Our tech can quickly identify the conditions under which features become important and then uncover the causal relations that connect them. Its pattern mining software can identify groups of subjects with shared characteristics and then let analysts inspect them within an easy to use interactive visual interface. Use cases in Biotech include:
Furthermore, our correlation miner will help you identify:
We took a data set with history data of subjects with Friedreich’s Ataxia to identify factors that could explain variations in the progression of the disease as measured by the modified Friedreich's Ataxia Rating Scale (mFARS). The mFARS scale is an exam-based neurological test in which a higher score indicates more advanced progression. The goal of the study was to specifically identify factors that would indicate a higher than average 1 year change in the mFARS scale (denoted as cMFARS). These factors could then be used during a clinical trial to select subjects which are likely to progress at a higher rate.
Akai Kaeru’s proprietary technology identifies groups of subjects where the disease progression is unusually high or low. These groups are statistically robust and defined by simple inclusion/exclusion criteria (e.g. Low Age at onset and Low Baseline MFARS). This information is then presented to the user through the interface shown in the figure below.
The top left plot contains the Group Bubble Chart. Each circle in this plot represents a group of subjects which are similar in some way and where the 1 year change in mFARS is unusually high (green) or low (red). The position of the groups is based on the attribute values associated with the x and y axis labels. We observe a strong trend in which lower Age is associated with higher disease progression. The opacity of a group tells us how important the x-axis attribute is in defining the groups. In this case, the opacity of the groups tells us that Age is only really important at its low values (i.e. there is an accelerated disease progression in children).
The user can select a group for further analysis. This is indicated by the circle with the black outline in the upper left of the bubble chart. The Group Summary and Group Detail panels (right) show more detailed information. We can see that the selected group is described by low Age (i.e. Age <= 15) and low Upper Limb Coordination score (ULC) (i.e. ULC <=13). The text in the right panel tells us that this is a statistically significant finding.
In the Probability Histogram panel (bottom) we can see the distribution of returns for both the selected group (green) and the full set of subjects (gray). The bottom right panel shows the summary statistics for the selected group and how it differs from the average population (green numbers). Finally, the Feature Importance panel (bottom left) shows the importance of the different features both globally (gray) as well as the important features for the selected group (blue).
This is just one example of the many patterns of interest found using Akai Kaeru’s pattern mining and pattern browsing interface. Some other useful features not covered here include exploring alternative explanations for a specific group, correlation mining (i.e. finding groups of subjects for which two attributes become highly correlated), and statistically controlling for the effects of confounding variables.