Automated conversational artificial intelligence (AI) for outpatient malignant bowel obstruction (MBO) symptom monitoring.
Bibliographic record
Abstract
1547 Background: MBO is a severe complication of advanced cancer. A Canadian ambulatory MBO program with nurse-led proactive call management demonstrated reduced hospitalization rates and improved survival. To overcome resource limitations, a smartphone app was developed, achieving 65% adherence. Building on this foundation, automated phone calls offer a promising approach to enhance adherence and improve symptom monitoring. Methods: We conducted a prospective pilot study at a tertiary Spanish hospital to remotely monitor MBO signs and symptoms using a conversational AI-based platform (Lola-Tucuvi). Patients (pts) with cancer with an active MBO or at risk of developing it (per PMMBO criteria) were enrolled. Automated, interactive phone calls were performed by the platform (Lola) weekly or biweekly. Lola performed structured MBO symptom assessments utilizing advanced natural language processing and AI algorithms, to analyze responses in real time. Alerts were generated for moderate or severe symptoms, which were flagged on a dashboard. Nurses contacted pts based on alerts. The primary objective was feasibility measured by adherence (% of answered calls), with a hypothesized adherence of ≥65% considered optimal. Results: From January 2024 to January 2025, 54 pts were enrolled, with 25 still active at the time of analysis. Median age was 60 years (range 29-86), and 96% of pts are female. Type of tumors included gynecologic (87%) and gastrointestinal (13%). All pts were on systemic therapy: chemotherapy (50%), immunotherapy (24%), ADC (15%), targeted (11%). Median prior lines of therapy were 2 (1-6), and 41% (22/54) of pts had an active MBO prior to enrollment. Lola performed 716 phone calls and 645 were answered, with an adherence of 90%. This resulted in an estimated 183.2 hours of nursing call time saved. Median time on the program was 117 days (7-356), and pts received a median of 14 calls. Of answered calls, the 36% (234/645) generated alerts, with 44% classified as severe. Most frequent severe and moderate alerts were constipation and abdominal pain, respectively. Nurses acted on 73% (171/234) of the alerts, providing interventions such as dietary modifications, medication adjustments, clinical or emergency assessments. During follow-up in the program 31.5% (17/54) of pts had ≥1 active MBO and 18.5% (10/54) required admissions for MBO. Feedback was received from 26 pts, indicating a high satisfaction (4.6/5), and 96% would recommend the use of Lola. Conclusions: This conversational AI platform demonstrated excellent feasibility with 90% adherence, higher than prior app-based solutions. It effectively monitored MBO symptoms, enabling timely clinical interventions and enhancing patient engagement. These results highlight the potential of AI-driven remote monitoring system to improve outcomes in cancer care. Further validation through randomized studies is warranted.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".