Photoplethysmography Signal Quality Assessment using Attentive-CNN Models

• Leonardo Silva SRBR
• Rafael Lima SRBR
• Giovani Lucafo SRBR
• Italo Sandoval SRBR
• Pedro Garcia Freitas UnB
• Otávio A. B. Penatti SRBR

DOI: https://doi.org/10.5753/sbcas.2024.2206

Resumo

Due to the rapid popularization of wearable computers such as smartwatches, Health Monitoring Applications (HMA) are becoming increasingly popular because of their capability to track different health indicators, including sleep patterns, heart rate, and activity tracking movements. These applications usually employ Photoplethysmography (PPG) sensors to monitor various aspects of an individual’s health and well-being. PPG is a non-invasive and cost-effective optical technique based on the detection of blood volume changes in the microvascular bed of tissue, capturing the dynamic physiological changes in the body with continuous measurements taken over time. Analyzing PPG as a time series enables the extraction of meaningful information about cardiovascular health and other physiological parameters, such as Heart Rate Variability (HRV), Peripheral Oxygen Saturation (SpO2), and sleep status. To enable reliable health indicators, it is important to have robustly sampled PPG signals. However, in practice, the PPG signal is often corrupted with different types of noise and artifacts due to motion, especially in scenarios where wearables are used. Therefore, Signal Quality Assessment (SQA) plays a fundamental role in determining the reliability of a given PPG for use in HMA. Considering this, in this work, we propose a novel PPG SQA method focused on the balance between storage size and classifier quality, aiming to achieve a lightweight and robust model. This model is developed using recent advances in attention-based strategies to significantly improve the performance of purely Convolutional Neural Network (CNN)-based SQA classifiers.

Referências

Azar, J., Makhoul, A., Couturier, R., and Demerjian, J. (2021). Deep recurrent neural network-based autoencoder for photoplethysmogram artifacts filtering. Computers & Electrical Engineering, 92:107065.

Bahdanau, D., Cho, K., and Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. 3rd International Conference on Learning Representations, ICLR 2015.

Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., and Amodei, D. (2020). Language models are few-shot learners. In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H., editors, Advances in Neural Information Processing Systems, volume 33, pages 1877–1901. Curran Associates, Inc.

Chatterjee, T., Ghosh, A., and Sarkar, S. (2022). Signal quality assessment of photoplethysmogram signals using quantum pattern recognition technique and lightweight cnn module. In International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pages 3382–3386.

Chong, J. W., Dao, D. K., Salehizadeh, S., McManus, D. D., Darling, C. E., Chon, K. H., and Mendelson, Y. (2014). Photoplethysmograph signal reconstruction based on a novel hybrid motion artifact detection–reduction approach. part i: Motion and noise artifact detection. Annals of biomedical engineering, 42:2238–2250.

Cisco (2019). Cisco visual networking index (vni) global mobile data traffic forecast update, 2017-2022 white paper. White paper. Accessed on 15 Mar 2021.

Dalianis, H. and Dalianis, H. (2018). Evaluation metrics and evaluation. Clinical Text Mining: secondary use of electronic patient records, pages 45–53.

Elgendi, M. (2016). Optimal signal quality index for photoplethysmogram signals. Bioengineering, 3(4):21.

Fioravanti, V. B. O., Freitas, P. G., Rodrigues, P. G., de Lima, R. G., Lucafo, G. D., Cabello, F. C., Seidel, I., and Penatti, O. A. B. (2024). Machine learning framework for inter-beat interval estimation using wearable photoplethysmography sensors. Biomedical Signal Processing and Control, 88:105689.

Freitas, P. G., De Lima, R. G., Lucafo, G. D., and Penatti, O. A. (2023a). Assessing the quality of photoplethysmograms via gramian angular fields and vision transformer. In 31st European Signal Processing Conference (EUSIPCO), pages 1035–1039.

Freitas, P. G., Lima, R. G. D., Lucafo, G. D., and Penatti, O. A. B. (2023b). Photoplethysmogram signal quality assessment via 1d-to-2d projections and vision transformers. In International Conference on Quality of Multimedia Experience, Ghent, Belgium, June 20-22, pages 165–170.

Gambarotta, N., Aletti, F., Baselli, G., and Ferrario, M. (2016). A review of methods for the signal quality assessment to improve reliability of heart rate and blood pressures derived parameters. Medical & biological engineering & computing, 54:1025–1035.

Gartner (2021). Gartner forecasts global spending on wearable devices to total $81.5 billion in 2021. Accessed on 15 Mar 2021.

Hao, J. and Bo, G. (2021). A quality assessment system for ppg waveform. In International Conference on Circuits and Systems (ICCS), pages 170–175.

Li, K., Warren, S., and Natarajan, B. (2011). Onboard tagging for real-time quality assessment of photoplethysmograms acquired by a wireless reflectance pulse oximeter. IEEE Transactions on Biomedical Circuits and Systems, 6(1):54–63.

Li, Q. and Clifford, G. D. (2012). Dynamic time warping and machine learning for signal quality assessment of pulsatile signals. Physiological measurement, 33(9):1491.

Lima, R. G., Freitas, P. G., Lucafo, G. D., Fioravanti, V., Seidel, I., and Penatti, O. A. (2023). Neural architecture search for tiny detectors of inter-beat intervals. In European Signal Processing Conference (EUSIPCO), pages 1085–1089.

Lucafo, G., Freitas, P. G., Lima, R., Luz, G., Bispo, R., Rodrigues, P., Cabello, F., and Penatti, O. (2022). Signal quality assessment of photoplethysmogram signals using hybrid ruleand learning-based models. In XIX Congresso Brasileiro de Informática em Saúde (CBIS). Brazilian Health Informatics Association (SBIS).

Luong, T., Pham, H., and Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1412–1421.

Naeini, E. K., Azimi, I., Rahmani, A. M., Liljeberg, P., and Dutt, N. (2019). A real-time ppg quality assessment approach for healthcare internet-of-things. Procedia Computer Science, 151:551–558.

Pereira, T., Gadhoumi, K., Ma, M., Liu, X., Xiao, R., Colorado, R. A., Keenan, K. J., Meisel, K., and Hu, X. (2019). A supervised approach to robust photoplethysmography quality assessment. IEEE journal of biomedical and health informatics, 24(3):649–657.

Reddy, G. N. K., Manikandan, M. S., and Murty, N. N. (2020). On-device integrated ppg quality assessment and sensor disconnection/saturation detection system for iot health monitoring. IEEE Transactions on Instrumentation and Measurement, 69(9):6351–6361.

Selvaraj, N., Mendelson, Y., Shelley, K. H., Silverman, D. G., and Chon, K. H. (2011). Statistical approach for the detection of motion/noise artifacts in photoplethysmogram. In International Conference of the IEEE Engineering in Medicine and Biology Society, pages 4972–4975.

Sukor, J. A., Redmond, S., and Lovell, N. (2011). Signal quality measures for pulse oximetry through waveform morphology analysis. Physiological measurement, 32(3):369.

Sun, X., Yang, P., and Zhang, Y.-T. (2012). Assessment of photoplethysmogram signal quality using morphology integrated with temporal information approach. In International Conference of the IEEE Engineering in Medicine and Biology Society, pages 3456–3459.

Vadrevu, S. and Manikandan, M. S. (2019). Real-time ppg signal quality assessment system for improving battery life and false alarms. IEEE transactions on circuits and systems II: express briefs, 66(11):1910–1914.

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, pages 5998–6008.

Zhang, X., Li, J., Cai, Z., Zhao, L., and Liu, C. (2022). Deep learning-based signal quality assessment for wearable ecgs. IEEE Instrumentation & Measurement Magazine, 25(5):41–52.