The cost of long-term conditions (LTCs), any ongoing health condition that cannot be cured, is becoming a major burden on healthcare providers. In many countries, these costs are covered by the government, which means they are then passed on to the taxpayers. Globally, the spending on LTCs is increasing, so there are plenty of incentives to find smart ways to reduce these health costs.

Mohsin Baig saw the challenge that LTCs bring to the New Zealand health system. Two out of every three New Zealand adults have been diagnosed with at least one LTC [1]. These conditions aren’t always debilitating, but usually require extensive monitoring and checkups. This translates into a huge cost over the period of these patient’s lives. One of the ways to minimise the cost of LTCs is through early detection. Many of these conditions, if caught early, will have less impact on patients and healthcare systems. In his summer research project, Mohsin sought ways to detect LTCs earlier through using wearable device data.

Mohsin noticed the increased popularity of wearable devices and health sensors over the last few years. He decided it would be worth researching whether these devices would be able to assist in the early detection of LTCs. The overall aim of his research project was to develop an automated patient monitoring system which could track vital signs and activity data.

His research collected the following data from participants:

• Heart rate and variability
• Breathing rate and volume
• Activity (steps, cadence, and calories)
• Height
• Weight
• Age
• Gender

Mohsin decided to focus on one LTC during his summer of research project: diabetes. Due to past research, we already know several factors that lead to diabetes. Obesity, smoking, high blood pressure and high cholesterol are all major factors that contribute to pre-diabetes or type 2 diabetes. Māori, Pacific and Indo-Asian people are also at higher risk of developing diabetes. We also know that there are many intervention options available to lower the risk of developing this disease. The most effective of these options is weight loss. In fact, for every 1 kg of weight loss, the risk of diabetes could reduce by 16 percent [2].

Adding vital sign data to the information already available regarding diabetes risk means that Mohsin has a unique combination of data points which may accurately predict LTCs. Using machine learning, Mohsin hopes to transform the raw data he has collected into meaningful and actionable information that can be delivered in real time. The study also supports future research into ongoing patient recruitment, barriers to intervention, and accuracy.

Being able to predict the chances of patients developing LTCs will be a huge benefit to any healthcare provider. Not only does this predictive ability offer the opportunity to prevent these conditions from developing further, but the information gathered allows for more precise healthcare in general. The Precision Driven Health initiative is all about having healthcare providers treat patients as individuals. Mohsin’s research project reinforces this by showing how the risks of LTCs are different for everyone.

Mohsin Baig is among a group of students who took part in the summer of research programme funded by Precision Driven Health. This month we are featuring a blog series examining these projects. While at an elementary stage and considered to be a ‘proof of concept’, these projects offer fresh insights into what the world of healthcare will look like when precision medicine is fully implemented.

References

1. Francesca, C., Ana, L. N., Jérôme, M., & Frits, T. (2011). OECD Health Policy Studies Help Wanted? Providing and Paying for Long-Term Care: Providing and Paying for Long-Term Care (Vol. 2011). OECD Publishing.
2. Hamman RF, Wing RR, Edelstein SL. 2006. Effects of weight loss with lifestyle intervention on risk of diabetes. Diabetes Care 29(9):2012-2017.