Artificial Intelligence and Machine Learning for Smart and Secure Healthcare System

By: Sandeep Kumar

In recent years, we have seen a number of people suffering from proactive diseases (such as heart problems, diabetes, stroke, etc.) are growing rapidly. According to the “World report on aging and health” published by the world health organization in 2015, around 22% of the population getting towards the age of 60 or above 60 will be affected by chronic diseases by 2050 [1]. Moreover, new diseases, human to human communicable virals are being discovered, like novel coronavirus, black, white, and yellow fungus. Therefore, the pressure on the healthcare industry will also be going to be increased significantly, because we have very few trained professionals and experts as compared to the population. Moreover, the majority of people cannot afford the service of these highly trained professionals and experts. As technology is growing and recent advancements in the technology, especially in AI and ML there is a need of implementing innovative ideas to make our healthcare more efficient and reliable [7, 10]. We have also witnessed cyber-attacks happen in healthcare industries due to which we lost many lives. So, there is a need to develop secure methods for sharing and storing valuable data.

History and Background

With time few advancements have been made to improve their efficiency such as AI-based IoT
devices being introduced and further, the data collected by them are sent to the cloud servers and using some predefined algorithms they process them. And this processed information is sent to the related doctors or hospitals. Examples of these are – wearable devices integrated with smart sensors which are used to monitor and collect the data like pulse rate, Spo2 and Co2 levels in the blood, temperature etc [1]. AI-based smart and social robots were also introduced. These bots are capable of monitoring the health condition as well as doing a social interaction with the patient. Which is good for patients’ mental health [1]. AI-enabled IoT-based drones aka IoD i.e. internet of drones [4], were proposed to monitor the patient’s health. And during the outbreak of COVID-19, it was used set to monitor the state of the patient as well as the current state of severe containment zones (labeled as a red zone).

Proposed Approach

The proposed approach is a collection of high-performance computers and databases/ servers which will be installed in various parts of the country. Like, in India we will install a database in each state and there will be a master database in which the processed data from the state’s database will be stored. These databases will be designed to store real-time data and also to produce or predict output in real-time. Apart, from collecting data via sensors, smartphones, drones etc we are also going to collect data from the patients and doctors through surveys. These surveys will be a questionnaire, like for a patient we are going to ask the previous medical history, a disease he’s suffering from and for how long, where he lives. And for doctors, mainly about the dos and don’ts under certain physical or mental illness, etc. By data processing, we will get the user data, which will be stored in the databases. And by using data analytics and ML algorithms, we will process the data. Later, this data will be used to train datasets for machine learning and use to study the trend of the disease in a particular area. For example, some disease is more severe in a particular region, like Kerala still has more cases of COVID-19 as compared to other states. So, we find the reason why a certain disease is more severe in a certain area and what could be done to minimize it. This model will also reduce the pressure on the healthcare workers. Because the data regarding a normal disease will already be there and using predictive analysis, our system will be able to give a prescription. For protecting privacy, we will be going to use secure multiparty computing and a privacy-preserving ML algorithm.

Open Issues and Challenges

The biggest challenge is the time and the capital required to implement the proposed model.
Another major challenge is to get experts to work on this. Here, we have just proposed the idea
but it will be going to be difficult to implement this idea. Availability of resources. Make it
affordable for the normal class people. Security is another major challenge because it is close
to impossible to develop a hack-proof and attack-proof system. Illiteracy is also an issue in
developing countries and many don’t have any idea of operating smartphones.

References

1. Tuli, S., et. al. (2020). Next generation technologies for smart healthcare: challenges, vision, model, trends and future directions. Internet Technology Letters, 3(2), e145.
2. Li, J., Cai, J., Khan, F., Rehman, A. U., Balasubramaniam, V., Sun, J., & Venu, P. (2020). A secured framework for sdn-based edge computing in IOT-enabled healthcare system. IEEE Access, 8, 135479-135490.
3. Nasr, M., Islam, M. M., Shehata, S., Karray, F., & Quintana, Y. (2021). Smart Healthcare in the Age of AI: Recent Advances, Challenges, and Future Prospects. IEEE Access.
4. CASE STUDY-” Smart Healthcare in the Age of AI: Recent Advances, Challenges, and Future Prospects”.
5. Fritchman, K., Saminathan, K., Dowsley, R., Hughes, T., De Cock, M., Nascimento, A., & Teredesai, A. (2018, December). Privacy-preserving scoring of tree ensembles: A novel framework for AI in healthcare. In 2018 IEEE International Conference on Big Data (Big Data) (pp. 2413-2422). IEEE.
6. Wazid, M., Bera, B., Mitra, A., Das, A. K., & Ali, R. (2020, September). Private blockchain-envisioned security framework for AI-enabled IoT-based drone-aided healthcare services. In Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond (pp. 37-42).
7. Mamta (2021) Technological Advancements in Healthcare Industry, Insights2Techinfo, pp.1
8. Ghoneim, A., Muhammad, G., et al. (2018). Medical image forgery detection for smart healthcare. IEEE Communications Magazine, 56(4), 33-37.
9. Mamta (2021) Quick Medical Data Access Using Edge Computing, Insights2Techinfo, pp.1
10. Quamara, M., et al. (2021, January). An End-to-End Security Framework for Smart Healthcare Information Sharing against Botnet-based Cyber-Attacks. In 2021 IEEE International Conference on Consumer Electronics (ICCE) (pp. 1-4). IEEE.

Cite this article as:

Sandeep Kumar (2021) Artificial Intelligence and Machine learning for Smart and Secure Healthcare System, Insights2Techinfo, pp.1

166950cookie-checkArtificial Intelligence and Machine Learning for Smart and Secure Healthcare Systemyes