# Feeling better, byte by byte: Effectiveness and safety of AI-supported interventions in the management of major depressive disorder - URL: https://alisanburak.com/en/wcp-2026-posterler/ev0468 - Language: en - Last updated: not specified - Page title: Feeling better, byte by byte: Effectiveness and safety of AI-supported interventions in the management of major depressive disorder | WCP 2026 Summary > AI-based clinical decision support and session analytics tools improve symptom outcomes and treatment retention in major depressive disorder, while prognostic… This page was translated automatically from Turkish. [Read the original](https://alisanburak.com/wcp-2026-posterler/ev0468) 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. EV0468 E-PosterDigital Psychiatry and Artificial IntelligenceSystematic review # Feeling better, byte by byte: Effectiveness and safety of AI-supported interventions in the management of major depressive disorder FEELING BETTER, BYTE BY BYTE: THE EFFECTIVENESS AND SAFETY OF ARTIFICIAL INTELLIGENCE-ENABLED INTERVENTIONS FOR THE MANAGEMENT OF MAJOR DEPRESSIVE DISORDER Presenter: Saksham Sharma Country: India AI-based clinical decision support and session analytics tools improve symptom outcomes and treatment retention in major depressive disorder, while prognostic machine learning models outperform clinician judgment in predicting remission and medication response. The study aimed to examine whether artificial intelligence and machine learning–supported interventions improve treatment precision and remission rates in major depressive disorder (MDD) compared with traditional clinical judgment. In this PRISMA-guided systematic review, 2,318 records were screened, 37 full-text articles were assessed, and 5 studies were included; these comprised randomized controlled trials of AI-based clinical decision support systems (CDSS) and prognostic machine learning studies, with usual care or clinician judgment as the comparator. In the Eleos Health randomized trial (n=47), symptom reductions at two months were 34% on the PHQ-9 (d=0.82) and 29% on the GAD-7 (d=0.78), compared with 20% (d=0.34) and 8% (d=0.14), respectively, with usual care; clinical notes were completed 55 hours earlier. In the PETRUSHKA randomized trial (n=520), all-cause treatment discontinuation at week 8 was 17% versus 27%, and discontinuation due to adverse effects was 9% versus 16%, with a reported 40% reduction in discontinuation (RR 0.62; p=0.007); at week 24, mean symptom scores were 7.1 versus 9.2 for the PHQ-9 and 4.6 versus 5.8 for the GAD-7. Among the prognostic models, the NESDA multi-omics model (n=804) achieved an AUROC of 0.78 for predicting two-year remission, outperforming psychiatrists’ accuracy of 51% to 55% (κ=0.32), while the EMBARC multimodal MRI model (n=229) predicted week 8 sertraline response using week 1 data with a balanced accuracy of 68% and an AUROC of 0.73. In the structural MRI model for ketamine and treatment-resistant depression (n=99/51), balanced accuracy was 72.2% in the discovery sample, 60% in external validation, and 41.1% in the saline control group. The authors concluded that decision support systems and session analytics improve treatment retention, reduce long-term depression and anxiety symptoms, and lessen the documentation burden. They emphasized the need for prospective, double-blind clinical trials evaluating the real-world effectiveness and cost-effectiveness of neuroimaging and multi-omics decision support tools before their adoption in routine practice. [View the original poster](https://cslide.ctimeetingtech.com/wcp26/attendee/eposter/file/2333) How to cite this study APA 7: Sharma, S., Gopalakrishnan, R., Sankar, M., & Raparthi, A. (2026, September 23-26). Feeling better, byte by byte: the effectiveness and safety of artificial intelligence-enabled interventions for the management of major depressive disorder [E-poster]. 26th WPA World Congress of Psychiatry (WCP 2026), Stockholm, Sweden. https://cslide.ctimeetingtech.com/wcp26/attendee/eposter/file/2333 Vancouver: Sharma S, Gopalakrishnan R, Sankar M, Raparthi A. Feeling better, byte by byte: the effectiveness and safety of artificial intelligence-enabled interventions for the management of major depressive disorder [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/2333 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/ev0468 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