Emily Getzen retweeted
Check out our latest review in @AmericanCancer @JournalCancer of #ArtificialIntelligence in #Oncology, led by @PennMedicine @likhitha_kolla, focused on diagnostics, prognostics, and #LLMs & #Chatbots! @HACLab_UPenn acsjournals.onlinelibrary.wi…
Emily Getzen retweeted
Want to know more about some of the challenges posed by incomplete electronic health record (EHR) data?
Check out this past blog from Emily Getzen and Dr. Long!
ldi.upenn.edu/our-work/resea…
Emily Getzen retweeted
A new study from LDI Fellows @DrQiLong and @GetzenEmily explores how missing EHR data can be leveraged to address comorbidities and improve patient monitoring.
Read more here: pubmed.ncbi.nlm.nih.gov/3822…
Emily Getzen retweeted
What AI implementors should know about healthcare before trying to "fix" it zaklab.org/blog/the-medical-… Deliberately opinionated. Comments welcome.
Emily Getzen retweeted
A new book "Statistics in Precision Health: Theory, Methods and Applications" is available:
Book Editors: Yichuan Zhao and Din Chen,
researchgate.net/publication…
Emily Getzen retweeted
Do we need to rely on DEXA for bone health risk assessment in #prostate #cancer? In press NOW @EurUrolOncol we validate a CT-based technique to predict #fracture risk in mHSPC.
🚨NEW publication in @EurUrolOnco 🚨
Can we use radiomics to measure fracture risk in prostate cancer? In this study, we validate biomechanical computed tomography (BCT) as an independent predictor of fracture among men with advanced prostate cancer.
Emily Getzen retweeted
Our new viewpoint describes five actions healthcare systems and policymakers can take to improve patient access and use of EHR portals. #EHR #amia2023 #BLM #HealthTech jamanetwork.com/journals/jam…
Emily Getzen retweeted
The rise and fall of popular transformer architectures 📈
One pro of having a lot of transformer architectures implemented in transformers & hosted on the @huggingface Hub is that one can see the evolution of popularity of different models 👀
Emily Getzen retweeted
If you see someone on the street who needs help, you can call the @PHLCityHomeless outreach hotline at (215) 232-1984. If you think someone is having a medical emergency, call 911. bit.ly/3btsCRe
Emily Getzen retweeted
"People underestimate how much benefit they get by investing the time and connecting with people.” @CIS_Penn 's @LyleUngar weighs in on what's most important to cultivating happiness: cnn.it/3puuhgc
Emily Getzen retweeted
Xylazine is showing up in illegal drugs, but little is known about its effects on the human body or how to treat the intense withdrawal symptoms it causes. Ashish Thakrar, MD, spoke with @TIME about the #addiction crisis. spr.ly/6017OmviF
Emily Getzen retweeted
Congratulations to our brilliant PhD student Benny Renn, co-advised by Ian Barnett and me, who just successfully defended his dissertation in the Biostatistics program at University of Pennsylvania!
In August he will be starting an assistant professor position at SUNY-Stonybrook!
@PennGGEB @UPennDBEI @Penn_SIVE @PennMedicine
Emily Getzen retweeted
I had to travel 26 hours and spend $2000+ to join #ICLR2023 in Rwanda.
But people in Africa have to do this every time a conference is held in US.
What happens when we make it easier to participate?
1530% higher registrations from Africa.
This is important and must continue.
Emily Getzen retweeted
Harnessing the Power of LLMs in Practice
A great comprehensive and practical guide for practitioners working with LLMs.
Discusses many use cases with practical applications and limitations of LLMs in real-world scenarios.
arxiv.org/abs/2304.13712
Emily Getzen retweeted
Missing EHR data has the potential to introduce bias into predictive models.
Learn more about the challenges of using EHR data, sources of disparities in EHR data, and implications for #HealthEquity from LDI Fellows @GetzenEmily and @DrQiLong.
ldi.upenn.edu/our-work/resea…
Emily Getzen retweeted
Congrats to @CIS_Penn PhD student @NeelayV who led this effort, colleagues Eric Wong @RICEric22, Qi Long @DrQiLong from @UPennDBEI, and our PhD students @GetzenEmily, Ziyang Li @_ziyang_, Jiani Huang @moqingyan233, Yinjun Wu @wu_yinjun, Adam Stein @adamlsteinl, and Zongyu Dai!
Congratulation to the team of @PennAsset researchers led by @AI4Code for winning honorable mention in the NIH Long Covid Computational Challenge: challenge.gov/?challenge=l3c…
Emily Getzen retweeted
In a Q&A with @PennLDI, @GetzenEmily (@PennGGEB) & @DrQiLong (@UPennDBEI) discussed their recent research finding that missing #EHR data can cause predictive models to perform poorly & further exacerbate health inequities https://nitter.cf/t.co/J2g2fGTe6x
Emily Getzen retweeted
A paper @JBI_Journal led by @GetzenEmily @PennGGEB @UPennDBEI demonstrates that incomplete data in #EHRs has adverse impact on algorithmic #fairness and worsens #healthinequity for groups with less access to healthcare. sciencedirect.com/science/ar…
Emily Getzen retweeted
Replying to @GetzenEmily
@GetzenEmily, a talented phd student @PennGGEB and @UPennDBEI led this study on comparing word embedding methods for analysis of structured and codified EHRs data collected at irregular time intervals. #DataScience #AI #EHR
Mining for Health: A Comparison of Word Embedding Methods for Analysis of EHRs Data medrxiv.org/cgi/content/shor… #medRxiv
Emily Getzen retweeted
1/4: Here’s a roundup of today’s #2021ResearchDay flash talk winners! The prize in #biostatistics went to @GetzenEmily: the #EHR holds great promise for early #disease prediction and #diagnosis—but which word embedding methods work best? #statstwitter #NLP





























