Tyler O'Neal, Staff Editor INTERCONNECTS

Russian scientists develop new algorithm that can predict populations demographic history

ITMO Scientists develop an algorithm that makes population history models for people and animals more accurate and easier to generate

Bioinformatics scientists from ITMO University have developed a programming tool that allows for quick and effective analysis of genome data and using it as a basis for building the most probable models of demographic history of populations of plants, animals and people. Operating with complex computational schemes, the software can, with a very high degree of likelihood, predict what history a particular group of living organisms has gone through in the past thousands of years, what periods of mass extinction or mass population growth a population has experienced, and how long it has been in contact with other populations of the same species. The scientists' article dedicated to this methodology has been published in GigaScience.

How to find out when exactly the modern tigers' first ancestors appeared on Earth? When did the two elephant populations split? Is there a difference between the Dama and the Moroccan gazelle? When did the division of the African and the Eurasian homo sapiens occur? The answers to all these questions can be found in the population's demographic history - in other words, the scenario that shows what stages the population went through in the course of its history, whether it underwent any mass extinctions, migrations, or sharp spikes in its numbers. CAPTION Genetic algorithm for inferring demographic history of multiple populations from allele frequency spectrum data, ITMO University CREDIT Dmitry Lisovskiy, ITMO.NEWS

Apart from solving fundamental questions, this data can help us in the matters of applied research in the field of ecology and environmental protection. For instance, if some region only has some 800 walruses left, scientists have to understand whether it constitutes a critical decrease or it is a natural population size which has remained constant for several thousand years now, and answer the question of whether valuable resources have to be spent on protecting and saving this species from becoming extinct. {module INSIDE STORY}

The creation of a population's demographic history on the basis of genetic information is a complicated task which requires population geneticists to possess not only knowledge in the field of biology but also programming skills. Such scientists have to garner data and write a code for computing possible models of a population's evolution which could have led to the vast multitude of the genetic information we can witness in this population's representatives today. Up until recently, this was a long process the end result of which relied very heavily on the researcher's initial hypothesis. If it had any defects or the research failed to take some aspect into consideration, the software couldn't correct this initial error and calculated the probability of particular demographic events only within the boundaries predefined by the researcher.

The software developed by a group of ITMO University scientists as part of the Project 5-100 grant programs and with support from JetBrains Research aims to solve this problem. The researchers proposed a programming product which independently and automatically predicts the most probable model of a population's demographic history. At that, it is significantly less dependent on the initial research hypothesis, doesn't require advanced programming skills and produces more accurate results. What is more, the software has the advantage of flexibility, meaning that if the obtained result somehow diverges from archaeological or historical data, you can easily introduce additional limitations into the underlying algorithm to update its hypothesis.

"Using genetic data, our software automatically computes the model it considers optimal," shares Vladimir Ulyantsev. "It looks at the entire volume of the scenarios available. As a scientist, I'll consider the scenarios I deem the most likely, there can be three, five, maybe ten of those. The software, on the other hand, will test all of the models it estimates as probable, this is a much bigger amount. That's why the solutions it comes up with are better than those proposed by people working on the basis of the initial methods. The most beautiful thing here is the method - a genetic algorithm inspired by how evolution happens: species multiply, mutate, with those with the least ability to adapt dying out. In the place of the species we have demographic models and their parameters, and their adaptability is measured on the basis of their similarity with the studied data."

After obtaining this data, the scientists can present it on a map and compare the information indicating that during a particular period a population underwent a migration with archaeological findings and other evidence. These algorithms were used to check a large number of hypotheses and research by evolutionary geneticists. In many cases, the obtained result was much more accurate than that of the initial works.

Mount Sinai researchers build artificial intelligence to scan doctors’ notes distinguishing between types of back pain

Tyler O'Neal, Staff Editor INTERCONNECTS

Mount Sinai researchers have designed an artificial intelligence model that can determine whether lower back pain is acute or chronic by scouring doctors’ notes within electronic medical records, an approach that can help to treat patients more accurately, according to a study published in the Journal of Medical Internet Research in February.

About 80 percent of adults experience lower back pain in their lifetime; it is the most common cause of job-related disability. Many argue that prescribing opioids for lower back pain contributed to the opioid crisis; thus, determining the quality of lower back pain in clinical practice could provide an effective tool not only to improve the management of lower back pain but also to curb unnecessary opioid prescriptions.

Acute and chronic lower back pain are different conditions with different treatments. However, they are coded in electronic health records with the same code and can be differentiated only by retrospective reviews of the patient’s chart, which includes the review of clinical notes. The single code for two different conditions prevents appropriate billing and therapy recommendations, including different return-to-work scenarios. The artificial intelligence model in this study, the first of its kind, could be used to improve the accuracy of coding, billing, and therapy for patients with lower back pain. Ismail Nabeel, MD{module INSIDE STORY}

The researchers used 17,409 clinical notes for 16,715 patients to train artificial intelligence models to determine the severity of lower back pain.

“Several studies have documented increases in medication prescriptions and visits to physicians, physical therapists, and chiropractors for lower back pain episodes,” said Ismail Nabeel, MD, MPH, Associate Professor of Environmental Medicine and Public Health at the Icahn School of Medicine at Mount Sinai. “This study is important because artificial intelligence can potentially more accurately distinguish whether the pain is acute or chronic, which would determine whether a patient should return to normal activities quickly or rest and schedule follow-up visits with a physician. This study also has implications for diagnosis, treatment, and billing purposes in other musculoskeletal conditions, such as the knee, elbow, and shoulder pain, where the medical codes also do not differentiate by pain level and acuity.”

CHOP researchers develop computational tool for tracking pediatric sepsis epidemiology using clinical data

Tyler O'Neal, Staff Editor INTERCONNECTS

Researchers at Children's Hospital of Philadelphia (CHOP) have developed a novel computational algorithm to track the epidemiology of pediatric sepsis, allowing for the collection of more accurate data about outcomes and incidence of the condition over time, which is essential to the improvement of care.

The tool was described in a paper published in the February 2020 issue of Pediatric Critical Care Medicine.

"We were able for the first time to have a consistent, objective, and unbiased definition of sepsis applied over a period of eight years, without having to rely on laborious and expensive manual chart review or claims data that suffer from variability across providers and time," said Scott Weiss, MD, MSCE, an attending physician in the pediatric intensive care unit at CHOP and first author of the study. {module INSIDE STORY}

Sepsis is a deadly complication to infection that occurs when the immune system stops fighting the infectious agent and instead turns on itself, attacking tissue in the lungs, kidneys and other vital organs. It is a leading cause of death in hospitals and contributes significantly to high health care costs.

Tracking the incidence of sepsis is critical to understanding the prevalence of the condition and improving outcomes and survival, but to date, there has not been an effective tool for monitoring sepsis incidence in the pediatric population. Current methods that involve gathering insurance claims data or manual chart reviews are inconsistent and often leave outpatients groups, such as those who transfer to a hospital for sepsis treatment when their sepsis was diagnosed elsewhere.

To allow for more precise tracking, the research team developed an algorithm with the help of the CHOP Research Institute's Arcus Pediatric Knowledge Network, an integrated data science platform that links the clinical and research data of more than 2 million patients. The program developed the algorithm using data from suspected or confirmed sepsis cases seen at CHOP between September 1, 2017, and June 30, 2018. Researchers then validated the algorithm on suspected or confirmed sepsis cases seen at CHOP between July 1, 2018, and January 31, 2019. 

Once researchers had developed and validated the algorithm, they then applied it to the 832,550 patients seen at CHOP in an emergency department or inpatient visit between 2011 and 2018 to gather the epidemiology of sepsis at CHOP.

They found that among more than 200,000 hospital admissions over the study period, the incidence of sepsis was 2.8%, and the incidence of sepsis among all hospital encounters increased over time after controlling for age, sex, and race. They also found that mortality was 6.7% and did not change over time, in contrast to claims-based sepsis data that have shown mortality has trended downward over time.

"This study is one example of how our program can partner with Arcus and the CHOP Research Institute to become a national leader in sepsis care," said Fran Balamuth, MD, Ph.D., Co-Director of CHOP's Center for Sepsis Excellence, Director of Research in the Emergency Department, and co-author of the paper. "The next step will be to externally validate the algorithm across different hospitals to make sure that it is not just applicable to CHOP, but at other academic children's hospitals and community hospitals as well."