Advances in medical innovation are leading toward precision medicine, matching disease to targeted treatment. Data modelling using advanced technology has become important to support this development. Prospection Labs is where experimental and innovative ideas come to life. Building a future decision support engine for doctors to determine the next best treatment for patients. Based on the patients’ medical history and profile. Prospection Labs aims to improve patient outcomes using advanced analytics.
With over 15 years experience leading innovation and building engineering teams, Ricky Chen, CTO & Head of Engineering and Prospection Co-founder. What role does Prospection Labs play?
“Innovation already happens throughout Prospection. Prospection Labs accelerates ideas through experiments. Dedicating resources to lead exploration for our teams. The scope of projects is not restricted, to date there have been projects relating to technical architecture, data analytic techniques or machine learning for predictive analytics.” Said Ricky
Prospection is always looking to innovate when analysing health data. Extensive experience working with health data allows Prospection to understand the nuances when modelling. We find patterns and insights to help put the right patient on the right treatment. Gaining access to additional data sets will further enhance Prospection’s capabilities. Allowing for new and exciting offerings using more sophisticated technology.
Observational study to find patterns to predict a particular outcome
“We investigated linking patient history to outcome. The experiment we did was to forecast or predict prostate cancer metastasis. The model delivered promising outcomes with a 90% level of accuracy. Building on this experiment, we are now looking at applying attribute clustering to identify patient archetypes within diseases. This work will aid therapeutic exploration to identify areas of unmet need or outcomes improvement. We are looking at various forecast and anomaly detection techniques next.” Ricky said.
Retrospective cohort analysis
Another example came out of Japan where we created patient segments and looked at treatment regimens vs. outcomes. Using PSA scores in prostate cancer. We found that there were certain drug regimens in each group that gave clearly better outcomes.
Prospection Labs currently has a focus on precision medicine. The aim is to allow doctors and researchers to predict more accurately which treatment and prevention strategies for a particular disease will work, in which groups of people. It is in contrast to a one-size-fits-all approach, in which disease treatment and prevention strategies are developed for the average person. An approach with less consideration for the differences between individuals.
The more datasets Prospection has access and can analyse, the more valuable the insights we can produce. Using the same methodology, with real world evidence across multiple countries will lead to larger samples and significant value to informing health decisions.
Prospection will provide better answers to some key questions such as:
Which patient cohorts have better outcomes for a particular drug?
Does one drug have better outcomes than another drug in certain groups?
What is exciting about predictive analytics?
“I think it is the possibility to solve a class of problems that used to require significant human intervention. Plus the field itself is relatively new so there’s a lot of room to explore. In terms of what are the most appropriate applications and where the limitations lie.” Ricky said.