Before a visit, a doctor has a few minutes to read dozens of discharge notes, test results and referrals in Cliniko or CGM and the national e-health system. A private model in the EU puts the documents from your clinic system into a chronological summary with a link to every original, and offers no diagnoses or treatment suggestions, which stay with the doctor.
Built for ISO 27001NIS2 DORA
A patient with a chronic condition or several diagnoses accumulates dozens of documents in a year: discharge notes from different providers, including those imported from the national e-health system, lab results, imaging reports, referrals, specialist opinions and e-prescription history. A visit is allotted 15 minutes, and the doctor spends part of them opening documents in Cliniko or CGM and in the e-health system viewer, looking for when the last test was and what a colleague wrote six months ago. Some information goes unread not through negligence but for lack of time, which raises the risk of errors and the number of repeated tests.
The solution is built on a private language model running in the MDP CLOUD GPU cloud in Lithuania (EU), in an environment dedicated to your practice, with no connection to public AI platforms. Before a visit (for example, the evening before, based on tomorrow's bookings in Cliniko or CGM), the solution takes that patient's documents from your clinic system, including discharge notes and e-prescription records imported from the national e-health system, and builds a chronological summary: dates, providers, test results with reference ranges exactly as written in the document, a list of prescribed medication from discharge notes and e-prescriptions, and the conclusions of referrals and consultations. Every statement carries a link to the original document and its location, so the doctor checks the source in one click. The summary deliberately does not interpret: it does not write a diagnosis, does not suggest treatment and does not assess test results, it only lays out the facts from the documents. The doctor reads the summary in a Cliniko or CGM window or in a separate panel, checks it and decides, and the summary is not written to the patient record or to the national e-health system as a medical document; only the doctor writes to the e-health system. We connect to Cliniko and CGM in read-only mode through an API, a file export or an email flow, depending on the version; we choose the method after checking. Data never leaves the EU, every summary generated and viewed is logged, access works through the user permissions in your clinic system, and the GDPR record of processing is prepared together with your data protection officer. We maintain the infrastructure like our other GPU cloud servers.
Four steps from input to a record in your system, with human approval wherever there is risk.
Based on tomorrow's list of bookings in Cliniko or CGM, the solution takes each patient's documents from your clinic system in read-only mode, including discharge notes and e-prescription records imported from the national e-health system, with the same permissions as the doctor conducting the visit. Scanned documents are first converted to text in a private environment.
The private model in the EU lays events out on a timeline and picks out test values exactly as recorded, the medication list from discharge notes and e-prescriptions, and conclusions, attaching to each statement a link to the document in Cliniko or CGM and the place in it. Contradictions and illegible passages are flagged.
The doctor opens the summary in a Cliniko or CGM window or panel before or during the visit, clicks a doubtful statement and sees the original document. All decisions, diagnosis and treatment belong to the doctor, and the summary remains a supporting tool, not written to the patient record or the national e-health system.
What was generated, for whom and who reviewed it is written to a log for GDPR. We maintain the model environment in the EU and the integration with Cliniko or CGM, check summary accuracy against the originals with your doctors every month and update the rules for what goes into a summary.
A model dedicated to your practice in the MDP CLOUD GPU cloud in Lithuania (EU) with an isolated network, no connection to public platforms and no training on your data.
Reading documents from Cliniko or CGM based on bookings through an API, an export or an email flow, and showing the summary in the doctor's window, with user permissions from your clinic system; nothing is written to the national e-health system.
An agreed structure of what the summary shows (discharge notes, tests, e-prescriptions, referrals) and what it never does, with technical restrictions and checks by your doctors during implementation.
A GDPR record of processing, impact assessment materials, an access and action log, and our support to ISO 27001 requirements.
Private model in the MDP CLOUD GPU cloud in Lithuania (EU) + Cliniko or CGM read-only integration through an API, a file export or an email flow, depending on the version; national e-health system documents are used only as far as they have already been imported into your clinic system. We choose the platform by the task and by where your data may be located; read more about this service and its limits on the service page.
No, and this is limited technically, not only by instruction: the summary is built only from statements in the documents, with links, and interpretations are filtered out. During implementation, doctors check summaries against the originals in Cliniko or CGM, and this check is repeated every month.
We connect to Cliniko and CGM in read-only mode through an API, a file export or an email flow, depending on your version and the vendor's terms; we choose the method after checking. The solution does not connect directly to the national e-health system and writes nothing there: it uses only those e-health documents and e-prescription records that have already been imported into your clinic system in the usual way.
No and no. The model runs in the MDP CLOUD GPU cloud in Lithuania (EU), in an environment dedicated to your practice, data travels between your clinic system and the model over an encrypted channel, and no public AI platform is used. The summary is shown as a supporting tool for the doctor, is not written to the patient record or the national e-health system, and the log records who viewed it and when.
The reception phone is busy, and most calls are about free appointments, test preparation and required documents.
Feedback arrives from post-visit surveys, email, Google Business Profile and the website form, and a complaint involving possible harm can sit in…
National health insurance billing reports on paid and rejected services, private insurer notices, pre-invoices and supplier invoices arrive by…
Hygiene procedures, the medication ordering process, how sick-leave certificates are issued through the social security portal, cover rules and…
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
AI systems are deployed with protection against data leakage and model abuse.
The AI security programme and its controls are managed following the ISACA methodology.
AI risks are identified and managed like any other IT risk.
We reply within 1 business day
