Development of a Novel Ulcerative Colitis Endoscopic Mayo Score Prediction Model Using Machine Learning.

Background and Aims: Endoscopic assessment is a co-primary end point in inflammatory bowel disease registration trials, yet it is subject to inter- and intraobserver variability. We present an original machine learning approach to Endoscopic Mayo Score (eMS) prediction in ulcerative colitis and report the model's performance in differentiating key levels of endoscopic disease activity on full-length procedure videos. Methods: Seven hundred ninety-three full-length videos with centrally-read eMS were obtained from 249 patients with ulcerative colitis, who participated in a phase II trial evaluating mirikizumab (NCT02589665). A video annotation approach was established to extract mucosal features and associated eMS classification labels from each video to be used as inputs for model training. The primary objective of the model was a categorical prediction of inactive vs active endoscopic disease evaluated against 2 independent test sets: a full set with a baseline single human expert read and a consensus subset in which 2 human reads agreed. Results: On the full test set of 147 videos, the model predicted inactive vs active endoscopic disease via the eMS with an area under the curve of 89%, accuracy of 84%, positive predictive value of 80%, and negative predictive value of 85%. In the consensus test set of 94 videos, the model predicted inactive vs active endoscopic disease with an area under the curve of 92%, accuracy of 89%, positive predictive value of 87%, and negative predictive value of 90%. Conclusion: We have demonstrated that this machine learning model supervised by mucosal features and eMS video annotations accurately differentiates key levels of endoscopic disease activity.

Improvement in adenoma detection using a novel artificial intelligence-aided polyp detection device.

Background and study aims Detecting colorectal neoplasia is the goal of high-quality screening and surveillance colonoscopy, as reflected by high adenoma detection rate (ADR) and adenomas per colonoscopy (APC). The aim of our study was to evaluate the performance of a novel artificial intelligence (AI)-aided polyp detection device, Skout, with the primary endpoints of ADR and APC in routine colonoscopy. Patients and methods We compared ADR and APC in a cohort of outpatients undergoing routine high-resolution colonoscopy with and without the use of a real-time, AI-aided polyp detection device. Patients undergoing colonoscopy with Skout were enrolled in a single-arm, unblinded, prospective trial and the results were compared with a historical cohort. All resected polyps were examined histologically. Results Eighty-three patients undergoing screening and surveillance colonoscopy at an outpatient endoscopy center were enrolled and outcomes compared with 283 historical control patients. Overall, ADR with and without Skout was 54.2 % and 40.6 % respectively ( P  = 0.028) and 53.6 % and 30.8 %, respectively, in screening exams ( P  = 0.024). Overall, APC rate with and without Skout was 1.46 and 1.01, respectively, ( P  = 0.104) and 1.18 and 0.50, respectively, in screening exams ( P  = 0.002). Overall, true histology rate (THR) with and without Skout was 73.8 % and 78.4 %, respectively, ( P  = 0.463) and 75.0 % and 71.0 %, respectively, in screening exams ( P  = 0.731). Conclusion We have demonstrated that our novel AI-aided polyp detection device increased the ADR in a cohort of patients undergoing screening and surveillance colonoscopy without a significant concomitant increase in hyperplastic polyp resection. AI-aided colonoscopy has the potential for improving the outcomes of patients undergoing colonoscopy.

Pharmacokinetics, metabolism and safety of deuterated L-DOPA (SD-1077)/carbidopa compared to L-DOPA/carbidopa following single oral dose administration in healthy subjects.

AIMS: SD-1077, a selectively deuterated precursor of dopamine (DA) structurally related to L-3,4-dihydroxyphenylalanine (L-DOPA), is under development for treatment of motor symptoms of Parkinson's disease. Preclinical models have shown slower metabolism of central deuterated DA. The present study investigated the peripheral pharmacokinetics (PK), metabolism and safety of SD-1077. METHODS: Plasma and urine PK of drug and metabolites and safety after a single oral 150 mg SD-1077 dose were compared to 150 mg L-DOPA, each in combination with 37.5 mg carbidopa (CD) in a double-blind, two-period, crossover study in healthy volunteers (n = 16). RESULTS: Geometric least squares mean ratios (GMRs) and 90% confidence intervals (90% CI) of SD-1077 vs. L-DOPA for Cmax , AUC0-t , and AUC0-inf were 88.4 (75.9-103.1), 89.5 (84.1-95.3), and 89.6 (84.2-95.4), respectively. Systemic exposure to DA was significantly higher after SD-1077/CD compared to that after L-DOPA/CD, with GMRs (90% CI) of 1.8 (1.45-2.24; P = 0.0005) and 2.06 (1.68-2.52; P < 0.0001) for Cmax and AUC0-t and a concomitant reduction in the ratio of 3,4-dihydroxyphenylacetic acid/DA confirming slower metabolic breakdown of DA by monoamine oxidase (MAO). There were increases in systemic exposures to metabolites of catechol O-methyltransferase (COMT) reaction, 3-methoxytyramine (3-MT) and 3-O-methyldopa (3-OMD) with GMRs (90% CI) for SD-1077/CD to L-DOPA/CD for 3-MT exposure of 1.33 (1.14-1.56; P = 0.0077) and 1.66 (1.42-1.93; P < 0.0001) for Cmax and AUC0-t , respectively and GMRs (90% CI) for 3-OMD of 1.19 (1.15, 1.23; P < 0.0001) and 1.31 (1.27, 1.36; P < 0.0001) for Cmax and AUC0-t . SD-1077/CD exhibited comparable tolerability and safety to L-DOPA/CD. CONCLUSIONS: SD-1077/CD demonstrated the potential to prolong exposure to central DA at comparable peripheral PK and safety to the reference L-DOPA/CD combination. A single dose of SD-1077 is safe for further clinical development in Parkinson's disease patients.

Impact of dosing regimen of custirsen, an antisense oligonucleotide, on safety, tolerability and cardiac repolarization in healthy subjects.

AIMS: Custirsen (OGX-011/TV-1011), a second-generation antisense oligonucleotide (ASO) that reduces clusterin production, is under investigation with chemotherapy in patients with solid tumours. Custirsen is associated with constitutional symptoms (CS) that may interfere with clinical pharmacology investigations, such as QT interval studies. Experience with other ASOs suggests NSAID premedication may ameliorate CS, but we observed suboptimal outcomes in healthy subjects given custirsen and NSAIDs. We sought to establish a custirsen regimen for future clinical pharmacology studies in healthy subjects. METHODS: Subjects received custirsen (640 mg intravenously over 120 min) with dexamethasone premedication or increasing doses (320, 480, 640 mg over 6 days) of custirsen with dexamethasone premedication, then one full custirsen dose without premedication on day 8. Incidence/severity of adverse events (AEs) and extensive electrocardiogram readings were evaluated. Pharmacokinetic parameters were estimated. RESULTS: AEs included CS, elevated transaminases and prolonged activated partial thromboplastin time (aPTT) that were predominantly grade 1/2. Administration of increasing custirsen doses and dexamethasone premedication reduced the incidence of CS associated with full dose custirsen. Transaminase elevation showed a dose-dependent effect (0% at days 2, 4, 27% at day 6) with the highest custirsen doses. Increasing doses of custirsen may have mitigated the severity but not incidence of aPTT prolongation. Neither regimen was associated with cardiac repolarization changes in QT values or concentration-effect analyses. The custirsen pharmacokinetic profile was consistent with previous experience. CONCLUSION: Escalation of custirsen dose combined with dexamethasone premedication reduced CS associated with full dose custirsen and should be considered in future clinical pharmacology studies of custirsen.