Yerkezhan Tleukulova

Ms. Yerkezhan Tleukulova

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 November 2026 in Information
Verified
Journal Article
Open access
PDF file
YTYerkezhan Tleukulova
Yerkezhan Tleukulova
Madina MansurovaMadina Mansurova
Madina Mansurova
ENElmira Shodmonovna Nazirova
Elmira Shodmonovna Nazirova
SKSabira Kulchimbayeva
Sabira Kulchimbayeva
ZTZhuldyz Talasbayeva
Zhuldyz Talasbayeva
Talshyn SarsembayevaTalshyn Sarsembayeva
Talshyn Sarsembayeva
Perinatal depression affects a large share of women during pregnancy and after childbirth, yet access to perinatal mental health care in Kazakhstan is limited. This paper presents MamaCare, a multi-agent platform based on open-weight Qwen3.5 large language models (LLMs) that provides conversational support, administers standardized screening instruments, and triages red-flag situations in Kazakh, Russian, and English. Two physician experts rated 286 single- and multi-turn sessions against a rubric adapted from HealthBench and ThReadMed-QA; mean scores for the accuracy, safety, and communication criteria ranged from 4.45 to 4.93 out of 5, and the lowest-scoring criterion was turn-level degradation (3.71). The platform was then compared with five prompt-engineered configurations of its own base model on 120 stratified cases, and every automated judgment was repeated with three judges from three model families: Qwen3.8-27B, Gemma-3-27B, and a Kazakh-adapted Llama-3.1-8B. In red-flag triage, MamaCare had the lowest false-alarm rate of all six configurations under all three judges and against physician urgency labels for the 58 cases on which any judge raised an alarm, and a prompt-only safety configuration escalated routine questions 3.6 to 4.2 times more often; agreement between judges was substantial for urgency labelling (Cohen’s κ = 0.67 and 0.79) and for escalation detection (κ = 0.78 and 0.47). Pairwise preference did not survive the same test (κ = 0.30, with 15.3% to 45.7% of verdicts reversing when the answer order was swapped) and is therefore reported as judge-dependent evidence rather than as a result. Retention of facts from earlier turns was the platform’s weakest property (71.8%); adding a structured patient-state handoff between agents raised it to 97.4% under both judges that measure it reliably, without increasing false alarms and with shorter answers. On a new holdout set of 15 parallel multi-turn dialogues in the three languages, written after the platform was fixed, physician-rated fact retention over the 10 completed dialogues was 0.85 (95% CI 0.74–0.91), with no difference between languages; the main multi-turn errors were information carried over from the user profile and replies truncated by server time-outs.