How Florence Nightingale used Data Science

Does an apple a day really keep a doctor away? Or are you better off eating a bowl of blueberries? Does the revolutionary new drug for diabetes increase your chances of getting a heart attack when had in combination with a popular medication for the common cold?

 

If a world pandemic flu were to begin, how quickly would it spread across continents- which are the likely hot spots and which groups of people would be most susceptible? How quickly can we get vaccinations to the most susceptible groups? These are just some of the questions that the healthcare, pharmaceutical and medicinal field grapple with on a day-to-day basis. 

 

Overall, life expectancy may have climbed up from 30-45 years at the beginning of the 20th century to well over 65 by now, but millions of questions remain unanswered and at any given time thousands of drugs are being tested in labs across the world. For the success of these tests, one can thank the humble statistician just as much as the noble physicist or pharmacologist.

 

Interestingly, one of the first medical health professionals to recognize the value of data and analysis was none other than the Lady with the Lamp- Florence Nightingale. To effect change in military medicinal practices and policy, Florence spent many months after returning from the Crimean War in compiling data about war mortality- the reasons, location and underlying drivers of death and disease during the war- and presented her findings to Queen Victoria. She also invented a new kind of graph, a sort of inverted pie chart called the coxcomb to display the results of her analysis. During the course of this analysis she discovered that the single largest driver for human mortality during war was sanitation- even more than the presence of basic supplies. Her analysis led to many changes in medical practices and policies and by the end of the century military mortality was lower than civilian mortality in hospitals.

 

In addition to affecting changes in medical policy, or the way we live or eat, analytics is also extensively used in new drug launch through a specialist field knows as Clinical Research and its ancillary Clinical Data Management. Clinical research is a branch of medical science that determines the safety and effectiveness of medications, devices, diagnostic products and treatment regimens intended for human use. Controlled statistical tests ensure the passage of a drug from the lab to animal testing to tests on human volunteers before they are launched in the market. A lucrative and fast-growing industry, Clinical Research Technicians and Statisticians are in demand across the globe, especially in large KPO hubs like India, where a lot of this work is now being outsourced.

 

BUSINESS APPLICATION

ANALYTICS FOR DISEASE ERADICATION

The first step towards any kind of preventive action is better availability of data and understanding of underlying drivers. This applies to the field of health and hygiene as well, and data collection and analysis agencies have played a significant role in the reduction in infant child mortality rates or the reduction in rates and instances of deadly diseases from across the world.

 

EXAMPLE FROM THE INDUSTRY

SAS FOR HEALTH CARE PROVIDERS

Turn Clinical and Operational Data into evidence based knowledge that you can act on

With global concerns about containing the cost of health care, discussions in many countries about how best to care for an aging population and the ongoing debate in the US on health system reform, it's clear that those health care organizations that can adapt swiftly and strategically to changing dynamics will be better prepared to succeed long-term. There has never been a greater need to derive trusted insights from data, and the use of advanced analytics is critical.

 

http://www.sas.com/industry/healthcare/provider/index.html

 

CAREER OPTIONS & HOW ATI CAN HELP

One of the most pertinent of all goals of ATI is to develop skill sets among individuals to use analytical based solutions so that they can bring about a change and are able to:

Improve process visualization and understanding

Detect significant events and problems

Identify sources of variation

Communicate key quality information

Support confident decision making

Drive continuous process improvement

Support development of best practices

Move from reactive to predictive process management

Lower costs and increase yield