tushaar gangavarapu
tushaar gangavarapu
tushaar gangavarapu
80% of medical data is unstructured!
80% of medical data is unstructured!
Mr. Tushaar is a ?-year-old male, with a history of migraines, underwent Toric Collamar surgery in 2020.
Post surgery, he developed vision with halo rings (two overlapping rings around light) and dry eyes. The patient was given Hyaluronic eye drops.
80% of medical data is unstructured!
rich patient information
(de-identification)
Mr. Tushaar is a ?-year-old male, with a history of migraines, underwent Toric Collamar surgery in 2020.
Post surgery, he developed vision with halo rings (two overlapping rings around light) and dry eyes. The patient was given Hyaluronic eye drops.
80% of medical data is unstructured!
rich patient information
(de-identification)
Mr. Tushaar is a ?-year-old male, with a history of migraines, underwent Toric Collamar surgery in 2020.
Post surgery, he developed vision with halo rings (two overlapping rings around light) and dry eyes. The patient was given Hyaluronic eye drops.
clinical forecasting
pains vs. aches?
cardiac arrest vs. heart attack?
pains vs. aches?
cardiac arrest vs. heart attack?
myocardial infarction, MI?
hospital in Michigan?
pains vs. aches?
nursing notes
radiology reports
nutrition
rehab services
consultation
echo and ECG
discharge summaries
radiology reports
nutrition
rehab services
consultation
echo and ECG
discharge summaries
nursing notes
acronyms (consistency)?
acronyms (consistency)?
duplicate notes with additions
acronyms (consistency)?
duplicate notes with additions
176.49 nursing notes per patient
(4,183 patients having more than 100 nursing notes, composed of over 17,890 words)
bag-of-words?
capturing rare terms?
bag-of-words →
capturing rare terms
bag-of-words →
word2vec (skipgram)?
capturing rare terms
bag-of-words →
word2vec (skipgram) → sentence2vec
capturing rare terms
bag-of-words →
word2vec (skipgram) → sentence2vec → doc2vec
capturing rare terms
bag-of-words →
word2vec (skipgram) → sentence2vec → doc2vec
the "essence" of the note?
capturing rare terms
bag-of-words →
word2vec (skipgram) → sentence2vec → doc2vec
topic modeling (Dirichlet, multinomial)
+ Poisson
capturing rare terms
bag-of-words →
word2vec (skipgram) → sentence2vec → doc2vec
topic modeling (Dirichlet, multinomial)
+ Poisson
capturing rare terms
bag-of-words →
word2vec (skipgram) → sentence2vec → doc2vec
topic modeling (Dirichlet, multinomial)
+ Poisson
capturing rare terms
bag-of-words →
word2vec (skipgram) → sentence2vec → doc2vec
topic modeling (Dirichlet, multinomial)
+ Poisson
attention, transformer encodings, ...
code range | diagnosis |
---|---|
001-139 | parasitic and infectious diseases |
140-239 | neoplasms |
240-279 | endocrine, immunity, metabolic, and nutritional |
280-289 | blood-forming organs and blood |
|
|
code range | diagnosis |
---|---|
001-139 | parasitic and infectious diseases |
140-239 | neoplasms |
240-279 | endocrine, immunity, metabolic, and nutritional |
280-289 | blood-forming organs and blood |
|
|
multi-label classification
code range | diagnosis |
---|---|
001-139 | parasitic and infectious diseases |
140-239 | neoplasms |
240-279 | endocrine, immunity, metabolic, and nutritional |
280-289 | blood-forming organs and blood |
|
|
bi-directional?