Breaking News
March 18, 2019 - Fibromyalgia can be reliably detected in blood samples
March 18, 2019 - Legacy Pharmaceutical Packaging, LLC Issues Voluntary Nationwide Recall of Losartan Potassium Tablets, USP, 25mg, 50mg, And 100mg Due to The Detection of Trace Amounts Of N-Nitroso N-Methyl 4-Amino Butyric Acid (NMBA) Impurity Found in The Active Pharmaceutical Ingredient (API)
March 18, 2019 - Researchers identify early home and family factors that contribute to obesity
March 18, 2019 - Fate and festivity: Match Day 2019
March 18, 2019 - Study finds TAVR to be as good as open-heart surgery for patients at low surgical risk
March 18, 2019 - EU-funded project is developing new tools for diagnosing cancer
March 18, 2019 - Gluten, lactose, food dyes in pills could be causing side effects finds study
March 18, 2019 - Taking painkillers during pregnancy is not responsible for asthma risk in children, study shows
March 18, 2019 - Prediagnosis Psychiatric Care Linked to Worse Cancer Mortality
March 18, 2019 - Paris hospital halts stool study after donor deluge
March 18, 2019 - Partial oral antibiotic therapy shows efficacy and safety in patients with infectious endocarditis
March 18, 2019 - Olympus improves access to science education through BioBus collaboration
March 18, 2019 - Depression screening does not improve quality of life in heart attack patients
March 18, 2019 - Echocardiography may aid in patient selection for TMVR
March 18, 2019 - Are ‘Inactive’ Ingredients in Your Drugs Really So Harmless?
March 18, 2019 - Wearable technology can safely identify atrial fibrillation
March 18, 2019 - Scientists tackle rare retinal disease in unique research project
March 18, 2019 - Death By A Thousand Clicks
March 18, 2019 - Absorbable, antibiotic-eluting envelope can reduce rate of cardiac device infections
March 18, 2019 - Hormonal treatment associated with depression in men with prostate cancer
March 18, 2019 - Porvair Sciences launches reinforced 96-well deep round microplate
March 18, 2019 - Simplified catheter ablation could slash waiting lists for atrial fibrillation patients
March 18, 2019 - BFR therapy as part of rehabilitation following ACL surgery may slow bone loss
March 18, 2019 - A human model to test implants for cataract surgery
March 18, 2019 - New risk adjustment model could reduce financial penalty for safety net hospitals
March 18, 2019 - NHS cancer patients’ wait to start treatment worrying
March 18, 2019 - Inventiva Announces Results from Phase IIb Clinical Trial with Lanifibranor in Systemic Sclerosis
March 18, 2019 - Cologuard
March 18, 2019 - Researchers find evidence of prenatal environment tuning genomic imprinting
March 18, 2019 - Dolomite Bio launches novel Nadia product family for single-cell research
March 18, 2019 - Intellipharmaceutics Announces Resubmission of New Drug Application to the U.S. FDA for its Oxycodone ER
March 18, 2019 - Excessive gestational weight gain tied to maternal morbidity
March 18, 2019 - RCEM issues position statement on metrics to supplement four-hour standard target
March 17, 2019 - Noncontrast Brain MRI Effective for Monitoring Multiple Sclerosis
March 17, 2019 - Brain region plays key role in regulation of parenting behavior, study finds
March 17, 2019 - Natural speed limit on DNA replication sets pace for life’s first steps
March 17, 2019 - New research reveals overlooked impact of herbicide glyphosate on the environment
March 17, 2019 - Molecular patterns could help predict relapse risk in breast cancer patients
March 17, 2019 - Study confirms sensitivity of microbiological cultures for detecting cholera
March 17, 2019 - Scientists Spot Clues to Predicting Breast Cancer’s Return
March 17, 2019 - Scientists identify gene that keeps PTSD-like behavior at bay in female mice
March 17, 2019 - New method would allow doctors to detect earliest stages of cancers in the lymph nodes
March 17, 2019 - Cholesterol protein discovery raises hope for smarter drugs
March 17, 2019 - New insect medium delivers high viable cell density growth and protein yield
March 17, 2019 - Opioid crisis brings concerns about heart dangers
March 17, 2019 - Resistance Training May Prevent Type 2 Diabetes Progression
March 17, 2019 - Bioluminescence sensors make new approaches to drug discovery possible
March 17, 2019 - New FDA Rules Aim to Keep Kids From Flavored E-Cigarettes
March 17, 2019 - Vitamin B3 analogue boosts production of blood cells
March 17, 2019 - Government cuts to stop smoking services have detrimental impact on public health
March 17, 2019 - Common tool to assess potential adoptive parents lags behind societal changes
March 17, 2019 - Patients’ own cells could be the key to treating Crohn’s disease
March 17, 2019 - Diagnostic delays common in inflammatory bowel disease
March 17, 2019 - Study uncovers dramatic differences in the brains of Hispanics with dementia
March 17, 2019 - Study describes epigenetic loss that changes how cells obtain energy from cancer
March 16, 2019 - Active Bathing in Non-ICU Setting Does Not Cut Infections
March 16, 2019 - How the immune system maintains a healthy gut microbiota
March 16, 2019 - Bacteria ‘trap’ could help in the fight against antimicrobial resistance
March 16, 2019 - Hospital work environment associated with all EHR usability outcomes
March 16, 2019 - Study unravels mystery behind how the brain encodes time when forming long-term memories
March 16, 2019 - Light physical activity may lower risk of cardiovascular disease in older women
March 16, 2019 - USP15 enzyme could potentially lead to new treatments for breast, pancreatic cancer
March 16, 2019 - After Chinese Infant Gene-Editing Scandal, U.S. Health Officials Join Call for a Ban
March 16, 2019 - PACS1 syndrome – Genetics Home Reference
March 16, 2019 - Researchers discover an unexpected organization of antimicrobial molecules that amplifies immune response
March 16, 2019 - With New Study, Era of Open-Heart Surgery for Aortic Stenosis May be Ending
March 16, 2019 - Dolomite Bio introduces high throughput sNuc-Seq protocol for its Nadia Instrument
March 16, 2019 - New course prepares materials scientists for biomedical testing
March 16, 2019 - Finding clues to a functional HIV cure
March 16, 2019 - People with chronic periodontitis have higher risk for dementia
March 16, 2019 - Few heart care recommendations are based on rigorous study
March 16, 2019 - Colorectal cancer diagnosed at early age is distinct from that in older patients
March 16, 2019 - Researchers use MRI and AI techniques at birth to predict cognitive development at age 2
March 16, 2019 - Discarding information from the brain linked to more mental effort, finds study
March 16, 2019 - OTA International supplement provides current snapshot and forward look at global trauma systems
March 16, 2019 - NIH trial to track outcomes of liver transplantation from HIV+ donors to HIV+ recipients
March 16, 2019 - Apple Heart Study shows how wearable technology can help detect heart problem
March 16, 2019 - Researchers determine factors that cause stress development in the human body
March 16, 2019 - Elderly Men Undertreated for Osteoporosis
March 16, 2019 - People with chronic pain are coping with the help of Pinterest, new study reveals
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