• Why were the patients infected with a particular disease last month? • Why were the patients in the emergency ward last month?
The diagnostic analytics goes a little beyond reporting, that is, descriptive analytics. The above question can be answered using the data with the business intelligence for insight. For example, diagnostic analytics analyze the big healthcare data to discover the reason for why these patients are infected with COVID-19.
Predictive analytics: Predictive analytics uses machine learning and artificial Intelligence to analyze the present and the past data. This type of analytics is used to predict and forecast the future. The predictive analytics use descriptive data to forecast what will happen in the future possibly. This predictive analysis is the very significant analytics for predicting and diagnosing the disease. These types of analysis have capability for controlling and avoiding non communicable diseases like cancer, heart disease, stroke, and diabetes. Noncommunicable diseases are together accountable for most of the deaths worldwide. The predictive analytics use patient history and patient current health information to make medical decisions. The predictive analytics identify the following:
• Identify the patients who have the maximum possibility of getting diabetics, stroke, and heart attack?
• Identify the patients who have the maximum risk of hospitalization?
The above questions are answered using the data and machine learning for forecasting. In predictive analytics, the researchers and data analysts train a model using data mining algorithms, machine learning techniques, artificial intelligence, and the deep learning algorithms to predict the future events.
Prescriptive analytics: This analytics makes recommendations from the predicted output. The prescriptive analytics in healthcare is the last course of action in analyzing medical big data. This analysis has the capacity to suggest the action to overcome the problem in the healthcare organization. The imminent opportunity and challenges of medical big data is prescriptive analytics. Prescriptive analytics is the most advanced level of data analytics in medical big data. It is going to be realistic in the near future due to machine learning techniques, data science, cloud computing, deep learning, data engineering, and artificial intelligence.
These analytics give the recommendation or suggest action to change the prediction. Prescriptive analytics uses the data, the business intelligence for insight, and the machine learning for forecasting.
Big data analytics perform the above analysis using machine learning, artificial intelligence, and natural language processing to explore the unknown patterns and relationships among data.
3.5 Big Data Applications in the Healthcare Sector
Healthcare sector is the top most sector which generates large volumes of data. So, big data is having a huge impact in the healthcare industry. The EHR of patients is widely adopted and analyzed to get deeper insights on clinical knowledge and for enhanced knowledge about illness and disease. The healthcare organization uses big data that improves the efficiency of healthcare practice and care. Big data with the recent development of data mining techniques, machine learning algorithms, deep learning, artificial intelligence, and image processing used to find many important features. The major applications of big data in the healthcare industry are discussed in the following sections.
3.5.1 Real Time Healthcare Monitoring and Altering
Remote patient monitoring or telehealth is healthcare service for patients and doctors, which use IoT devices to track and analyze health status [25].
The work becomes easy for the doctors and nurses in the hospital because of the application of big data. According to researchers at IBM Watson [2], “Above one million gigabytes of medical associated data is likely to be generated by an average person in their lifetime.” With the new innovations in technology, there is a prevalent use of wearable health monitors. The wearable devices collect data such as temperature, oxygen level, heartbeat, calories burned, BP, water intake, and distance walked. These data can be used by the healthcare professional for the clinical research, monitoring and tracking patients’ health. The sensors are also used with in-patients to continuously monitor the patients. For example, the Fitbit smart watches are used by the patients for self-tracking of their health status. All these monitoring systems are connected to hospitals and physicians through the IoT concept for medical assistance. Table 3.5 lists various remote patient monitoring devices with its features.
3.5.2 Early Disease Prediction with Big Data
Predictive analytics is not new to the healthcare industry. But, it became more powerful with the emergence of big data and its tool to understand the gathered data. The predictive analytics in the healthcare sector helps the doctors to predict or for the early diagnosis of the disease like diabetes, heart disease, stroke, and cancer. Disease prediction is the big data automotive tool of the healthcare field. These analyses are used for developing the disease diagnosing process which improves healthcare practices. The patients, medical professionals, pharmaceutical industry, and insurance companies can be benefitted from predictive analytics in healthcare using big data.
Table 3.5 Patient health checking devices.
| Patient health checking devices | Features |
| Glucose checking meter | It used by diabetes patients for checking the glucose level. |
| Heart rate monitoring | It is used to monitor heart rate. |
| Hand hygiene monitoring | It is used in hospital to remind the people to sanitize their hands before entering hospital room. |
| Depression monitoring | It collects information like heart rate and BP and analyzes this information for a patient᾽s mental health. |
| Blood pressure (BP) monitoring | This device monitors blood pressure. Some BP devices take multiple readings for the daily averages. |
| Pulse oximeter | This device is used to track the oxygen saturation level in blood and also the pulse rate of the patient. |
| Patient wearable | Patient wearable devices are used to sense heart rate, blood pressure, glucose levels, weight, and physical activities. |
| Maternity care monitoring | This remote monitoring reduces clinic visits for pregnant women. |
| Electrocardiography (ECG) devices | This device is used to diagnose cardiac abnormalities. |
Predictive analysis mainly used by hospitals:
• To accurate diagnosis of disease
• To reduce healthcare costs
• For preventive medicine
Predictive analyses with medical data are used for determining the risk level of patients for disease based on lifestyle choices and health history.
One example for predictive analytics in healthcare is the predictive analytics algorithm by Kaiser Permanente [4]. This algorithm