Machine learning algorithms are often drawn from statistics, calculus, and linear algebra. Some popular examples of machine learning algorithms include linear regression, decision trees, random forest, and XGBoost.
These plaques are suspected to damage nerve cells in particular areas of the brain. This leads to a loss of mental functions such as memory and the ability to carry out activities of daily living, amongst others.
AI programs can analyze and contextualize data to provide information and perform like human intelligence in real-world environments.
Today, AI is at the heart of many technologies we use, including smart devices and voice assistants such as Siri on Apple devices.
In healthcare, AI could be used to analyze data from people living with Alzheimer’s diseasein forms of cognitive assessments, blood samples, and sleep recordings to give an early diagnosis of the disease.
Biomarker detection can use a range of methods from blood tests to magnetic resonance imaging (MRI), or amyloid-PET scans, which are i.e. used to diagnose Alzheimer’s disease.
Cognition includes mental processes such as thinking, memory, attention, perception, language, and learning.
CSF is obtained through a lumbar puncture, which is a medical procedure where a needle and syringe is used to extract CSF from the lower part of the spinal cord. CSF can be tested for amyloid and other substances that could help to diagnose Alzheimer’s disease.
Deep learning models use complex algorithms and large neural networks — networks that function like a human brain to logically analyze data — to learn complex patterns and make predictions independent of human input.
This damage leads to symptoms which can include problems with memory, planning, orientation, comprehension, learning, and language, amongst others. The risk of developing dementia becomes greater as we age, however dementia is not a normal part of the aging process.
Secondly, it distinguishes them from one’s own healthy cells in order to prevent or limit infection.
The innate system is the preconfigured protection that everyone is born with. This system is composed by the external barriers (such as the skin) of our body that an invader first encounters. The adaptative immune system is, however, a tailored-response to each specific situation. Unlike the innate immune system, the adaptative is developed thanks to previous exposures to the invaders and remembers individual types of infection.
The white blood cells or leukocytes are constantly looking for invaders. When they find one, they spark an immune response and launch the attack.
There are 5 types of white blood cells; eosinophils, basophils, neutrophils, monocytes and lymphocytes. Lymphocytes are the ones that recognise antigens (i.e., proteins) on the surface of the invaders and produce antibodies against them (i.e., another type of protein that lock onto the antigen and mark invaders for death).
Lymphocytes’ life starts in the bone marrow, some of them will stay there and develop into B cells, and some will travel to the thymus and become T cells. Natural killer cells are also lymphocytes. They contain granules with powerful chemicals that are useful to attack unwanted cells. They destroy virally-infected and tumor cells.
B and T cells’ functions are different. While B cells spot the antigen and secrete the antibodies, T cells kill marked-invaders, alert other leukocytes and stimulate B cells to produce more antibodies. Killer T cells (cytotoxic T cells) are a subtype of T cells that mostly engulfs cancer cells or cells infected by viruses. Memory cytotoxic T cells are a small percentage of cytotoxic T cells that remain in the body for a long time after the infection has been cleared. These cells persist in the immune system for a long time and quickly recognise and launch an attack against the pathogen in the event of re-infection.
By studying and experimenting with machine learning, programmers test the limits of how much they can improve the perception, cognition, and action of a computer system.
For example, in natural language processing, machine learning models can parse and correctly recognize the intent behind previously unheard sentences or combinations of words.
The model used in this project is a deep learning model that takes multi-modal input and can make decisions of disease diagnosis.
This biological analysis approach combines genomic data with data from other modalities such as transcriptomics, epigenetics, and proteomics, to measure gene expression, gene activation, and protein levels.
Multiomics profiling studies enable a more comprehensive understanding of molecular changes contributing to normal development, cellular response, and disease. Using integrative omics technologies, researchers can better connect genotype to phenotype and fuel the discovery of novel drug targets and biomarkers.
https://www.illumina.com/techniques/popular-applications/multiomics.html
During stage 1 of non-REM sleep our body starts relaxing, our eye movement slows, and the electrical activity that emanates from neurons that are communicating amongst themselves (also called brain waves) decreases as well. This stage takes us from wakefulness to a period of light sleep. Stage 2 of non-REM sleep relaxes our muscles and slows the brain waves even further, drops our body temperature and stops our eye movement, allowing our body to enter a period of light sleep before the deeper one. Stage 3 refers to the deep non-REM sleep that allows us to rest and occurs during the first half of the night. In this phase, eye movements, brain waves, heartbeat and breathing slow to their minimum and muscles relax to the lowest degree.
About 90 minutes after falling asleep, REM sleep occurs. As the name indicates, during REM sleep, our eyes move rapidly from side to side. Brain electrical pulses become similar to that observed when we are awake. Breathing, heart rate become faster and irregular, and blood pressure increases as well. Dreams and nightmares happen mostly during this type of sleep, which is also needed for our brain to consolidate memory.
In the second step of this process, the RNA is translated into proteins. Even though a liver cell and a brain cell have the same genome, they look very different and also have very different functions (phenotype). The phenotype of a cell is determined by the combination of genes, which are transcribed into RNA. An innovative scientific method called “single cell RNA sequencing” enables the quantification of the RNA composition of single cells. Using the single cell sequencing data, the cell types within the investigated sample can be identified.
In addition, many diseases cause changes in RNA composition of certain cell types. In Alzheimer’s disease, previous data point towards changes in the RNA composition of immune cells. Therefore, we will isolate immune cells from the blood of patients with Alzheimer’s disease and healthy individuals to perform single cell RNA sequencing. The identified changes in RNA composition of immune cells might help to diagnose Alzheimer’s disease earlier.
Sleep allows our body to recover from illness, remove toxins, conserve energy. It is also essential to helping our cells regenerate, and our brain consolidate memory (i.e., the process of securing information in our memory). Although the biological purpose of the sleep is still unclear, a chronic lack of it increases the risk of having high blood pressure, diabetes, obesity and cardiovascular diseases, among others.