Bibliographic record
Abstract
AI Device Aims to Diagnose Sepsis Rapidly The Sepsis ImmunoScore from Prenosis, Inc., an AI-powered device designed to diagnose sepsis rapidly, has received marketing authorization from the FDA, according to a company press release. (April 3, 2024; https://tinyurl.com/5622mvf4.) It is the first AI diagnostic tool for sepsis granted such authorization.Figure: AI, sepsis, diagnosis, Sepsis Immunoscore, Prenosis, FDA, artificial intelligence, machine learning, ICU, biomarkers, vasopressor, EMRs, ultrasound, arm fractures, portable ultrasound, Ultrasound Arm Injury Detection Tool, wrist, arm, shoulder, x-ray, MRI, physician burnout, Ambience Healthcare, documentation, AutoScribe, AutoCDI, AutoAVSThe Sepsis ImmunoScore is a medical device powered by machine learning software that guides rapid diagnosis and prediction of sepsis, leveraging a combination of 22 biomarkers and clinical data through AI to assess a patient's risk of sepsis within 24 hours of assessment in the emergency department. It then gives a risk score and four risk categories. These categories correlate to a patient's risk of deterioration represented by length of stay in the hospital, in-hospital mortality, and escalation of care within 24 hours, such as ICU admission, mechanical ventilation placement, and vasopressor use. This combination of diagnostic and predictive information has never been available in a legally marketed device for sepsis, according to the press release. The Sepsis ImmunoScore's software is integrated directly into hospital EMRs, making it easily accessible for physicians. An intuitive display reveals how each patient's parameters was used to calculate a final sepsis score. This facilitates faster treatment decisions, improved outcomes, quality metrics, and better hospital financials. AI Ultrasound Designed to Detect Arm Fractures A researcher developing a portable ultrasound tool that uses AI to detect arm fractures has received more than $700,000 for further research, according to a press release from the company making the grant. (Feb. 26, 2024; https://tinyurl.com/2tb288ua.) Abhilash Hareendranathan, an assistant professor of radiology and diagnostic imaging at the University of Alberta, developed the Ultrasound Arm Injury Detection tool. He said it could shorten wait times and save money in emergency departments by allowing triage nurses and physicians to scan for wrist, arm, and shoulder injuries quickly instead of waiting for an x-ray. Dr. Hareendranathan received $748,500 in February from Alberta Innovates, a group that provides funding, business advice, and industrial testing facilities to accelerate research and innovations. The Ultrasound Arm Injury Detection tool automates the process of capturing an ultrasound image, allowing it to be used by nurses and physicians who have less training using imaging equipment than a sonographer or radiologist. The patient will get a follow-up x-ray or MRI to confirm the diagnosis when a fracture is detected. A condition of the funding is Dr. Hareendranathan has up to three years to validate his system with patients at a pediatric emergency department in Edmonton. Operating System Takes Aim at Physician Burnout The San Francisco startup Ambience Healthcare says AI could help solve physician burnout. The company recently received $70 million in funding to develop a suite of applications designed to alleviate burnout, improve overall system efficiency, and enable high-quality care, according to a company press release. (Feb. 21, 2024; https://tinyurl.com/59xr8kcc.) Ambience's products support nonlinear, fast-paced documentation flows in the emergency department, including critical care documentation and consults with paramedics and specialists. The Ambience operating system currently includes several AI-powered tools. AutoScribe is a real-time AI medical scribe that generates comprehensive notes across all specialties, including emergency medicine, and integrates directly with all major EMRs. Another tool, AutoCDI, aims to improve clinical documentation by analyzing health records and notes. AutoRefer improves handoffs by composing clinically relevant and well-organized referral letters to specialists for expert consult and from specialists back to primary care for long-term management. AutoAVS is an after-visit summary tool that creates comprehensive educational handouts for patients, families, and caregivers tailored to each visit and translated into their language of preference. These applications reduce documentation time by an average of 78 percent and improve coding integrity, according to the press release. MR. MATHERS is the associate editor of Emergency Medicine News.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.008 | 0.007 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.469 | 0.523 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".