StayCurrentMD
Sepsis
Everything in the library about sepsis — built automatically from the recorded discussions that name it
Educational content from recorded physician discussions — not medical advice. Always talk to your child's care team about your child's situation.
Content of this collection
Acute Management
1 item
Surviving Sepsis - APSA Practice Gaps 2019
Watch →
At the 7th Annual Pediatric Surgery Update Course, Dr. Saleem Islam discusses surviving sepsis guidelines, one of the 2019 practice gaps identified by the American Pediatric Surgical Association’s Professional Development Committee.
video · Mar 2020
Emerging & Future Directions
3 items
#APSA50: Artificial Intelligence
Listen →
This episode is the third in our #APSA50 series, where we teamed up with the Behind the Knife Podcast to cover the 50th Anniversary Meeting of the American Pediatric Surgical Association. In this episode, we interviewed the Dr. Michael Muel
podcast15:04 · Dec 2020
Artificial Intelligence Applications in Healthcare - Transforming Healthcare, Episode 7, Part 2
Watch →
In a previous video we introduced the concept of artificial intelligence aka AI. In this video we’ll discuss the way to apply AI in healthcare with some examples. Here’s what you need to know in a nutshell!
Host: Em Tombash, MD
Curren
video · Sep 2022
2022 Pediatric Surgery Update Course - Top disruptive technologies in medicine
Watch →
In this session, Drs. Ramy Shaaban and Em Tombash guide us through the most disruptive technologies of the last year. What innovations are going on in the world? They explain each one. An amazing trip on what is coming and how the future ma
video26:52 · Jul 2026
Summaries and takeaways+ Show
The doctors in this collection+ Show
All expert statements+ Show
Every expert statement below comes from the recorded discussions, with its speaker and moment.
#APSA50: Artificial Intelligence
At the Radiological Society of North America annual meeting, there are about 100 to 150 AI startups presenting in the machine learning showcase, with some products available for purchase and deployed at healthcare systems.
epidemiologicalMichael Muley1:46 ↗
Yale has deployed AI for prioritization of head CTs with bleeds, cutting down the time until a radiologist reviews the study.
clinicalMichael Muley2:24 ↗
Most current AI applications in radiology are in the operational realm, augmenting workflow rather than making diagnostic decisions.
clinicalMichael Muley2:45 ↗
Radiology jobs are here to stay despite AI advances.
opinionMichael Muley3:03 ↗
AI applications in healthcare offer tremendous opportunity to achieve a truly evidence-based medical system.
opinionMichael Muley3:35 ↗
What surgeons are taught during surgical training is what they will do in practice, and most of the time there is no evidence behind it, or the evidence is very weak.
clinicalMichael Muley3:58 ↗
Laparoscopic surgery offers a natural opportunity for AI because it captures data digitally with video.
clinicalMichael Muley4:43 ↗
Surgical robots are not currently using AI tools primarily for regulatory reasons, but will start to incorporate them once that hurdle is overcome.
opinionMichael Muley4:50 ↗
Trauma triaging is currently done based on very simple rules and is not very data driven.
clinicalMichael Muley5:28 ↗
AI impact on the actual operating room (outside of operational tasks) will take a lot longer, if it happens at all.
opinionMichael Muley5:42 ↗
A simple sepsis alert system based on four criteria (elevated or low white count, temperature, heart rate) was rolled out at Penn State but failed because it was a simple rule set that went off all the time.
clinicalMichael Muley6:29 ↗
With deep learning, sepsis alerts can be much more sophisticated, and some places like Emory have sepsis alerts deployed into the workflow.
clinicalMichael Muley7:06 ↗
Deep learning requires very large datasets because the neural networks learn just by example and need many examples with good variety of the data space.
clinicalMichael Muley7:45 ↗
In radiology, whether a GE or Siemens device is used may affect what the algorithm learns.
clinicalMichael Muley8:11 ↗
The current limitation for AI in healthcare is access to very large datasets, especially compared to other domains where billions of data points are available daily.
clinicalMichael Muley8:19 ↗
The more specific the disease or patient population (such as pediatric surgery), the harder it becomes to collect large, high-quality labeled datasets.
clinicalMichael Muley8:45 ↗
Tesla has 100,000 to 200,000 cars driving around every day collecting data for training self-driving capability.
epidemiologicalMichael Muley9:11 ↗
Waymo has collected about 10 million miles of driving experience for self-driving cars.
epidemiologicalMichael Muley9:26 ↗
It is very difficult to generate large datasets in healthcare because data collection must fit into clinical workflow, cannot be easily simulated, and faces technical, organizational, and regulatory barriers.
clinicalMichael Muley9:34 ↗
Deep learning models are very good at learning associations from images if given enough data, but they learn whatever association is present, including spurious ones.
clinicalMichael Muley10:26 ↗
In melanoma image recognition, AI learned that the presence of a ruler in the picture was associated with malignancy.
host_summaryAlexander Gibbons10:12 ↗
On CT scans, markers that exist outside the patient may tip the algorithm that the scan is from a particular hospital with different disease prevalence.
clinicalMichael Muley10:45 ↗
Cloud-based data infrastructure is the way data centers in general and healthcare specifically will operate in the future, opening opportunities for access to larger datasets.
opinionMichael Muley11:17 ↗
Once data is centralized in the cloud, it becomes much easier to create frameworks that allow data sharing between institutions for research purposes, while still maintaining access controls.
clinicalMichael Muley11:33 ↗
A model trained on data in the US may not work anywhere else due to differences in patient populations.
clinicalMichael Muley12:26 ↗
If there is any racial or ethnic bias in training data, the AI model will have that bias as well.
clinicalMichael Muley12:36 ↗
Training a machine learning model is actually a very small part of what needs to be done to deploy AI in healthcare.
opinionMichael Muley13:00 ↗
How the FDA will decide what is a safe medical device for AI applications remains an unsolved question.
clinicalMichael Muley13:05 ↗
Even if AI models are not better than humans, they are much more consistent, which is their great promise.
opinionMichael Muley13:21 ↗
There is huge variance between how different radiologists read studies, sometimes incorrectly and sometimes due to differences of opinion.
clinicalMichael Muley13:33 ↗
What's new+ Show