Articles on AI in healthcare
This page collects our team's technical articles, case studies and notes on sector developments. The articles cover AI in healthcare, ethics and where the sector is heading.
A three-layer model architecture for Turkish clinical language and 14 specialties
MINA’s open-weight base model was adapted to Turkish and the clinical language of 14 specialties through continued pre-training. LoRA adapters add specialty, institution and task expertise, and agentic orchestration over a clinical knowledge graph draws on 30M+ sources.
Read articleStructuring the discharge summary for ICD-10 coding and SUT checks
Discharge summaries and reports become structured fields in the patient twin; ICD-10 suggestions and SUT checks move ahead of payment, and gaps are flagged in advance. The physician gives the final approval.
Read articleContinuously monitoring inventory thresholds and audit indicators
MKYS inventory data is scanned every day against the 60- and 90-day thresholds, and BH and ADSH indicators are monitored continuously, so loss and audit risk reach management before they materialize.
Read articleDividing the work between the rule engine, AI and people
In health and insurance workflows, the rule engine carries out the assessment, AI explains the reasoning and the source, and a person makes the decision. The article covers why document and inference are kept apart, the six separate rules defined for six pharmacy rejection types, and how every output can be audited.
Read articleA ready file for the medical reviewer at pre-authorization
From pre-authorization to reimbursement, policy analysis, limit tracking, file history, SUT compliance and clinical context reach the medical reviewer ready on one page. The final decision stays with the insurer's medical specialists.
Read articlePatient and physician data twins bring scattered records into a single view
The patient twin merges HBYS and Medula data into one live profile; the physician twin turns test, coding and treatment patterns into personalized, reasoned decision support. The data stays inside the institution.
Read articleThe measurable case for localized payer AI
Fraud and claim leakage occur in every country, but the rules that catch them are local.
Read articleClinical AI that keeps data inside the institution
For health institutions, the first question about AI is where the data goes, even before accuracy. In our approach, the data does not leave the institution.
Read articleWhat building clinical AI in Türkiye taught us
We did not start in an easy market. The platform can be taken to other markets mainly because it was developed under Türkiye's complex regulations.
Read articleWhy generic AI fails on local clinical reality
Generic LLMs produce impressive results, but they fall short when they meet a real health system's coding, language and rules.
Read articleThe AI perception crisis in healthcare
In Türkiye, AI in healthcare is often equated with chatbots. This narrow view makes it harder for institutions to see where AI can help with data analysis and decision support.
Read articleDigital chaos in healthcare
The data management problem known as “data chaos” makes it harder for healthcare institutions to make accurate and timely decisions.
Read articleChatbot psychosis
There is growing discussion that intense, prolonged use of chatbots may distort some users’ sense of reality. The concept is not yet defined in the clinical literature.
Read articleA new era in health insurance fraud detection
AI-supported audit systems help health insurers spot fraudulent and inflated claims earlier.
Read articleIs it possible to copy human health?
Digital twin technology aims to build a dynamic digital model from a person’s health data. It opens new possibilities for personalized diagnosis and treatment planning, but it also raises ethical and security questions.
Read articleData manipulation through artificial intelligence
AI systems are only as reliable as the data they are given. In healthcare, manipulated or incomplete data can lead to consequences as serious as incorrect diagnosis and treatment.
Read articleThe future triangle in healthcare
AI is joining the traditional doctor-patient relationship and turning it into a triangle. As information becomes easier to access, protecting empathy and human contact becomes an important question.
Read articleDigital threat in healthcare
Incorrect and fabricated outputs, known as AI hallucinations, are on the agenda as a new risk to patient safety in healthcare.
Read articleAI chatbots are increasing doctors’ workload
Unverified medical information that patients get from general-purpose chatbots creates a need for extra explanation during visits and can affect the doctor-patient relationship.
Read article