Wicki, Andreas

Abstract Cancer outcomes vary widely between individual patients, each accumulating an irregular record of treatments, diagnoses, measurements, and complications. Current prognostic models reduce this complexity into a single snapshot, focus on narrow clinical settings, and rarely generalize across hospitals. Here we introduce Chronicle , an explainable transformer that learns from entire patient trajectories to predict diverse clinical outcomes throughout the disease course while capturing both short- and long-term temporal dependencies. Trained on 53.7 million longitudinal data points from 51,711 patients spanning 67 cancer types, Chronicle operates natively on irregular data without imputation and jointly predicts eight endpoints within a flexible framework adaptable to additional outcomes. Chronicle outperformed cross-sectional models for overall survival prediction (C-index 0.84 vs 0.76-0.79), stratified patients more accurately than established prognostic systems, including TNM stage, and predicted seven adverse event and transfusion endpoints (AUC 0.80-0.92). Applied without retraining to 69,341 patients in Germany, Switzerland, and the United States, Chronicle generalized across healthcare systems and improved further with local fine-tuning. Integrated explainability traced each risk update to patient-specific clinical factors, revealing distinct temporal persistence of prognostic information, with relevance half-lives ranging from weeks for therapies to nearly one year for baseline characteristics. These findings demonstrate that learning from hospital-wide patient trajectories enables interpretable and continuously updated predictions, providing a scalable framework to support individualized treatment decisions.

Background: Bimiralisib is a pan-PI3K/mTOR inhibitor demonstrating antitumor efficacy in preclinical models. The objectives of this study were to identify a maximum tolerated dose (MTD), pharmacokinetics (PK), a dosing schedule, and adverse events (AEs) in patients with advanced solid tumors. Patients and Methods: Patients received oral bimiralisib to determine the MTD of one continuous (once daily) and two intermittent schedules (A: Days 1, 2 weekly; B: Days 1, 4 weekly) until progression or unacceptable AEs occurred. Results: The MTD for the continuous schedule was 80 mg, with grade three fatigue as the dose-limiting toxicity (DLT). No MTD was reached with intermittent schedules, with only one DLT in schedule B. PK analysis suggested that 140 mg (schedule A) was within the biologically active dose range and was selected for further exploration. The most frequent treatment-emergent AEs were hyperglycemia (76.2%) in the continuous schedule, and nausea (56–62.5%) in schedules A and B. The most frequent treatment-emergent > grade three AE for all schedules combined was hyperglycemia (28.6%, continuous schedule; 12.0%, schedule A; 12.5%, schedule B). There was one partial response in a head and neck squamous cancer patient with a NOTCH1T1997M mutation. Conclusions: Bimiralisib demonstrated a manageable AE profile consistent with this compound class. Intermittent schedules had fewer > grade three AEs, while also maintaining favorable PK profiles. Intermittent schedule A is proposed for further development in biomarker-selected patient populations.

Abstract Background: Bimiralisib is a balanced dual panPI3K/mTOR inhibitor, which demonstrated anti-cancer activity in a number of preclinical models. Pharmacokinetic (PK) data suggested that intermittent targeting of the PI3K/mTOR pathway could be preferable to continuous daily dosing. Preclinical models in squamous cell head and neck cancer (SCCHN) demonstrated that NOTCH1 Loss of Function (LoF) mutations were associated with efficacy of bimiralisib and other PI3K inhibitors. Methods: We conducted a first-in-human dose-escalation study (3+3 design) to identify the maximum tolerated dose (MTD), recommended phase 2 dose (RP2D), dose-limiting toxicities (DLT) and overall safety (CTCAE v4) of bimiralisib administered either as a continuous (80 mg – 120 mg daily) or one of two intermittent schedules (schedule A: twice weekly 80 mg – 200 mg on Day 1 and 2, or schedule B: twice weekly 80mg – 200 mg on Day 1 and 4) until disease progression or unacceptable adverse events (AEs). Eligible patients had histologically confirmed solid cancers refractory to standard therapies, ECOG <1, life expectancy >12 weeks, adequate bone marrow, liver, and renal functions, HgbA1c <7%, and fasting plasma glucose < 7.0mmol/L. Tumor responses were evaluated according to RECIST v1.1 every 6 weeks. PK and blood biomarkers were analyzed. Results: 70 patients (female, 70%; white, 93%; median age 57 years [range, 49-65]) with heavily pretreated advanced solid cancers were enrolled (continuous schedule, 21; intermittent schedule A, 25; intermittent schedule B, 24). The MTD for the continuous schedule was established as 80 mg daily. For all treatment groups, DLTs included grade 2 and 3 fatigue. Clinically significant treatment-related AEs included fatigue in the continuous schedule, none in the intermittent schedule A and diarrhea, hyperglycemia in the intermittent schedule B. Intermittent schedules A and B did not reach the MTD, and after review of PK data, 140 mg administered in schedule A was selected as the RP2D for further exploration. Day 1 peak plasma concentration proportionally increased with increasing doses of bimiralisib only up to 140mg. Weekly AUC on intermittent dosing at all dose levels studied were considerably lower than continuous daily dosing at 80mg. There was one partial response (PR, -85% per RECIST) in a heavily pretreated patient with SCCHN and NOTCH1 LoF mutation, which was maintained for 8.2 months until death from pulmonary artery rupture in the setting of known fistula (assessed as unrelated to bimiralisib). In addition, 30 (42.9%) pts achieved stable disease (SD) including one with anal SCC carrying a NOTCH1 LoF mutation. SD > 6 months was observed in five pts (23.8%) in continuous schedule, 12 (48%) in intermittent schedule A, and 13 (54.2%) in intermittent schedule B. Results on patients, who consented to the serial circulating tumor DNA collection will be presented. Conclusions: Bimiralisib was well tolerated and RP2D of 140 mg given orally twice weekly on Days 1 and 2 was selected for further studies. In agreement with our preclinical models, there was an encouraging activity in a SCCHN patient with NOTCH1 LoF mutation and this observation is now being validated in a proof-of-concept phase 2 study (NCT03740100). Citation Format: Filip Janku, Faye M. Johnson, Mateusz Opyrchal, Afshin Dowlati, Cinta Hierro, Martin Forester, Sarah P. Blagden, Andreas Wicki, Debora Schmitz, Alex A. Adjei. Oral dual PI3K/mTOR inhibitor bimiralisib demonstrates tolerability and a signal of activity in head and neck squamous cell cancer with NOTCH1 loss-of-function mutation [abstract]. In: Proceedings of the AACR-NCI-EORTC International Conference on Molecular Targets and Cancer Therapeutics; 2019 Oct 26-30; Boston, MA. Philadelphia (PA): AACR; Mol Cancer Ther 2019;18(12 Suppl):Abstract nr B109. doi:10.1158/1535-7163.TARG-19-B109