# An AI pipeline for recognizing and structuring retrospective psychiatric discharge records from digitized archives - URL: https://alisanburak.com/en/wcp-2026-posterler/ev0477 - Language: en - Last updated: not specified - Page title: An AI pipeline for recognizing and structuring retrospective psychiatric discharge records from digitized archives | WCP 2026 Summary > A five-stage pipeline combining OCR and a large language model converted paper psychiatric discharge summaries into a structured research database of 14,554 re… This page was translated automatically from Turkish. [Read the original](https://alisanburak.com/wcp-2026-posterler/ev0477) This page is an AI-assisted Turkish summary of the study presented at the 26th World Congress of Psychiatry. The study belongs to the presenting authors; please refer to the original source when citing it. EV0477 E-PosterDigital Psychiatry and Artificial IntelligenceMethod development study (retrospective archive) # An AI pipeline for recognizing and structuring retrospective psychiatric discharge records from digitized archives ARTIFICIAL INTELLIGENCE PIPELINE FOR RECOGNIZING AND STRUCTURING RETROSPECTIVE PSYCHIATRIC DISCHARGE RECORDS FROM DIGITIZED ARCHIVES Presenter: Andrey Sheyanov Country: Russian Federation Institution: Mental Health Research Centre A five-stage pipeline combining OCR and a large language model converted paper psychiatric discharge summaries into a structured research database of 14,554 records, achieving high completeness across key clinical fields. The aim was to develop and evaluate an end-to-end artificial intelligence pipeline that converts heterogeneously digitized psychiatric discharge records into a validated relational research database suitable for epidemiological analysis. The source material consisted of paper discharge summaries from two inpatient units at a federal mental health research center in Moscow: 112 multi-record PDFs from 2011–2023, together with JPG and HEIC photographs of pages, totaling 429 unique source files and covering admissions from 2003–2023; consecutive inclusion was used, with no probability sampling. The five-stage pipeline comprises conversion of pages into images; optical character recognition using Yandex Vision (OCR, with Tesseract as a local fallback); structuring into JSON using YandexGPT according to a field-level system prompt (temperature 0.2, maxTokens 6,000, an input limit of 45,000 characters, and documents exceeding 50,000 characters split at institutional headers and then reassembled); validation (date normalization, mandatory patient-name checks, and deduplication using file_hash; responses with fewer than 30% of fields populated are quarantined rather than entered into the database); and storage in SQLite. The pipeline produced 14,554 records, extracting more than 40 structured fields per admission. Field completeness in the extracted records was as follows: patient name 100.0%, admission date 98.5%, discharge date 97.9%, ICD-10 code 94.5%, diagnosis text 93.9%, mental status 90.0%, treatment administered 89.3%, life history 85.8%, age at admission 83.1%, date of birth 79.0%, treatment outcome 67.1%, and family history 56.6%. Through prompt engineering, the system prompt was reduced from approximately 43 KB to approximately 12 KB, and maxTokens from a range of 6,000–8,000 to 4,000; this yielded an approximately 70% reduction in tokens per document without a measurable loss in field completeness. The authors report that the same setup can be transferred to other centers and languages, and that deduplication is essential (otherwise, multi-patient PDFs silently generate duplicate records). The stated limitation is that completeness does not imply validated accuracy, and field-level agreement with the source document has not yet been quantified. [View the original poster](https://cslide.ctimeetingtech.com/wcp26/attendee/eposter/file/2106) How to cite this study APA 7: Sheyanov, A., Sheyanova, Y., Romanov, D., & Volel, B. (2026, September 23-26). Artificial intelligence pipeline for recognizing and structuring retrospective psychiatric discharge records from digitized archives [E-poster]. 26th WPA World Congress of Psychiatry (WCP 2026), Stockholm, Sweden. https://cslide.ctimeetingtech.com/wcp26/attendee/eposter/file/2106 Vancouver: Sheyanov A, Sheyanova Y, Romanov D, Volel B. Artificial intelligence pipeline for recognizing and structuring retrospective psychiatric discharge records from digitized archives [e-poster]. 26th WPA World Congress of Psychiatry (WCP 2026); 2026 Sep 23-26; Stockholm, Sweden. Available from: https://cslide.ctimeetingtech.com/wcp26/attendee/eposter/file/2106 Author names and title formatting were generated automatically from the congress system; please check them against the original poster before use. ## On the same topic - [Siber tanıkların davranışını belirleyen etkenler](https://alisanburak.com/en/wcp-2026-posterler/ev0041) - [Z kuşağında sosyal medyanın "lunapark etkisi"nin modellenmesi: örtük değişken yaklaşımı](https://alisanburak.com/en/wcp-2026-posterler/ev0046) - [DEHB'de dijital girişimler: etkililik ve çok modlu tedavi yaklaşımlarına entegrasyon](https://alisanburak.com/en/wcp-2026-posterler/ev0072) - [Algoritmaların inşa ettiği beyinler: dijital çağda DEHB, patolojiyi mi tanılıyoruz yoksa yeni bir normali mi patolojikleştiriyoruz?](https://alisanburak.com/en/wcp-2026-posterler/ev0077) - [Genç erişkin bir örneklemde nomofobi ile yaygın anksiyete bozukluğu arasındaki ilişki](https://alisanburak.com/en/wcp-2026-posterler/ev0111) [All WCP 2026 summaries](https://alisanburak.com/en/wcp-2026-posterler) --- Kaynak / Source: https://alisanburak.com/en/wcp-2026-posterler/ev0477 İletişim / Contact: Bağdat Caddesi, Veli Güneysu Apt. No:453 K:4 D:9, Suadiye / Kadıköy, İstanbul · +90 532 642 95 25 · info@alisanburak.com · https://alisanburak.com/bagdat-caddesi-psikoterapi-iletisim