The healthcare industry is currently facing numerous challenges. The developing and underdeveloped countries are more vulnerable due to low resource settings, high population, and less health workforce in local hospitals. According to an estimate by the World Health Organization (WHO), 400 million people across the globe do not have access to basic healthcare facilities . The recent COVID-19 pandemic has further aggravated this situation as the hospitals have to cater for a patient count way beyond their capacity. They face a deficiency of COVID-19 testing facilities, and a shortage of resources to purchase PPEs and necessary instruments. This situation puts both patients and healthcare workers at risk.
Research is currently being conducted in remote health monitoring, biomedical devices and telemedicine — a trend attributed to the advancements in semiconductor devices, micro/nanoelectronics and Information of Things (IoT). Moreover, there has been significant development in wearable health monitoring devices, wireless health monitoring systems, and implantable biosensors. Multiple diagnostic and prognostic models based on machine learning, neural networks and artificial intelligence have also been developed which have high selectivity, specificity and accuracy.
Below are some examples of newly developed products that are revolutionizing the healthcare industry.
Wearable health monitoring systems
A wearable health monitoring device (WHD) is a technology that can continuously monitor human vital signs during their daily routine or in clinical environments, thereby minimizing discomfort and interference. Recently, multiple certified international companies have introduced various WHDs. Vital Tracer’s smartwatch VTLAB is a wearable medical-grade device  that collects raw biological signals and converts them into reliable vital signs data. It also has an ECG monitor, step counter, and gyroscope installed within it. BiPS monitoring system measures heart rate, oxygen saturation, systolic and diastolic blood pressure . It then converts them into electrical medical records (EMRs) and sends these values to doctors, family or some database. BiPS medical solution also monitors the trend of a patient’s vital signs to track the development in the patient’s health situation. Apple introduced a new version of its smartwatch in 2020 , wherein they have added blood oxygen concentration measurement, sleep tracking capability, and ECG monitoring among other features. One can monitor their oxygen concentration value, duration of sleep, and ECG on the screen of the smartwatch using a touch-sensitive display.
Contactless vital signs monitoring
For this type of monitoring, no wearable devices or electrodes or wires are in direct contact with the human body. This type of sensing technology is important in cases when it is difficult or inappropriate to connect sensors directly to the patient, like in the case of infants, or patients with burnt skin or a contagious disease. Multiple techniques are used for this approach.
Kajiro Watanabe and his group proposed a system based on the in-bed technique for contactless vital signs monitoring . They developed a non-invasive pressure-sensor-based system in the form of a thin air-sealed cushion that was able to measure the heartbeat, respiration rate, snoring, and body movements of a subject in bed overnight. Another technique proposed for this purpose is the Doppler phase change principle. The chest wall movement caused by the volume change during respiration can be detected using the Doppler radar motion-sensing system. Travis Hall and his group proposed a contactless biosensing system that uses a 2.4 GHz continuous-wave (CW) RF signal. Their system generated highly accurate results . Camera-based systems for vital signs monitoring have also gained popularity with the advancement of computer vision and spectrometry. Mayank Kumar and his team used monochrome camera and PPG estimation algorithms for this purpose . Their proposed system was able to measure heart rate, oxygen saturation, and blood oxygen level with high accuracy.
Machine learning-based systems
With advancements in the field of machine learning and deep learning, multiple researchers have proposed different ML-based diagnostic and prognostic systems. Muhammad Forkan and his group presented a prognostic system to predict the future state of the health patients using a machine learning algorithm, called ViSiBiD, and vital signs of patients . Their system gave an accuracy of 95.85% using a random forest classifier. Daniel Chang and his group used the recurrent neural network (RNN) to predict the values of vital signs in the next hour using current values of vital signs of patients . The minimum accuracy of their system was 78.7 using RNN and long short-term memory model (LSTM).
The basic idea behind the aforementioned technologies is to provide Point-of-Care Testing (POCT) and treatment. These technologies aim to reduce the workload on the doctors and nursing staff and to increase the efficiency of the healthcare system. The need for such healthcare services is the highest during COVID-19. The implementation of such technologies will not only aid the healthcare workers but will also help them to follow the SOPs, maintain social distancing, and avoid contact with the COVID-19 virus.
While the use of such technologies in the developed countries — which already have sufficient medical resources — is prevalent, public hospitals of underdeveloped countries still lag these facilities. There are numerous reasons for this gap between technological evolution and implementation of such technology in places where it is needed the most. Following are some of the main reasons why the use of modern technology has not become common in developing or underdeveloped countries yet.
“We have to look at [COVID-19] as a global problem, otherwise, we’re never going to truly eliminate it.”Dr Anthony Fauci, MD, director of the National Institute of Allergy and Infectious Diseases (NIAID)
Most of such systems are developed by developed countries having enough resources. The environment and circumstances of these countries defer greatly from the situation in the public hospitals of low-resource settings. Moreover, such systems are generally expensive for low-resource settings due to the difference in currency values, government certification process, and import procedure among numerous reasons. Particularly, the systems based on machine learning and computer vision cannot be generalized for a global population due to the difference in the pattern of patient’s data, immune system, type of measuring instruments, and other demographical factors. Moreover, healthcare workers in public hospitals of developing or underdeveloped countries are not trained to use modern technology. Hence, researchers are burdened with the additional responsibility of ensuring the technical accessibility of technologies.
Professionals from these countries should try to propose low-cost, smart and versatile alternatives to expensive, conventional, and modern equipment which is suitable to their country’s environment and needs. Furthermore, the authorities of such countries should encourage their professionals and researchers to innovate the healthcare industry. Government supervision and assistance should be provided to researchers during the documentation, certification, and approval of their products by the respective authorities. Doctors, nurses, and other healthcare workers should be trained to use modern technology in addition to traditional healthcare instruments. The government, patients, healthcare workers, and the general public should welcome and embrace the change. To become comfortable with technological evolution may seem tough initially, but COVID-19 has elucidated the importance of adapting to the evolution in the tech world. And in a world that is constantly undergoing evolution, change is the only way of survival.
References ”World Health Organization .:. Sustainable Development Knowledge Platform”, Sustainabledevelopment.un.org, 2021. [Online]. [Accessed: 03- Feb- 2021].
 https://vitaltracer.com/, 2020[Online] [Accessed: 16- March- 2021]
 https://www.bipsmed.com/, 2020[Online] [Accessed: 16- March- 2021]
 https://www.apple.com/apple-watch-series-6/, 2020[Online] [Accessed: 16- March- 2021]
 Watanabe K, e., 2020. Noninvasive Measurement Of Heartbeat, Respiration, Snoring And Body Movements Of A Subject In Bed Via A Pneumatic Method. – Pubmed – NCBI. [online] Ncbi.nlm.nih.gov. Available at: https://www.ncbi.nlm.nih.gov/pubmed/16366233 [Accessed 25 April 2020].
 Non-Contact Sensor for Long-Term Continuous Vital Signs Monitoring: A Review on Intelligent Phased-Array Doppler Sensor Design”, https://www.mdpi.com/1424-8220/17/11/2632, 2020
 Mayank Kumar, Ashok Veeraraghavan, and Ashutosh Sabharwal, ”Distance PPG: Robust non-contact vital signs monitoring using a camera,” Biomed. Opt. Express 6, 1565-1588 (2015)
 ViSiBiD: A learning model for early discovery and real-time prediction of severe clinical events using vital signs as big data”, 2017. [Online]. Available: http://www.sciencedirect.com/science/article/abs/pii/S1389128616304431. [Accessed: 04- Feb- 2021].
 D. Chang, ”Risk Prediction of Critical Vital Signs for ICU Patients Using Recurrent Neural Network”, Ieeexplore.ieee.org, 2019. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9070954. [Accessed: 04- Feb- 2021].