Machine Learning (ML) or “Machine Learning” It is part of artificial intelligence, where machine learning algorithms create models based on sampled data, known as “training data,” to make unprogrammed predictions or decisions. The computer learns from the information provided to perform certain tasks. for simple tasks assigned to computers which has greatly contributed to saving human effort without the need for humans to waste time configuring algorithms by themselves (1)
machine learning Able to help work in a variety of branches even in the medical field And it is advancing rapidly in the field. For example, in 2012, Sun Microsystems co-founder Vinod Khosla estimated that 80% of physician jobs would be lost in the next two decades from machine learning medical diagnostic software. Automation (2) In 2020, machine learning technology will be used to help diagnose and assist researchers in developing a cure for COVID-19 (3).
Latest new articles from the University of Helsinki. published September 6, 2022, Nature Communications. has introduced a method for accurate genomic data analysis in cancer biopsy. This tool uses machine learning methods. to fix damaged DNA and reveal the true mutation process in tumor samples. This has helped unlock new approaches to cancer treatment and the production of highly valuable therapeutic drugs in millions of archived cancer samples. (4)
Molecular Diagnosis Helps Match Patients to the Right Cancer Treatment Researchers are particularly interested in DNA profiling in clinical cancer samples. Qingli Guo from the University of Helsinki The lead author of this research said: This invaluable cancer resource is not currently used for molecular diagnostics due to poor DNA quality. It also causes severe damage to DNA, which is an inevitable challenge in analyzing cancer genomes in preserved tissues.
Analysis of mutations in cancer genomes can help detect cancer in its early stages. Accurately diagnose cancer and reveals why some cancers are resistant to treatment This new method can greatly accelerate the development of clinical applications. This may directly affect the care of cancer patients in the future.
interesting is The new method can predict the development of cancer processes by more than 90%.
Qingli Guo works closely with scientists from the Institute of Cancer Research (ICR) London and Queen Mary University of London. Developed a machine learning/machine learning method called FFPEsig to study how formalin causes DNA mutations.
The results show that usually Nearly half of the cancer screening process will be missed without correcting for factors that interfered with the sample. However, more than 90% of the FFPEsig was used to predict with accuracy.
Cancer gradually develops, profiling the mutation process in horizontal samples. Longitudinal data, which is tracking the same sample at different times, can help identify clinical predictors and diagnose disease at different tumor stages.
“Our findings enable the identification of clinically relevant signatures from tumor biopsies that have been stored at room temperature for decades. with a deeper understanding of how formalin affects the cancer genome Our study opens up a huge opportunity to transform the form of identity testing developed using cost-effective, large-scale archival samples.” Qingli Guo said (4)
This is one of the new advancements in the use of machine learning to treat cancer. Progress has been made in the use of machine learning for this purpose, for example, recently a new deep learning approach developed by researchers at the Koch Institute for Integrative Cancer was announced. Research at MIT and Massachusetts General Hospital (MGH) that may help classify idiopathic cancer by looking at the gene expression programs involved in early cell development and differentiation (5).
Cancer cells look and behave quite differently than normal cells. This is partly due to dramatic changes in gene expression. But because of advances in single cell profiling and efforts to catalog different cell expression patterns in cell mapping. There is a lot of information that indicates that different types of cancer. how did this happen This is a very useful use of data for human life.
However, the challenge of using data and machine learning to help catch cancer is that If the model is too complex and shows too many characteristics of cancer gene expression, The model may appear to have learned the training data completely. but stumbles when new information is found. But if the model is simplified by reducing the number of features The model may miss different types of information that would lead to an accurate classification of cancer.
Machine learning isn’t perfect. But it is ready to be perfected in the future. At least the use of its algorithm has greatly reduced the burden of human-based diagnostics.
For example, the research team at the Koch Institute has balanced machine learning in analyzing different types of cancer samples. The researchers compared two large cell maps, identifying the relationship between tumors and embryonic cells: the Cancer Genome Atlas (TCGA), which contains gene expression data for 33 tumor types, and the Mouse Organogenesis Cell Atlas (MOCA), which Route 56 separate embryonic cells as they develop and differentiate.
The resulting map of the relationship between developmental gene expression patterns in tumors and embryonic cells was converted to a machine learning model. The researchers isolated the gene expression of tumor samples from the TCGA into individual components. which corresponds to a specific point of time in the development trajectory and assign a mathematical value to each of these elements. The researchers then created a machine learning model called Developmental Multilayer Perceptron (D-MLP), which determines the components of tumor development and predicting its origin
After the machine learning system was trained, D-MLP was applied to 52 new samples of hard-to-diagnose cancers, especially of unknown primary cancers that could not be diagnosed using instruments. existing These cases represent some of the most challenging encountered in MGH hospitals over a period of 4 4 beginning in 2017. The model classifies four tumor types and provides predictive results and other data that can guide the diagnosis and treatment of these patients
refer
1. Ethem Alpaydin (2020). Introduction to Machine Learning (Fourth ed.). MIT. pp. xix, 1–3, 13–18. ISBN 978-0262043793.
2. Vinod Khosla (January 10, 2012). “Do We Need Doctors or Algorithms?”. Tech Crunch.
3. Vaishya, Raju; Javaid, Mohd.; Khan, Ibrahim Haleem; Haleem, Abid (July 1, 2020). “Artificial Intelligence (AI) applications for COVID-19 pandemic”. Diabetes & Metabolic Syndrome: Clinical Research & Reviews. 14 (4): 337–339. doi:10.1016/j.dsx.2020.04.012. PMC 7195043. PMID 32305024.
4. “Researchers use machine learning to unlock the genomic code in clinical cancer samples”. (6-SEP-2022). UNIVERSITY OF HELSINKI.
5. Bendta Schroeder. (September 1, 2022). “Using machine learning to identify undiagnosable cancers”. MIT NEWS.
National Cancer Institute photo,