A new mathematical model assesses ICU patients' mortality risk
(Press-News.org) A research team led by Dr Rosario Delgado from the UAB Department of Mathematics, in collaboration with the Hospital de Mataró, developed a new machine learning-based model that predicts the risk of mortality of intensive care unit patients according to their characteristics. The research was published in the latest edition of the journal Artificial Intelligence in Medicine, with a special mention as a "Position paper".
Under the framework of Artificial Intelligence, machine learning allows a model to gain knowledge based on the information provided by available historical data, and automatically modifies its information when new information appears. One of the current challenges is the creation of models with which to make personalised medical predictions, and one of the areas in which artificial intelligence can be of great help is in deciding how to proceed with intensive care unit (ICU) patients. This process is complex and comes at a high cost, and depends on the inherent variability of the opinion of specialists, based on their experience and instinct. Therefore, to improve the quality of care in the ICUs, it is important to set down protocols based on objective data and on an accurate prediction of a patient's risk of mortality according to their characteristics. In this sense, machine learning tools may be of great help to medical experts.
A group of researchers led by Dr Rosario Delgado from the Department of Mathematics of the UAB, in collaboration with Head of the ICU at Hospital de Mataró Dr Juan Carlos Yébenes, UAB associate lecturer Àngel Lavado from the Information Management Unit of the Maresme Health Consortium, and José David Núñez-González, PhD student of the UAB Department of Mathematics, used machine learning tools to create a model capable of predicting the risk of mortality of ICU patients, based on a real database which also served to validate the model. The model will aid in the decision-making process of healthcare workers by improving the prediction of premature deaths, making medical decisions about high-risk patients more efficient, evaluating the effectiveness of new treatments and detecting changes in clinical practices.
The use of this model represents a clear improvement in traditional approaches, consistent with predicting the risk of mortality based on the Acute Physiology And Chronic Health Evaluation (APACHE) score - a questionnaire widely used to assess a person's state of health with the help of different indicators. The new model makes use of an estimated logistical regression that was validated in previous groups of patients. Researchers were able to demonstrate experimentally that the new model they created overcomes the weak points of traditional approaches, offering good results and presenting itself as a better alternative.
The predictive self-learning prognosis model created by researchers consists in a set of Bayesian classifiers used by assigning a life prognosis label (live or die) to each individual, according to traits such as demography, gender and age; the Charlson comorbidity index; their place of origin; the cause of admission; the presence or lack of sepsis; severity reached in the first 24 hours after aadmission; and the APACHE II score.
Researchers improved the model's prediction through a combination of individual predictions of each classifier designed in a way that the faults of some predictions could be compensated with other correct predictions, and taking into account the imbalance represented by a low proportion of patients dying in the ICUs. The model predicts the cause of death of patients at a high risk, as well as the outcome of patients at a low risk of dying. This type of model is known as a hierarchical predictive model, given that there are two stages of prediction.
"The hierarchical predictive prognosis model we have introduced has a good predictive behaviour, and it also allows studying which of the patient's traits are the most decisive, which can become risk factors, in assessing their risk of death. It also can be extrapolated to compare different ICUs, or in a longitudinal study to analyse improvements through the timing of protocols in specific ICUs", explains Dr Rosario Delgado. "This is a useful and promising methodology, and has important clinical applicability from the moment in which it can help physicians make patient-tailored medical decisions, and also for health authorities in their management of available resources", she concludes.
The study was published in the latest edition of Artificial Intelligence in Medicine with a special mention as a "Position paper", and was conducted in collaboration with the Hospital de Mataró.
ELSE PRESS RELEASES FROM THIS DATE:
When can we say that a certain property of a system is robust? Intuitively, robustness implies that, even under the effect of external perturbations on the system, no matter how strong or random, said property remains unchanged. In mathematics, properties of an object that are robust against deformations are called topological. For example, the letters s, S, and L can be transformed into each other by stretching or bending their shape. The same holds true for letters o, O, and D. However, it is impossible to turn an S into an O without a discontinuous operation, such as cutting the O apart or sticking the two ends of the S together. Therefore, we say that the letters s, S and L have the same topology - as do the letters o, O and D - ...
Chemotherapy has helped make acute lymphoblastic leukemia (ALL) one of the most survivable childhood cancers. Now, researchers working in the U.S., Germany and China have shown how chemotherapy drugs called thiopurines can lead to mutations that set patients up for relapse. The work appears today in the journal Nature Cancer.
The research provides the first direct genomic and experimental evidence in pediatric cancer that drug-resistant mutations can be induced by chemotherapy and are not always present at diagnosis.
"The findings offer a paradigm shift in understanding how drug resistance develops," said Jinghui Zhang, Ph.D., Department of Computational Biology chair at St. Jude Children's Research Hospital. "The ...
Rivers are lifelines for many countries. They create valuable ecosystems, provide drinking water for people and raw water for agriculture and industry. In the Global South in particular, there is strong competition for access to freshwater resources. The increasing use of hydropower has recently intensified this competition further.
Take Ethiopia, for example: when the country began filling the mega-?dam Gibe III on the Omo River in 2015, downstream users saw a drop in water volumes. Natural flooding declined, reducing the volume of fertile mud washed onto the floodplain. The level of Kenya's Lake Turkana, into which the Omo flows, fell temporarily by two metres, resulting in significant consequences for people and agriculture.
Scientists have identified five new plant species in the Bolivian Andes.
The species are all part of the genus Jacquemontia, which are twining or trailing plants with pretty blue flowers.
With rapid biodiversity loss taking place across South America and worldwide, identifying plant species is a vital step towards protecting them.
The new study, which classifies and describes the 28 Jacquemontia species now known to live in Bolivia and Peru, was carried out by the universities of Exeter and Oxford, and the Royal Botanic Gardens, Kew.
"Many plant species have not been identified and classified, especially in the tropics," said Rosie Clegg, of the University of Exeter and Kew.
"If you don't know what a species is, you can't ...
Most children with a mental health disorder are not receiving services to address their needs--according to a new study from researchers at Simon Fraser University's Children's Health Policy Centre. Their research was published this week in the journal Evidence-Based Mental Health.
Researchers found that of the one in eight children (12.7 per cent) who experience a mental disorder, less than half (44.2 per cent) receive any services for these conditions.
"We have illuminated an invisible crisis in children's mental health and unacceptable service shortfalls in high-income countries -- including in Canada -- to a degree that violates children's rights," says study author Charlotte Waddell, ...
After gaining world attention by 'unboiling' egg protein, Flinders University scientists have now used an Australian-made novel thin film microfluidic device to manipulate Beta-lactoglobulin (β-lactoglobulin), the major whey protein in cow's, sheep's and other mammals.
The so-called Vortex Fluidic Device has previously been used in an array of experiments to successfully 'un-boil' egg protein and even break the molecular bonds of one of the world's hardest material, carbon nanotubes.
In the latest application, published in Molecules, College of Science and Engineering experts have combined the capabilities of the VFD with a new form of biosensor called TPE-MI, which is an aggregation-induced emission luminogen (AIEgen).
"In the human body, protein folding is ...
The human body is essentially made up of trillions of living cells. It ages as its cells age, which happens when those cells eventually stop replicating and dividing. Scientists have long known that genes influence how cells age and how long humans live, but how that works exactly remains unclear. Findings from a new study led by researchers at Washington State University have solved a small piece of that puzzle, bringing scientists one step closer to solving the mystery of aging.
A research team headed by Jiyue Zhu, a professor in the College of Pharmacy and Pharmaceutical Sciences, recently identified a DNA region known as VNTR2-1 that appears to drive the activity of the telomerase gene, which has been shown to prevent ...
Almost all crop plants form associations with a particular type of fungi - called arbuscular mycorrhiza fungi - in the soil, which greatly expand their root surface area. This mutually beneficial interaction boosts the plant's ability to take up nutrients that are vital for growth.
The more nutrients plants obtain naturally, the less artificial fertilisers are needed. Understanding this natural process, as the first step towards potentially enhancing it, is an ongoing research challenge. Progress is likely to pay huge dividends for agricultural productivity.
In a study published in the journal PLOS Biology, researchers used the bright red pigments of beetroot - called betalains - to visually track soil fungi as they colonised plant roots in a living plant.
"We can now ...
Many disease-causing bacteria such as Pseudomonas aeruginosa crawl on surfaces through a walk-like motility known as "twitching". Nanometers-wide filaments called type IV pili are known to power twitching, but scientists ignore which sensory signals coordinate the microbes' movements.
Now, EPFL researchers have found that Pseudomonas bacteria use a mechanism similar to our sense of touch to navigate on surfaces. "This study changes the way we think about motility in bacteria," says senior author Alexandre Persat, a tenure track assistant professor at EPFL's School of Life Sciences.
Scientists have known that ...
Oncotarget published "Role for Fgr and Numb in retinoic acid-induced differentiation and G0 arrest of non-APL AML cells" which reported that retinoic acid is a fundamental regulator of cell cycle and cell differentiation.
Using a leukemic patient-derived in vitro model of a non-APL AML, these authors previously found that RA evokes activation of a macromolecular signaling complex, a signalosome, built of numerous MAPK-pathway-related signaling molecules; and this signaling enabled Retinoic-Acid-Response-Elements to regulate gene expression that results in cell differentiation/cell cycle arrest. Toward mechanistic ...
LAST 30 PRESS RELEASES:
[Press-News.org] A new mathematical model assesses ICU patients' mortality risk