Extraction of apex beat waveform from acoustic pulse wave by sound sensing system using stochastic resonance.

With a sound sensing system using stochastic resonance (4SR), it became possible to obtain an acoustic pulse wave (APW)-a waveform created via a mixture of apex beat and heart sound. We examined 50 subjects who were healthy, with no underlying cardiovascular diseases. We could determine boundary frequency (BF) using APW and phonocardiogram signals. APW data was divided into two bands, one from 0.5 Hz to BF, and a second one from BF to 50 Hz. This permitted the extraction of cardiac apex beat (CAB) and cardiac acoustic sound (CAS), respectively. BF could be expressed by a quadratic function of heart rate, and made it possible to collect CAB and CAS in real time. According to heart rate variability analysis, the fluctuation was 1/f, which indicated an efficient cardiac movement when heart rate was 70 to 80/min. In the frequency band between 0.5 Hz and BF, CAB readings collected from the precordial region resembled apex cardiogram data. The waveforms were classified into five types. Therefore, the new 4SR sensing system can be used as a physical diagnostic tool to obtain biological pulse wave data non-invasively and repeatedly over a long period, and it shows promise for broader applications, including AI analysis.

Recurrent probabilistic neural network-based short-term prediction for acute hypotension and ventricular fibrillation.

In this paper, we propose a novel method for predicting acute clinical deterioration triggered by hypotension, ventricular fibrillation, and an undiagnosed multiple disease condition using biological signals, such as heart rate, RR interval, and blood pressure. Efforts trying to predict such acute clinical deterioration events have received much attention from researchers lately, but most of them are targeted to a single symptom. The distinctive feature of the proposed method is that the occurrence of the event is manifested as a probability by applying a recurrent probabilistic neural network, which is embedded with a hidden Markov model and a Gaussian mixture model. Additionally, its machine learning scheme allows it to learn from the sample data and apply it to a wide range of symptoms. The performance of the proposed method was tested using a dataset provided by Physionet and the University of Tokyo Hospital. The results show that the proposed method has a prediction accuracy of 92.5% for patients with acute hypotension and can predict the occurrence of ventricular fibrillation 5 min before it occurs with an accuracy of 82.5%. In addition, a multiple disease condition can be predicted 7 min before they occur, with an accuracy of over 90%.

Unconstrained Vital Sign Monitoring System Using an Aortic Pulse Wave Sensor.

This paper proposes a novel unconstrained monitoring system that measures heart and respiratory rates and evaluates autonomic nervous activity based on heart rate variability. The proposed system measures the aortic pulse waves (APWs) of a patient via an APW sensor that comprises a single microphone integrated into a mattress. Vital signs (i.e., heart rate, respiratory rate) and autonomic nervous activity were analyzed using the measured APWs. In an experiment with supine and seated participants, vital signs calculated by the proposed system were compared with vital signs measured with commercial devices, and we obtained the correlations of r > 0.8 for the heart rates, r > 0.7 for the respiratory rates, and r > 0.8 for the heart rate variability indices. These results indicate that the proposed system can produce accurate vital sign measurements. In addition, we performed the experiment of image stimulus presentation and explored the relationships between the self-reported psychological states evoked by the stimulus and the measured vital signs. The results indicated that vital signs reflect psychological states. In conclusion, the proposed system demonstrated its ability to monitor health conditions by actions as simple as sitting or lying on the APW sensor.

Unconstrained Monitoring of Biological Signals Using an Aortic Pulse Wave Sensor.

This paper proposes a system to extract biological signals from aortic pulse waves which are measured by a microphone type pulse wave sensor. Theproposed system enables extraction of three biological signals corresponding to respiratory rate, pulse pressure wave, and RR interval simply by sitting on the seat on which the sensor is laid. Experiment results demonstrated that the mean absolute errors between the signals measured by the proposed system and the conventional sensors are as low as 0.38 times per minute for the respiratory rate, 11.2 mmHg for the pulse pressure wave, and 16.6 ms for the RR interval. The proposed system thus may be applied to monitor the physiological state of a human subject to prevent accident caused by health condition.

Noninvasive biological sensor system for detection of drunk driving.

Systems capable of monitoring the biological condition of a driver and issuing warnings during instances of drowsiness have recently been studied. Moreover, many researchers have reported that biological signals, such as brain waves, pulsation waves, and heart rate, are different between people who have and have not consumed alcohol. Currently, we are developing a noninvasive system to detect individuals driving under the influence of alcohol by measuring biological signals. We used the frequency time series analysis to attempt to distinguish between normal and intoxicated states of a person as the basis of the sensing system.