Breaking News
November 17, 2018 - new horizon in dental, oral and craniofacial research
November 17, 2018 - How does poor air quality affect your health?
November 17, 2018 - New device can regulate children’s blood glucose more like natural pancreas
November 17, 2018 - Game-Changers in Western Blotting and Protein Analysis
November 17, 2018 - FDA announces new actions to limit sale of e-cigarettes to youth
November 17, 2018 - Warmer winter temperatures related to higher crime rates
November 17, 2018 - MCO places increasing emphasis on helping people find and access healthy food
November 17, 2018 - Group of students aim to improve malaria diagnosis using old smartphones
November 17, 2018 - Transplantation of feces may protect preterm children from deadly bowel disease
November 17, 2018 - Researchers explore whether low-gluten diets can be recommended for people without allergies
November 17, 2018 - New and better marker for assessing patients after cardiac arrest
November 17, 2018 - For 7-year-old with failing bone marrow, a life-saving transplant | News Center
November 17, 2018 - New first-line treatment for peripheral T-cell lymphoma approved by FDA
November 17, 2018 - Artificial intelligence could be valuable tool to help young victims disclose traumatic testimony
November 17, 2018 - Breakthrough in the treatment of Restless Legs Syndrome
November 16, 2018 - FDA Approves Keytruda (pembrolizumab) for the Treatment of Patients with Hepatocellular Carcinoma (HCC) Who Have Been Previously Treated with Sorafenib
November 16, 2018 - Eagle Books | Native Diabetes Wellness Program
November 16, 2018 - Patients with common heart failure more likely to have lethal heart rhythms
November 16, 2018 - How AI could help veterinarians code their notes | News Center
November 16, 2018 - Bias-based bullying does more harm to students than generalized bullying
November 16, 2018 - Researchers find first direct evidence that cerebellum plays role in cognitive functions
November 16, 2018 - Non-coding genetic variant plays key role in endothelial function and disease incidence
November 16, 2018 - EMA recommends first all-oral treatment to tackle deadly sleeping sickness
November 16, 2018 - Drug used to treat dizziness may slow down growth of triple-negative breast cancer
November 16, 2018 - AHA: Icosapent Ethyl Cuts CV Risk From Elevated Triglycerides
November 16, 2018 - ‘Orphan’ RNAs make cancer deadlier, but potentially easier to diagnose
November 16, 2018 - Air Cube touches down at hospital | News Center
November 16, 2018 - CRISPR-based tool shown to enhance cell-based immunotherapy
November 16, 2018 - Mechanisms that govern HIV latency differ in the gut and blood, finds study
November 16, 2018 - Researchers unravel mystery of NPM1 protein in acute myeloid leukemia
November 16, 2018 - High school students less likely to select milk, fruit for lunch when fruit juice is available
November 16, 2018 - Football coaches with great emotional competence are more successful
November 16, 2018 - Researchers awarded $10 million grant to address root causes of asthma in Puerto Rico
November 16, 2018 - Health Tip: Manage Morning Sickness
November 16, 2018 - Infant gut microbes altered by mother’s obesity may increase risk for future disease
November 16, 2018 - Immunotherapy combination and chemotherapy show encouraging results in Phase II acute myeloid leukemia study
November 16, 2018 - ACC Latin America Conference brings experts to discuss latest cardiovascular science
November 16, 2018 - Pooled analysis of Intersect ENT’s steroid releasing implants in patients after frontal sinus surgery to be published
November 16, 2018 - Expectations about pain intensity can become self-fulfilling prophecies
November 16, 2018 - NIH awards $3.4 million to UC researchers to study gastrointestinal lymphatic system
November 16, 2018 - Highlighting Advances in Bioengineering and Analytical Technologies with eBooks
November 16, 2018 - Scientist Dr David Taylor of MR Solutions is a finalist in the BMW i UK Tech Founder Awards
November 16, 2018 - Earlier treatment could help reverse autistic-like behavior in tuberous sclerosis
November 16, 2018 - Sucking your baby’s pacifier could improve their health
November 16, 2018 - Vegetables and salad may include bacteria that are resistant to antibiotics
November 16, 2018 - Autism linked to prolonged connection between brain regions
November 16, 2018 - Endocrine Society chooses four Diabetes Caucus leaders as winners of Diabetes Champion Award
November 16, 2018 - Brain and muscle cells found within kidney organoids
November 16, 2018 - Person’s sex hormones may play key role in trauma survival, finds study
November 16, 2018 - PTEN Genetic Test: MedlinePlus Lab Test Information
November 16, 2018 - Toxic metal pollution linked with development of autism spectrum disorder
November 16, 2018 - Calcified nodules in the retina increase risk for progression to late stages of AMD
November 16, 2018 - ZEISS teams up with arivis AG to offer complete 3D imaging solutions
November 16, 2018 - Georgia State professor receives $1.2 million grant to study how the brain controls eating behavior
November 16, 2018 - Specific bacterial toxins reduce number of cells suppressing immune response
November 16, 2018 - Review by ID physician improves outcomes for outpatient parenteral antimicrobial therapy
November 16, 2018 - Conditions that produce signs similar to arthritis
November 16, 2018 - New artificial intelligence-based method predicts treatment effectiveness
November 16, 2018 - AHA: Dapagliflozin Noninferior to Placebo for MACE in T2DM
November 16, 2018 - Surgery remains best treatment for appendicitis, Stanford study finds
November 16, 2018 - Non-surgical fistula creation system Ellipsys becomes key focus of attention at CiDA
November 16, 2018 - Researchers find no link between ‘allergy friendly’ dogs and lower risk of asthma
November 16, 2018 - Researchers elucidate new rules of connectivity of neurons in the neocortex
November 16, 2018 - Treating children with ‘bubble baby disease’
November 16, 2018 - Nexus announces availability of Arsenic Trioxide Injection in the US
November 16, 2018 - Researchers find metabolite shuttle between cells in the liver that may combat tissue fibrosis
November 16, 2018 - AHA: PTSD Common Among Those Who Suffer Tear in the Aorta’s Wall
November 16, 2018 - Many RA patients’ pain related to central nervous system
November 16, 2018 - Changes in Himalayan gut microbiomes linked to diet
November 16, 2018 - Inhibition of prostaglandin E2 enhances ability to combat infectious colitis
November 16, 2018 - Chronic dry eye can slow reading rate and disrupt day to day tasks
November 16, 2018 - Researchers develop new drug molecule that inhibits inflammation
November 16, 2018 - Dementia symptoms peak in winter and spring, study finds
November 16, 2018 - Stanford tobacco researcher weighs in on JUUL
November 16, 2018 - Increasing omega-3 fatty acid intake during pregnancy reduces risk of premature birth, review finds
November 16, 2018 - Researchers find no link between infants waking up at night and later developmental problems
November 16, 2018 - Both parents and children agree about confidential medical services
November 16, 2018 - FDA warns against use of unapproved pain medications with implanted pumps
November 16, 2018 - Precision medicine-based approach to slow or reverse biologic drivers of Alzheimer’s disease
November 16, 2018 - Study provides new insight into norovirus outbreaks, may help guide efforts to develop vaccines
Predictive model could improve sepsis care

Predictive model could improve sepsis care

image_pdfDownload PDFimage_print

Researchers from MIT and Massachusetts General Hospital (MGH) have developed a predictive model that could guide clinicians in deciding when to give potentially life-saving drugs to patients being treated for sepsis in the emergency room.

Sepsis is one of the most frequent causes of admission, and one of the most common causes of death, in the intensive care unit. But the vast majority of these patients first come in through the ER. Treatment usually begins with antibiotics and intravenous fluids, a couple liters at a time. If patients don’t respond well, they may go into septic shock, where their blood pressure drops dangerously low and organs fail. Then it’s often off to the ICU, where clinicians may reduce or stop the fluids and begin vasopressor medications such as norepinephrine and dopamine, to raise and maintain the patient’s blood pressure.

That’s where things can get tricky. Administering fluids for too long may not be useful and could even cause organ damage, so early vasopressor intervention may be beneficial. In fact, early vasopressor administration has been linked to improved mortality in septic shock. On the other hand, administering vasopressors too early, or when not needed, carries its own negative health consequences, such as heart arrhythmias and cell damage. But there’s no clear-cut answer on when to make this transition; clinicians typically must closely monitor the patient’s blood pressure and other symptoms, and then make a judgment call.

In a paper being presented this week at the American Medical Informatics Association’s Annual Symposium, the MIT and MGH researchers describe a model that “learns” from health data on emergency-care sepsis patients and predicts whether a patient will need vasopressors within the next few hours. For the study, the researchers compiled the first-ever dataset of its kind for ER sepsis patients. In testing, the model could predict a need for a vasopressor more than 80 percent of the time.

Early prediction could, among other things, prevent an unnecessary ICU stay for a patient that doesn’t need vasopressors, or start early preparation for the ICU for a patient that does, the researchers say.

“It’s important to have good discriminating ability between who needs vasopressors and who doesn’t [in the ER],” says first author Varesh Prasad, a PhD student in the Harvard-MIT Program in Health Sciences and Technology. “We can predict within a couple of hours if a patient needs vasopressors. If, in that time, patients got three liters of IV fluid, that might be excessive. If we knew in advance those liters weren’t going to help anyway, they could have started on vasopressors earlier.”

In a clinical setting, the model could be implemented in a bedside monitor, for example, that tracks patients and sends alerts to clinicians in the often-hectic ER about when to start vasopressors and reduce fluids. “This model would be a vigilance or surveillance system working in the background,” says co-author Thomas Heldt, the W. M. Keck Career Development Professor in the MIT Institute of Medical Engineering and Science. “There are many cases of sepsis that [clinicians] clearly understand, or don’t need any support with. The patients might be so sick at initial presentation that the physicians know exactly what to do. But there’s also a ‘gray zone,’ where these kinds of tools become very important.”

Co-authors on the paper are James C. Lynch, an MIT graduate student; and Trent D. Gillingham, Saurav Nepal, Michael R. Filbin, and Andrew T. Reisner, all of MGH. Heldt is also an assistant professor of electrical and biomedical engineering in MIT’s Department of Electrical Engineering and Computer Science and a principal investigator in the Research Laboratory of Electronics.

Other models have been built to predict which patients are at risk for sepsis, or when to administer vasopressors, in ICUs. But this is the first model trained on the task for the ER, Heldt says. “[The ICU] is a later stage for most sepsis patients. The ER is the first point of patient contact, where you can make important decisions that can make a difference in outcome,” Heldt says.

The primary challenge has been a lack of an ER database. The researchers worked with MGH clinicians over several years to compile medical records of nearly 186,000 patients who were treated in the MGH emergency room from 2014 to 2016. Some patients in the dataset had received vasopressors within the first 48 hours of their hospital visit, while others hadn’t. Two researchers manually reviewed all records of patients with likely septic shock to include the exact time of vasopressor administration, and other annotations. (The average time from presentation of sepsis symptoms to vasopressor initiation was around six hours.)

The records were randomly split, with 70 percent used for training the model and 30 percent for testing it. In training, the model extracted up to 28 of 58 possible features from patients who needed or didn’t need vasopressors. Features included blood pressure, elapsed time from initial ER admission, total fluid volume administered, respiratory rate, mental status, oxygen saturation, and changes in cardiac stroke volume — how much blood the heart pumps in each beat.

In testing, the model analyzes many or all of those features in a new patient at set time intervals and looks for patterns indicative of a patient that ultimately needed vasopressors or didn’t. Based on that information, it makes a prediction, at each interval, about whether the patient will need a vasopressor. In predicting whether patients needed vasopressors in the next two or more hours, the model was correct 80 to 90 percent of the time, which could prevent an excessive half a liter or more of administered fluids, on average.

“The model basically takes a set of current vital signs, and a little bit of what the trajectory looks like, and determines that this current observation suggests this patient might need vasopressors, or this set of variables suggests this patient would not need them,” Prasad says.

Next, the researchers aim to expand the work to produce more tools that predict, in real-time, if ER patients may initially be at risk for sepsis or septic shock. “The idea is to integrate all these tools into one pipeline that will help manage care from when they first come into the ER,” Prasad says.

The idea is to help clinicians at emergency departments in major hospitals such as MGH, which sees about 110,000 patients annually, focus on the most at-risk populations for sepsis. “The problem with sepsis is the presentation of the patient often belies the seriousness of the underlying disease process,” Heldt says. “If someone comes in with weakness and doesn’t feel right, a little bit of fluids may often do the trick. But, in some cases, they have underlying sepsis and can deteriorate very quickly. We want to be able to tell which patients have become better and which are on a critical path if left untreated.”

Source:

http://news.mit.edu/2018/machine-learning-sepsis-care-1107

Tagged with:

About author

Related Articles