Boosting (machine learning)In machine learning, boosting is an ensemble meta-algorithm for primarily reducing bias, and also variance in supervised learning, and a family of machine learning algorithms that convert weak learners to strong ones. Boosting is based on the question posed by Kearns and Valiant (1988, 1989): "Can a set of weak learners create a single strong learner?" A weak learner is defined to be a classifier that is only slightly correlated with the true classification (it can label examples better than random guessing).
InsulinInsulin (ˈɪn.sjʊ.lɪn, from Latin insula, 'island') is a peptide hormone produced by beta cells of the pancreatic islets encoded in humans by the INS gene. It is considered to be the main anabolic hormone of the body. It regulates the metabolism of carbohydrates, fats and protein by promoting the absorption of glucose from the blood into liver, fat and skeletal muscle cells. In these tissues the absorbed glucose is converted into either glycogen via glycogenesis or fats (triglycerides) via lipogenesis, or, in the case of the liver, into both.
Machine learningMachine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.
Acute fatty liver of pregnancyAcute fatty liver of pregnancy is a rare life-threatening complication of pregnancy that occurs in the third trimester or the immediate period after delivery. It is thought to be caused by a disordered metabolism of fatty acids by mitochondria in the fetus, caused by long-chain 3-hydroxyacyl-coenzyme A dehydrogenase deficiency. This leads to decreased metabolism of long chain fatty acids by the feto-placental unit, causing subsequent rise in hepatotoxic fatty acids in maternal plasma.
Liver biopsyLiver biopsy is the biopsy (removal of a small sample of tissue) from the liver. It is a medical test that is done to aid diagnosis of liver disease, to assess the severity of known liver disease, and to monitor the progress of treatment. Liver biopsy is often required for the diagnosis of a liver problem (jaundice, abnormal blood tests) where blood tests, such as hepatitis A serology, have not been able to identify a cause. It is also required if hepatitis is possibly the result of medication, but the exact nature of the reaction is unclear.
Acute liver failureAcute liver failure is the appearance of severe complications rapidly after the first signs (such as jaundice) of liver disease, and indicates that the liver has sustained severe damage (loss of function of 80–90% of liver cells). The complications are hepatic encephalopathy and impaired protein synthesis (as measured by the levels of serum albumin and the prothrombin time in the blood). The 1993 classification defines hyperacute as within 1 week, acute as 8–28 days, and subacute as 4–12 weeks; both the speed with which the disease develops and the underlying cause strongly affect outcomes.
Supervised learningSupervised learning (SL) is a paradigm in machine learning where input objects (for example, a vector of predictor variables) and a desired output value (also known as human-labeled supervisory signal) train a model. The training data is processed, building a function that maps new data on expected output values. An optimal scenario will allow for the algorithm to correctly determine output values for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way (see inductive bias).
Naive Bayes classifierIn statistics, naive Bayes classifiers are a family of simple "probabilistic classifiers" based on applying Bayes' theorem with strong (naive) independence assumptions between the features (see Bayes classifier). They are among the simplest Bayesian network models, but coupled with kernel density estimation, they can achieve high accuracy levels. Naive Bayes classifiers are highly scalable, requiring a number of parameters linear in the number of variables (features/predictors) in a learning problem.
Liver support systemA liver support system or diachysis is a type of therapeutic device to assist in performing the functions of the liver. Such systems focus either on removing the accumulating toxins (liver dialysis), or providing additional replacement of the metabolic functions of the liver through the inclusion of hepatocytes to the device (bioartificial liver device). This system is in trial to help people with acute liver failure (ALF) or acute-on-chronic liver failure.
