Enhance clinical decision making with facts from medical documents
Case Study:
Improve Patient Flow Forecasting
Key factors that influence a patient’s flow (How likely they are to admitted? For how long? For what?):
Volume of arrivals
Outpatient
Referrals
Emergency Room
Operation Room
Admission specialty
Oncology
Hip-replacement
Renal Disease
Cardiology, …
Timing of arrival
Hour of the day
Day of the week
Holidays
Seasonal variables
Flu season
Natural disasters
Patient's length of stay
per unit (ICU, CVICU, …)
Nurse staffing levels & skill mix:
Certified Nurses
Licensed N.P.’s
Unlicensed Staff
Unique certifications
Results
The results of an NLP pipeline are often used as features in another machine learning model, that also leverages all the available structured data signals.
John Snow Labs enabled real-time decision-making and strategic planning, by predicting:
states started last night, upper abd, took alka seltzer approx 0500, no relief. nausea no vomiting
Since yeatreday 10/10 “constant Tylenol 1 hr ago. +nausea. diaphoretic. Mid abd radiates to back
Generalized abd radiating to lower x 3 days accompanied by dark stools. Now with bloody stool this am. Denies dizzy, sob, fatigue. Visiting from Japan on business.”
Features
Type of Pain
Intensity of Pain
Body part of region
Symptoms
Onset of symptoms
Attempted home remedy
Why John Snow Labs?
01
Clinical Language Understanding
02
State of the Art Accuracy
03
Tuned to Emergency Room Jargon
Case Study:
Precision Medicine
Recommending the next best action requires biomarkers that are only available in pathology, radiology and sequencing.
Spark NLP can automatically extract specific tumor characteristics and automate knowledge extraction from pathology reports
Demos
