Combining data with technical healthcare knowledge to drive business values, improve predictive analytics, and take the necessary steps for prevention.
Data science combines multiple fields, including statistics, scientific methods, artificial intelligence (AI) and data analysis, to extract value from data. It is the domain of study that deals with vast volumes of data using modern tools and techniques to find unseen patterns, derive meaningful information, and make business decisions. Data science uses complex machine learning algorithms to build predictive models.
Data scientists combine skills like mathematics, computer science and visualisations to analyse data collected from the web, smartphones, customers, sensors, and other sources to derive insights.
What’s the difference between data science, artificial intelligence (AI), and machine learning?
To understand data science, it’s important to know other field-related terms, such as AI and machine learning. Often, you’ll find that these terms are used interchangeably, but there are nuances.
Here’s a simple breakdown:
- AI means getting a computer to mimic human behaviour in some way.
- Data science is a subset of AI, and refers mostly to the overlapping areas of statistics, scientific methods, and data analysis — all of which are used to extract meaning and insights from data.
- Machine learning is another subset of AI, and consists of the techniques that enable computers to figure things out from the data and deliver AI applications.
How data science is transforming business
Organisations are using data science to refine their products and services and therefore, turn data into a competitive advantage. Some examples include:
- Improving patient diagnoses by analysing medical test data and reported symptoms, so doctors can diagnose diseases earlier and treat them more effectively.
- Improving efficiency by analysing traffic patterns, weather conditions, and other factors so logistics companies can improve delivery speeds and reduce costs.
- Optimising the supply chain by predicting when equipment will break down.
- Detecting fraud in financial services by recognising suspicious behaviours and anomalous actions.
Asking the Right Questions
What is the opportunity that needs to be accessed? What is the point that your stakeholders are facing?
Asking questions can help gain a better and deeper understanding of the problem as stakeholders have domain knowledge in the problem. For example, in healthcare it is a priority to interact with caretakers, physicians and nurses, as they can point out directions or interpretations of the metrics calculated. The task is to learn the domain knowledge from them and combine technical knowledge with data to come up with a solution to drive business values.
Exploratory Data Analysis (EDA)
EDA refers to the critical process of performing initial investigations on data so as to discover patterns, to spot anomalies, to test hypotheses and to check assumptions with the help of summary statistics and graphical representations of the data. It is a good practice to understand the data first and try to gather as many insights from it. EDA is all about making sense of data in hand, and in that process we can gather a new set of hypotheses.
Modelling the data using various algorithms
A model represents what was learned by a machine learning algorithm. The model is the output that is obtained after running a machine learning algorithm on training data and represents the rules, numbers, and any other algorithm-specific data structures required to make predictions. Some examples might make this clearer, the linear regression algorithm results in a model consisting of an array of coefficients with specific values.
Data Science in Health
Medicine and healthcare are two of the most important facets of our human life. Traditionally, medicine solely relied on the discretion advised by doctors. For example, a doctor would make a diagnosis based on a patient’s symptoms and suggest a treatment accordingly.
However, this led to occasional mistakes as it was human error-prone. Nowadays, with the advancements in information technology and in particular, Data Science, it is possible to obtain accurate diagnostic measures.
Activity trackers have made the inner workings of our body accessible to anyone who’s willing to wear one and wants to know more about their resting heart rate, sleep patterns, and exercise output. In some cases, these trackers have even saved lives, for example, a man in Texas, 79 years old, did get a notification on his wearable saying that he was in atrial fibrillation, with that information he visited a doctor that confirmed that diagnosis.
Unfortunately for most, it can be more of an entertaining gadget rather than a tool useful for a healthy population. What do you do with hundreds of nights of sleep data? Have you made changes to your sleep routine based on the percent of awake time displayed on your watch? Are you taking your resting heart rate seriously and taking steps to lower it?
Predictive Analytics in Healthcare
Predictive Analytics is one of the most popular topics in health analytics and is playing an important role in improving patient care and chronic disease management.
Population health management is becoming an increasingly popular topic in predictive analytics. It is a data-driven approach focusing on prevention of diseases that are commonly prevalent in society.
A predictive model uses historical data, learns from it, finds patterns and generates accurate predictions from it. It finds correlations and association of symptoms, habits and diseases, to then make meaningful predictions.
With data science, caretakers can predict the deterioration in patient health, recommend preventive measures and start an early treatment that will assist in reducing the risk of the further decline of patient health.
Monitoring Patient Health
Data Science plays a vital role in the Internet of Things (IoT). These IoT devices are present as wearable devices that track heart rate, temperature and other users medical parameters, this data after collected is analysed using data science techniques.
With the help of analytical tools, caretakers are able to keep track of patient heart rate cycles, blood pressure, sleep patterns, mobility, well as their daily routines.
Other than wearable monitoring sensors, caretakers can monitor a patient’s health through home devices. For patients that are chronically ill, there are several systems that track patient movements, monitor their physical parameters and analyse the patterns that are present in the data.
It uses real-time analytics to predict any potential problems a patient may face based on their present condition. Furthermore, it helps the caretakers to take the necessary decisions to help the patients in distress.
Tracking and Preventing Diseases
Data Science plays a pivotal role in monitoring a patient’s health, allowing necessary steps to be taken in order to prevent potential diseases from occurring. Data Scientists are using powerful predictive analytical tools to detect chronic diseases at an early level.
Holmes, A. (2019), ‘A Texas man says his Apple Watch saved his life by detecting problems with his heartbeat’, Business Insider, 25 Nov. Available at: https://www.businessinsider.com/apple-watch-saved-mans-life-detected-heart-problems-2019-11 (Accessed: 2nd February 2022)
Written by Diogo Ribeiro, Data Scientist at MySense.