The Synthetic Minority Oversampling TEchnique (SMOTE) is widely-used for the analysis of imbalanced datasets. It is known that SMOTE frequently over-generalizes the minority class, leading to misclassifications for the majority class, and effecting the overall balance of the model. In this article, we present an approach that overcomes this limitation of SMOTE, employing Localized Random Affine Shadowsampling (LoRAS) to oversample from an approximated data manifold of the minority class. We benchmarked our algorithm with 14 publicly available imbalanced datasets using three different Machine Learning (ML) algorithms and compared the performance of LoRAS, SMOTE and several SMOTE extensions that share the concept of using convex combinations of minority class data points for oversampling with LoRAS. We observed that LoRAS, on average generates better ML models in terms of F1-Score and Balanced accuracy. Another key observation is that while most of the extensions of SMOTE we have tested, improve the F1-Score with respect to SMOTE on an average, they compromise on the Balanced accuracy of a classification model. LoRAS on the contrary, improves both F1 Score and the Balanced accuracy thus produces better classification models. Moreover, to explain the success of the algorithm, we have constructed a mathematical framework to prove that LoRAS oversampling technique provides a better estimate for the mean of the underlying local data distribution of the minority class data space.

Clinical research relies on high-quality patient data, however, obtaining big data sets is costly and access to existing data is often hindered by privacy and regulatory concerns. Synthetic data generation holds the promise of effectively bypassing these boundaries allowing for simplified data accessibility and the prospect of synthetic control cohorts. We employed two different methodologies of generative artificial intelligence – CTAB-GAN+ and normalizing flows (NFlow) – to synthesize patient data derived from 1606 patients with acute myeloid leukemia, a heterogeneous hematological malignancy, that were treated within four multicenter clinical trials. Both generative models accurately captured distributions of demographic, laboratory, molecular and cytogenetic variables, as well as patient outcomes yielding high performance scores regarding fidelity and usability of both synthetic cohorts (n = 1606 each). Survival analysis demonstrated close resemblance of survival curves between original and synthetic cohorts. Inter-variable relationships were preserved in univariable outcome analysis enabling explorative analysis in our synthetic data. Additionally, training sample privacy is safeguarded mitigating possible patient re-identification, which we quantified using Hamming distances. We provide not only a proof-of-concept for synthetic data generation in multimodal clinical data for rare diseases, but also full public access to synthetic data sets to foster further research.

The current generation of sequencing technologies has led to significant advances in identifying novel disease-associated mutations and generated large amounts of data in a high-throughput manner. Such data in conjunction with clinical routine data are proven to be highly useful in deriving population-level and patient-level predictions, especially in the field of cancer precision medicine. However, data harmonization across multiple national and international clinical sites is an essential step for the assessment of events and outcomes associated with patients, which is currently not adequately addressed. The Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) is an internationally established research data repository introduced by the Observational Health Data Science and Informatics (OHDSI) community to overcome this issue. To address the needs of cancer research, the genomic vocabulary extension was introduced in 2020 to support the standardization of subsequent data analysis. In this review, we evaluate the current potential of the OMOP CDM to be applicable in cancer prediction and how comprehensively the genomic vocabulary extension of the OMOP can serve current needs of AI-based predictions. For this, we systematically screened the literature for articles that use the OMOP CDM in predictive analyses in cancer and investigated the underlying predictive models/tools. Interestingly, we found 248 articles, of which most use the OMOP for harmonizing their data, but only 5 make use of predictive algorithms on OMOP-based data and fulfill our criteria. The studies present multicentric investigations, in which the OMOP played an essential role in discovering and optimizing machine learning (ML)-based models. Ultimately, the use of the OMOP CDM leads to standardized data-driven studies for multiple clinical sites and enables a more solid basis utilizing, e.g., ML models that can be reused and combined in early prediction, diagnosis, and improvement of personalized cancer care and biomarker discovery.

The phase III clinical trial PERFECT was designed to assess clinical safety and efficacy of intramyocardial CD133+ bone marrow stem cell treatment combined with CABG for induction of cardiac repair. Multicentre, double-blinded, randomised placebo controlled trial. The study was conducted across six centres in Germany October 2009 through March 2016 and stopped due slow recruitment after positive interim analysis in March 2015. Post-infarction patients with chronic ischemia and reduced LVEF (25-50%). Eighty-two patients were randomised to two groups receiving intramyocardial application of 5ml placebo or a suspension of 0.5-5×106 CD133+. Primary endpoint was delta (∆) LVEF at 180days (d) compared to baseline measured in MRI. Safety (n=77): 180d survival was 100%, MACE n=2, SAE n=49, without difference between placebo and CD133+. Efficacy (n=58): The LVEF improved from baseline LVEF 33.5% by +9.6% at 180d, p=0.001 (n=58). Treatment groups were not different in ∆LVEF (ANCOVA: Placebo +8.8% vs. CD133+ +10.4%, ∆CD133+vs placebo +2.6%, p=0.4). Responders (R) classified by ∆LVEF≥5% after 180d were 60% of the patients (35/58) in both treatment groups. ∆LVEF in ANCOVA was +17.1% in (R) vs. non-responders (NR) (∆LVEF 0%, n=23). NR were characterized by a preoperative response signature in peripheral blood with reduced CD133+ EPC (RvsNR: p=0.005) and thrombocytes (p=0.004) in contrast to increased Erythropoeitin (p=0.02), and SH2B3 mRNA expression (p=0.073). Actuarial computed mean survival time was 76.9±3.32months (R) vs. +72.3±5.0months (NR), HR 0.3 [Cl 0.07-1.2]; p=0.067.Using a machine learning 20 biomarker response parameters were identified allowing preoperative discrimination with an accuracy of 80% (R) and 84% (NR) after 10-fold cross-validation. The PERFECT trial analysis demonstrates that the regulation of induced cardiac repair is linked to the circulating pool of CD133+ EPC and thrombocytes, associated with SH2B3 gene expression. Based on these findings, responders to cardiac functional improvement may be identified by a peripheral blood biomarker signature. ClinicalTrials.govNCT00950274.

AMPK is a conserved serine/threonine kinase whose activity maintains cellular energy homeostasis. Eukaryotic AMPK exists as αβγ complexes, whose regulatory γ subunit confers energy sensor function by binding adenine nucleotides. Humans bearing activating mutations in the γ2 subunit exhibit a phenotype including unexplained slowing of heart rate (bradycardia). Here, we show that γ2 AMPK activation downregulates fundamental sinoatrial cell pacemaker mechanisms to lower heart rate, including sarcolemmal hyperpolarization-activated current (I_f) and ryanodine receptor-derived diastolic local subsarcolemmal Ca²⁺ release. In contrast, loss of γ2 AMPK induces a reciprocal phenotype of increased heart rate, and prevents the adaptive intrinsic bradycardia of endurance training. Our results reveal that in mammals, for which heart rate is a key determinant of cardiac energy demand, AMPK functions in an organ-specific manner to maintain cardiac energy homeostasis and determines cardiac physiological adaptation to exercise by modulating intrinsic sinoatrial cell behavior.