basis for their performance assessment, monitoring, and improvement; and second, a highly sensitive problem of human society, the emergency assistance tools for individuals with disabilities. Both extensions explore various technological-societal dimensions of smart cities, including interoperability, standardization, and accessibility to assistive technologies for people with disabilities. Regarding cognitive workload monitoring, the core result is a novel AI formalism, an ensemble of machine learning processes aggregated using machine reasoning. This ensemble enables predictive situation assessment and self-aware computing, which is the basis of the digital twin concept. We experimentally demonstrate a specific component of a digital twin of an NGFR, a near-real-time monitoring of the NGFR cognitive workload. Regarding our second result, a problem of emergency assistance for individuals with disabilities that originated as accessibility to assistive technologies to promote disability inclusion, we provide the NGFR specification focusing on interactions based on AI formalism and using a unified hub platform. This paper also discusses a technology roadmap using the notion of the Emergency Management Cycle (EMC), a commonly accepted doctrine for managing disasters through the steps of mitigation, preparedness, response, and recovery. It positions the NGFR hub as a benchmark of the smart city emergency service.

Structural neural correlates of mental fatigue and reward-induced improvement in performance

Neuroimaging studies investigating the association between mental fatigue (henceforth fatigue) and brain physiology have identified many brain regions that may underly the cognitive changes induced by fatigue. These studies focused on the functional changes and functional connectivity of the brain relating to fatigue. The structural correlates of fatigue, however, have received little attention. To fill this gap, this study explored the associations of fatigue with cortical thickness of frontal and parietal regions. In addition, we aimed to explore the associations between reward-induced improvement in performance and neuroanatomical markers in fatigued individuals. Thirty-nine healthy volunteers performed the psychomotor vigilance task for 15 min (i.e., 3 time-on-task blocks of 5 min) out of scanner; followed by an additional rewarded block of the task lasting 5 min. Baseline high-resolution T1-weigthed MR images were obtained. Reaction time increased with time-on-task but got faster again in the rewarded block. Participants' subjective fatigue increased during task performance. In addition, we found that higher increase in subjective mental fatigue was associated with the cortical thickness of the following areas: bilateral precuneus, right precentral gyrus; right pars triangularis and left superior frontal gyrus. Our results suggest that individual differences in subjective mental fatigue may be explained by differences in the degree of cortical thickness of areas that are associated with motor processes, executive functions, intrinsic alertness and are parts of the default mode network.

[Mental fatigue state recognition method based on convolution neural network and long short-term memory]

The pace of modern life is accelerating, the pressure of life is gradually increasing, and the long-term accumulation of mental fatigue poses a threat to health. By analyzing physiological signals and parameters, this paper proposes a method that can identify the state of mental fatigue, which helps to maintain a healthy life. The method proposed in this paper is a new recognition method of psychological fatigue state of electrocardiogram signals based on convolutional neural network and long short-term memory. Firstly, the convolution layer of one-dimensional convolutional neural network model is used to extract local features, the key information is extracted through pooling layer, and some redundant data is removed. Then, the extracted features are used as input to the long short-term memory model to further fuse the ECG features. Finally, by integrating the key information through the full connection layer, the accurate recognition of mental fatigue state is successfully realized. The results show that compared with traditional machine learning algorithms, the proposed method significantly improves the accuracy of mental fatigue recognition to 96.3%, which provides a reliable basis for the early warning and evaluation of mental fatigue.

Time-domain heart rate variability features for automatic congestive heart failure prediction

AIMS

Heart failure is a serious condition that often goes undiagnosed in primary care due to the lack of reliable diagnostic tools and the similarity of its symptoms with other diseases. Non-invasive monitoring of heart rate variability (HRV), which reflects the activity of the autonomic nervous system, could offer a novel and accurate way to detect and manage heart failure patients. This study aimed to assess the feasibility of using machine learning techniques on HRV data as a non-invasive biomarker to classify healthy adults and those with heart failure.

METHODS AND RESULTS

We used digitized electrocardiogram recordings from 54 adults with normal sinus rhythm and 44 adults categorized into New York Heart Association classes 1, 2, and 3, suffering from congestive heart failure. All recordings were sourced from the PhysioNet database. Following data pre-processing, we performed time-domain HRV analysis on all individual recordings, including root mean square of the successive difference in adjacent RR interval (RRi) (RMSSD), the standard deviation of RRi (SDNN, the NN stands for natural or sinus intervals), the standard deviation of the successive differences between successive RRi (SDSD), the number or percentage of RRi longer than 50 ms (NN50 and pNN50), and the average value of RRi [mean RR interval (mRRi)]. In our experimental classification performance evaluation, on the computed HRV parameters, we optimized hyperparameters and performed five-fold cross-validation using four machine learning classification algorithms: support vector machine, k-nearest neighbour (KNN), naïve Bayes, and decision tree (DT). We evaluated the prediction accuracy of these models using performance criteria, namely, precision, recall, specificity, F1 score, and overall accuracy. For added insight, we also presented receiver operating characteristic (ROC) plots and area under the ROC curve (AUC) values. The overall best performance accuracy of 77% was achieved when KNN and DT were trained on computed HRV parameters with a 5 min time window. KNN obtained an AUC of 0.77, while DT attained 0.78. Additionally, in the classification of severe congestive heart failure, KNN and DT had the best accuracy of 91%, with KNN achieving an AUC of 0.88 and DT obtaining 0.92.

CONCLUSIONS

The results show that HRV can accurately predict severe congestive heart failure. The findings of this study could inform the use of machine learning approaches on non-invasive HRV, to screen congestive heart failure individuals in primary care.

Acute Effects of Fatigue on Cardiac Autonomic Nervous Activity

The onset of fatigue disrupts the functioning of the autonomic nervous system (ANS), potentially elevating the risk of life-threatening incidents and impairing daily performance. Previous studies mainly focused on physical fatigue (PF) and mental fatigue (MF) effects on the ANS, with limited knowledge concerning the influence of physical-mental fatigue (PMF) on ANS functionality. This study aimed to assess the immediate impact of PMF on ANS function and to compare its effects with those of PF and MF on ANS function. Thirty-six physically active college students (17 females) without burnout performed 60-min cycling exercises, AX-Continuous Performance Task (AX-CPT), and cycling combined with AX-CPT to induce PF, MF, and PMF respectively. Subjective fatigue levels were measured using the Rating of Perceived Exertion scale and the Visual Analog Scale-Fatigue. Heart rate variability was measured before and after each protocol to assess cardiac autonomic function. The proposed tasks successfully induced PF, MF, and PMF, demonstrated by significant changes in subjective fatigue levels. Compared with baseline, PMF decreased the root mean square of successive differences (RMSSD) between normal heartbeats (P < 0.001, d = 0.50), the standard deviation of normal-to-normal RR intervals (SDNN) (P < 0.01, d = 0.33), and the normalized high-frequency (nHF) power (P < 0.001, d = 0.32) while increased the normalized low-frequency (nLF) power (P < 0.001, d = 0.35) and the nLF/nHF ratio (P < 0.001, d = 0.40). Compared with MF, PMF significantly decreased RMSSD (P < 0.001, η2 = 0.431), SDNN (P < 0.001, η2 = 0.327), nLF (P < 0.01, η2 = 0.201), and nHF (P < 0.001, η2 = 0.377) but not the nLF/nHF ratio. There were no significant differences in ΔHRV (i.e., ΔRMSSD, ΔSDNN, ΔnLF/nHF, ΔnLF, and ΔnHF), heart rate, and training impulse between PF- and PMF-inducing protocols. Cognitive performance (i.e., accuracy) in AX-CPT during the PMF-inducing protocol was significantly lower than that during the MF-inducing protocol (P < 0.001, η2 = 0.101). PF and PMF increased sympathetic activity and decreased parasympathetic activity, while MF enhanced parasympathetic activity.