Innovation

Where is the AI in HealthTech?

No items found.

If you suspect that there is an AI bubble in HealthTech – you are 100% right. So where really is the AI in HealthTech?

The validation study performed by our partner on MNM’s AI tool for predicting the response of cancer patients to CDK4/6i treatment is a good example of how advanced the AI in HealthTech is.

The synopsis of the story:

  1. Cancer patients are given CDK4/6i without an understanding of who will benefit;
  2. We get genomic and clinical data to build an AI predictive model;
  3. We run ML/AI to obtain the model;
  4. We evaluate the model internally and supply it to the partner who validates it.

Let’s get started: we do what the playbook says, but the model is not working. We go back and spend weeks curating the data (cleaning, understanding, labelling, extracting features, etc). Progress is starting to show, and the model is working now (Model 1). However, the results of internal validation are not great.So, we go back and spend weeks improving the playbook (writing new code, debugging tools, benchmarking available tools). It’s going great, the model is improved (Model 2), but we think we can still make it better.We again go back and spend weeks building completely new tools dedicated to the dataset. The result - a model outperforming all previous approaches (Model 3).

In sum, here is where AI in HealthTech (particularly in cancer genomic) is currently:

  1. The AI can deliver great things (identification of patients who will respond to therapy);
  2. Most of us think that AI is a magic wand. It is NOT. Most AI companies spend a huge amount of their time curating the data and building novel tools for specific data modalities – so today AI is very human-labor intensive;
  3. But stay tuned. The AI will soon transition from current incremental growth to an exponential one. You will see that news about new datasets, tools, and insights will give space to solutions to difficult problems. We’re nearly there!
Where is the AI in HealthTech?
October 13, 2022

You may also like

We simplify the functioning of genomics pipelines

The roots of MNM go back to the world of science, where sharing knowledge is essential.

Are deep learning models exponentially more efficient than conventional models in learning complex patterns from DNA sequencing data?

A pilot study utilizing 4174 samples from The Cancer Genome Atlas (#TCGA) has published results of a 77.6% accuracy in predicting cancer types using the raw tumor sequences that integrate all somatic mutations and germline variants.

Prediction of drug response with mutational signatures. Correlated mutational signatures and the drug phenotyping

There is strong evidence that alterations in the cancer genome can significantly affect the sensitivity and probability of response to treatment.

Improvements in sequencing methods

The discovery of genomic and epigenetic changes in individual cancers has led to many medical innovations and therapeutic successes in oncology.