Companies scale up their operations and analyze data from billions of events and make predictions about millions of people. Data science and data science in healthcare can affect a single person. There was an important incident that happened late in 2017. An attorney, Scott Killian, was woken up at one a.m. by his Apple watch which was reporting an elevated heart rate. It was 121 beats per minute as opposed to his resting average of 49 beats per minute. He also had a taste of indigestion in his mouth, which actually could have been a sign of a heart attack. He went to the hospital and found that his four blocked arteries and treated with four different stents. Had he kept sleeping, he probably would not have woken up. If his Apple watch had not woken him to identify him with a possible heart attack, he probably would have died in his sleep. A piece of technology based on data from thousands of people is being used to save the life of one particular person.
Data science can help diagnose diseases. It can do this either in parallel with physicians or can do it in new ways that are semi-independent. For example, researchers in Denmark developed an AI assistant that listens on the phone to breathing patterns, tones of voice, and background noises during emergency calls to help diagnose heart attacks, with up to 95% accuracy, allowing them to get people the help they need more quickly. Researchers from the Broad Institute and Harvard University are preparing a website that will soon allow people to upload their DNA from services like ancestry.com or 23andME and free of charge, get their genetic risk scores for heart disease, breast cancer, type two diabetes, chronic inflammatory bowel disease, and atrial fibrillation. Google’s Deep mind AI is currently able to analyze eye scans and diagnose over 50 conditions that threaten the health of the eye with the same accuracy as physicians. But, because it is automated, it can do it much faster at a much higher scale, fulfilling one of the main promises of data science. In addition to diagnosing diseases, data science can help find cures. First, it gives researchers better understanding of the mechanisms of diseases. For example, Barbara Engelhard, a computer scientist at Princeton University and a principal investigator with the Genotype-Tissue expression consortium, led a team that took complete genome sequences and parsed through every mutation of every gene in their samples. That is over, three trillion tests to find the mutations in the genotype of diseases like Type two diabetes. Second, prominent methods in data science, such as neural networks, helped researchers at atom wise, an AI startup, sort through 7000 different drugs to ultimately identify two that could help make humans cells more resistant to the Ebola virus. And third, researchers at the Stanford biomedical data science initiative are using large scale data science methods to find ways that existing drugs that is those that have already been through the FDA approval process, how those drugs can be used to fight a wide range of diseases that currently don’t have adequate medication. Using these methods, data science can help find important new ways of treating and potentially curing diseases.
Data science can also help predict outbreaks. The best-known example of this is google flu trends which back in November 2008, was able to use data from billions of searches on flu-related symptoms to provide near-real-time maps of flu prevalence. They were able to get that map in about one day, which is over 10 days faster than the research by the centers for disease control could do. While this was promising, several factors such as differences between seasonal flu, epidemic flu, and the way that people used google to search for symptoms, have led google flu trends to become less accurate over time, but the concept of using this kind of internet-based data and large data sets to diagnose diseases, that was set in place. For instance, in a similar study in 2014, researchers at the Los Alamos National Laboratory examined, not google searches but Wikipedia searches, not just for flu but for six other diseases like dengue fever. Speaking of dengue, scientists at IBM were able to combine models of regional sensitivity to outbreaks based on data from the WHO and bring in climate data to predict where outbreaks of dengue fever were most likely to occur.
Healthcare is all about meeting the needs of a community, and data science can help meet those needs a little better. When it comes to optimizing delivery, there are several aspects that data science can contribute. In any hospital, Operating Room (OR) is one of the most important places. They account for 60% of admissions and also 60% of the revenue of the hospital but in most hospitals, the operating rooms are scheduled by phone calls or faxes, or emails which makes scheduling slow. One example is UC Health in Colorado went through a relatively simple process of a smartphone app that could schedule the operating rooms, and they found that the surgeons increase the number of scheduled blocks that they released, by nearly 50% and that freed up some of the most valuable resources in the hospital.
Predictive modeling is one of the main tasks for data science in healthcare. Predictive modeling refers to using data instead of hunches. Predictive modeling includes predicting future events like predicting the disease outbreak as well as approximating responses from another method, meaning that you are not looking into the future. For example, if your smartwatch tells you that you have an irregular heartbeat, it is not predicting what your heartbeat is going to be in the future instead, it is attempting to tell you what a doctor might say if they were to look at your heart right now
To conclude, data science provides insights and helps in strategic decision making when it comes to healthcare.
