Predicting subgroup treatment effects for a new study: Motivations, results and learnings from running a data challenge in a pharmaceutical corporation.

We present the motivation, experience, and learnings from a data challenge conducted at a large pharmaceutical corporation on the topic of subgroup identification. The data challenge aimed at exploring approaches to subgroup identification for future clinical trials. To mimic a realistic setting, participants had access to 4 Phase III clinical trials to derive a subgroup and predict its treatment effect on a future study not accessible to challenge participants. A total of 30 teams registered for the challenge with around 100 participants, primarily from Biostatistics organization. We outline the motivation for running the challenge, the challenge rules, and logistics. Finally, we present the results of the challenge, the participant feedback as well as the learnings. We also present our view on the implications of the results on exploratory analyses related to treatment effect heterogeneity.

Methodology for Good Machine Learning with Multi-Omics Data.

In 2020, Novartis Pharmaceuticals Corporation and the U.S. Food and Drug Administration (FDA) started a 4-year scientific collaboration to approach complex new data modalities and advanced analytics. The scientific question was to find novel radio-genomics-based prognostic and predictive factors for HR+/HER- metastatic breast cancer under a Research Collaboration Agreement. This collaboration has been providing valuable insights to help successfully implement future scientific projects, particularly using artificial intelligence and machine learning. This tutorial aims to provide tangible guidelines for a multi-omics project that includes multidisciplinary expert teams, spanning across different institutions. We cover key ideas, such as "maintaining effective communication" and "following good data science practices," followed by the four steps of exploratory projects, namely (1) plan, (2) design, (3) develop, and (4) disseminate. We break each step into smaller concepts with strategies for implementation and provide illustrations from our collaboration to further give the readers actionable guidance.

Reference intervals for reticulocyte indices, immature reticulocyte fraction, and the percentage of hypochromic red blood cells in adult large breed dogs using the ADVIA 2120 hematology analyzer.

Reticulocyte indices are used to characterize anemia, including the identification of regeneration. In people, the immature reticulocyte fraction (IRF), percentage of hypochromic red blood cells (%HYPO-RBC), and other reticulocyte indices have been used as earlier indicators of erythropoiesis and as valuable monitoring tools in the assessment of various therapies. The reference intervals (RI) of the IRF and %HYPO-RBC have not been reported in dogs. The objective of this study was to establish RIs for novel variables (IRF, %HYPO-RBC, and CH-delta) and assess RIs for more commonly reported reticulocyte indices in healthy dogs. RIs were calculated from blood results retrospectively collected from 106 client-owned healthy dogs at the time of induction into a blood donor program using the ADVIA 2120 hematology analyzer (Siemens Healthcare Diagnostics). For the calculation of RIs, appropriate tests were applied for outlier detection and normality assessment. For variables normally distributed, RIs and their respective 90% confidence intervals (CIs) were calculated using parametric methods, while for variables not normally distributed, robust methods were used and bootstrapping for calculating the 90% CIs. The following RIs were established: reticulocyte hemoglobin content (CHr) 24.5-28 pg, mean reticulocyte volume (MCVr) 85.9-99.3 fL, mean corpuscular hemoglobin concentration of reticulocytes (CHCMr) 271.0-306.3 g/L, IRF 10.4%-43.5%, CH-delta 0.5-4.3 pg, and percentage of hypochromic red blood cells (%HYPO-RBC) 0.10%-0.80%. The results of this study provide RIs for novel reticulocyte variables. Further studies are required to determine the clinical utility of IRF, %HYPO-RBC, and CH delta as early indicators of erythropoietic activity in canine patients.

Allogenic blood patch pleurodesis for management of pneumothorax in a Cavalier King Charles Spaniel puppy with multiple pulmonary blebs and bullae.

A 9-week-old male intact Cavalier King Charles Spaniel was presented for evaluation of acute onset dyspnea caused by left-sided pneumothorax. Thoracic computed tomography (CT) identified multiple pulmonary bullae and blebs in multiple lung lobes. Rupture of ≥1 pulmonary blebs or bullae, precipitated by low impact trauma, was the suspected cause of pneumothorax. A volume of 7.5 mL/kg of fresh whole blood was collected from a type-matched donor dog and administered into the left pleural space using a thoracostomy tube. The pneumothorax was successfully resolved and no adverse effects of blood patch pleurodesis were noted. The dog was clinically normal 12 months later.