Experiments in the life sciences field require significant time and cost, and many cases involve challenges that make trials difficult and labor-intensive. Machine learning can be used as a tool to address these issues by enabling data analysis and experimental predictions.
Our engineers use their domain expertise to assist with model development, hypothesis validation, and analytical processing. We also engage in discussions on the implications of analysis results. We have experience in AI-driven organ incision support platforms, natural language processing (NLP) for research paper search and classification, AI-based patient prognosis prediction, and various projects related to drug discovery support.
CASE 01
CASE 02
CASE 03
We developed a system that predicts optimal incision lines by analyzing surgical videos from experienced surgeons using machine learning. The system assists less-experienced doctors by marking the appropriate incision lines.
There are ongoing efforts to integrate this system with augmented reality (AR) for real-world applications.
https://pubmed.ncbi.nlm.nih.gov/35511359/#affiliation-4
We investigated the feasibility of using machine learning to search and classify research papers based on titles, abstracts, and methodologies.
By applying natural language processing (NLP) and clustering techniques, we identified commonalities among complex biological experimental techniques, providing valuable insights through discussions with researchers.
We explored the development of a system that predicts patient prognosis on a daily basis for those undergoing rehabilitation after surgery.
Typically, prognosis prediction relies on a physician’s experience, but by analyzing accumulated patient data with AI, the system enables prognosis predictions even for less-experienced medical professionals.
