MNM is a place where we share our niche knowledge. You will find here information about biotechnology, artificial intelligence, interdisciplinary texts and many more.
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.
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.
Over the last couple of years, with incredible achievements in the field of DNA sequencing, scientists were able to identify many somatic driver mutations in protein-coding regions of the genome. This part of DNA comprises only 2% of the human genome. What about the remaining 98%?
The discovery of the human genome sequence in the 2000s was a major breakthrough in genetics. However, initially only 92% of the genome was sequenced, leaving the remaining 8% in the shadow. This changed in 2022 when scientists from Telomere-to-Telomere (T2T) consortium showed the results of their work!
There is strong evidence that alterations in the cancer genome can significantly affect the sensitivity and probability of response to treatment. Single gene mutations are increasingly being used as clinical guidance to enable an optimal predictive of anti-cancer therapies, e.x correlated with DNA repair pathways.
The discovery of genomic and epigenetic changes in individual cancers has led to many medical innovations and therapeutic successes in oncology. This has underpinned the development of precision oncology, used as molecular profiling of tumors to identify changes that may be targeted for therapy.