Supreeth Shashikumar (@spshash) profile picture

Research scientist @UCSDHealth working on improving healthcare delivery using machine learning. Formerly: PhD @GeorgiaTech, @MSFTResearch, @qualcomm_in

San Diego, CA
Joined June 2016
Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)Photo by Supreeth Shashikumar (@spshash)
Supreeth Shashikumar retweeted
🚨 New study alert! Wearable devices + multiscale entropy = better prediction of unplanned hospital readmissions. Promising step for AI in healthcare! #AI #Wearables #HealthcareInnovation Great work by @vishal15n @WardiGabriel @spshash @AtulMalhotra13 academic.oup.com/jamia/artic…
6
1
20
2,078
Supreeth Shashikumar retweeted
4/5 In an ER setting, ordering of blood culture is often followed by administration of antibiotics, therefore it's not clear if providers will wait for a AI risk score to initiate treatments for sepsis. Moreover, all cases without a clinical suspicion of sepsis will be missed!
1
1
2
354
Supreeth Shashikumar retweeted
Great working with @ABoussina @spshash @AtulMalhotra13 @ShamimNemati to get this important work out there! That you for highlighting this important work on #sepis and #ai in healthcare!
1
2
10
733
Supreeth Shashikumar retweeted
2/4 The composer platform leverages #FHIR and #AWS cloud to enable real-time predictive analytics for various clinical scenarios, such as sepsis, respiratory failure, and deterioration, among others. It also integrates with existing #EHR systems and clinical workflows.
1
1
6
233
Supreeth Shashikumar retweeted
1/4 Deployment of COMPOSER AI platform was associated with a 1.9% absolute reduction (17% relative decrease) in in-hospital #sepsis mortality, a 5.0% absolute increase (10% relative increase) in sepsis bundle compliance, and a 4% reduction in 72h SOFA change after sepsis onset.
Can a novel #DeepLearning algorithm to predict #sepsis in the emergency department improve care? Researchers from @UCSDHealth show proper implementation of the model can save lives of sepsis patients and improve quality metrics. nature.com/articles/s41746-0…
5
11
1
44
9,055
Supreeth Shashikumar retweeted
Great collaborative effort with @ShamimNemati @spshash @ABoussina to put this forward. And huge thanks to the wonderful residents @UCSDEMResidency for attending the presentation at #ACEP23!
3
1
1
26
2,193
Supreeth Shashikumar retweeted
MCoPet (Mobile Companion Pet) can now talk in different languages, communicate with #EHR via #FHIR, connect to #wearables & #IoT devices, and analyze a host of inclusive and insightful personal health-related data via #ArtificialIntelligence.
Voice-Enabled Response Analysis Agent (VERAA): Leveraging Large Language Models to Map Voice Responses in SDoH Survey medrxiv.org/cgi/content/shor… #medRxiv
4
16
2,402
Supreeth Shashikumar retweeted
Great article by our #AWS partner featuring the Amazon Research Award winner @spshash & the brain behind our #sepsis #AI & quality improvement efforts @UCSDHealth: amazon.science/research-awar…
Thanks to @beckersHR for highlighting our efforts in using #AI for early #sepsis prediction @UCSDHealth! A true team effort with @CALonghurst @ShamimNemati @ABoussina @AtulMalhotra13 to get this going! @ucsdpccsm @SepsisAlliance beckershospitalreview.com/in…
2
3
13
4,080
Supreeth Shashikumar retweeted
Interested in how to make your predictive models more clinically relevant? Check out our viewpoint on strategies to do this in @CritCareMed! @ShamimNemati @CALonghurst @AtulMalhotra13 @DrBobOwens journals.lww.com/ccmjournal/…
6
11
1,504
Supreeth Shashikumar retweeted
Nice work by @FatemehAmrollah, @spshash, @NathanYungMDMS showing wearable data can predict #sepsis readmissions @CALonghurst @AtulMalhotra13 Predicting Hospital Readmission among Patients with Sepsis using Clinical and Wearable Data medrxiv.org/content/10.1101/…
2
1
8
778
Supreeth Shashikumar retweeted
1/4) >$4.6 billion in excess cost savings for CMS! Check out this interesting work by @parker_rog and colleagues: "Optimizing the Implementation of Clinical Predictive Models to Minimize National Costs: A Sepsis Case Study": preprints.jmir.org/preprint/… #digitalhealth via @jmirpub
1
5
1
19
4,093
Supreeth Shashikumar retweeted
Loving that @AllofUsResearch is producing these #plainlanguagesummaries. Check out the #ResearchHighlight about a study that used social determinants of health data to model sepsis readmission from @WardiGabriel and colleagues - allof-us.org/3V15afK #SciComm
1
1
7
Supreeth Shashikumar retweeted
A new model using social determinants of health (#SDOH) data from All of Us participants better predicts which patients with sepsis, a serious infection, may have to return to hospital. Check out our #ResearchHighlight about a study published in #JAMIA: allof-us.org/3V15afK
4
1
15
Hospital AI learns to say "I don't know" when faced with erroneous data, reducing false alarms when it comes to predicting who's at greatest risk for sepsis New in @NaturePortfolio by Supreeth Shashikumar @WardiGabriel @AtulMalhotra13 @ShamimNemati ucsdhealthsciences.tumblr.co…
1
1
1
10
Supreeth Shashikumar retweeted
Awesome work by a great team - the computer beats the expert again but this time it says “I don’t know” when appropriate rather than spewing out nonsense - I think a major key to getting clinician buy in #ucsd #ats2021 #nature_npj #sepsis #SCCM – at Houston, TX
2
19