More effective and cheaper care through the digitization of conversations
Secure and organized note taking at the touch of the button
Better archiving and information availability
Join the waiting list
Accurate voice-to-text transcriptions for healthcare professionals.
HealthTalk is a secure, cloud-based medical speech recognition solution that enables the digitization of conversations between the healthcare provider and the patient.
How Does it works
1 step
Appointment Scheduling
- Patients can book appointments with doctors in affiliated hospitals.
- Get appointments from all Dutch Hospitals using MedMij
- Connect to your Hospital agenda
2 step
Intake
We perform an extended intake that consists of the following modules:
- Based on the Hospitals’ clinical workflow
- Get data from all 8.400 Dutch healthcare institutes
- Get data from any PGO (Personal Health Environment)
- Standardised and clinical validated questionnaires (PROM)
3 step
Collect biomarkers
We are able to collect various vital signs using the camera of your mobile in just 1 minute including:
- pressure
- heart rate
- heart rate variability
- oxygen saturation
- breathing rate
- sympathetic stress
- parasympathetic activity
- pulse-respiration quotient (PRQ)
Groundbreaking bloodless blood tests (under research) enable measuring hemoglobins, hemoglobins A1C, and cholesterol total. More additional blood tests coming soon.
4 step
Patient summary
Based on all the user generated input, or from other Doctors, we will generate a simple and understandable summary for the Doctor just before the meeting
5 step
Doctors consultation
Provides a mechanism for each healthcare provider and their patients to perform automated clinal note taking.
Speech to text into clinical vocabularies based on MeSh and UMLS coding systems.
Automatically we move the spoken text into the SOEP (Subjective, Objective, Evaluate, and Plan) model.
6 step
Automated reporting
Based on the clinical vocabularies we will create the SOAP model (or SOEP model in Dutch) that will be the input for patient and referral letters that could either be created automatically, or dictated by the healthcare provider.
This letter or report will be sent to the healthcare provider (in technical format) to include into their Health Records system or to the patient..
Assertion Detection
The meaning of medical content is highly affected by modifiers, such as negative or conditional assertions which can have critical implications if misrepresented.
Analytics for health supports three categories of assertion detection for entities in the text:
- Certainty
- Conditional
- Association
Named Entity Recognition
Named Entity Recognition detects words and phrases mentioned in unstrucutred text that can be associated with one or more semantic types, such as diagnosis, medication name, symptom/sign, or age.
.png){kind=spacer}
Relation extraction
Relation extraction identifies meaningful connections between concepts mentioned in text.
For example, a "time of condition" relation is found by associating a condition name with a time or between an abbreviation and the full description.
.png){kind=spacer}
Entity linking
Entity linking disambiguates distinct entities by associating named entities mentioned in text to concepts found in a predefined database of concepts including the Unified Medical Language System (UMLS).
Medical concepts are also assigned preferred naming, as an additional form of normalization.
.png){kind=spacer}
Assertion Detection
The meaning of medical content is highly affected by modifiers, such as negative or conditional assertions which can have critical implications if misrepresented.
Analytics for health supports three categories of assertion detection for entities in the text:
- Certainty
- Conditional
- Association
.png){kind=spacer}
7 step
Automated Clinical Decision support
(in research phase)Based on the clinical vocabularies we provide a query on PUBmed SUBmed to give the most relevant papers for the best Treatment suggestion.
