Maximilian Lukas Peters

Dr. Maximilian Lukas Peters


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2022 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
DSDavid Schöler
David Schöler
Karel KostevKarel Kostev
Karel Kostev
MPMaximilian Lukas Peters
Maximilian Lukas Peters
CZCosmin Zamfir
Cosmin Zamfir
AWAgnieszka Wolk
Agnieszka Wolk
SLSven Loosen
Sven Loosen
Background: Inflammatory bowel disease (IBD) is of high medical and socioeconomic relevance. Moderate and severe disease courses often require treatment with biologics. The aim of this study was to evaluate machine learning (ML)-based methods for the prediction of biologic therapy in IBD patients using a large prescription database. Methods: The present retrospective cohort study utilized a longitudinal prescription database (LRx). Patients with at least one prescription for an intestinal anti-inflammatory agent from a gastroenterologist between January 2015 and July 2021 were included. Patients who had received an initial biologic therapy prescription (infliximab, adalimumab, golimumab, vedolizumab, or ustekinumab) were categorized as the “biologic group”. The potential predictors included in the machine learning-based models were age, sex, and the 100 most frequently prescribed drugs within 12 months prior to the index date. Six machine learning-based methods were used for the prediction of biologic therapy. Results: A total of 122,089 patients were included in this study. Of these, 15,824 (13.0%) received at least one prescription for a biologic drug. The Light Gradient Boosting Machine had the best performance (accuracy = 74%) and was able to correctly identify 78.5% of the biologics patients and 72.6% of the non-biologics patients in the testing dataset. The most important variable was prednisolone, followed by lower age, mesalazine, budesonide, and ferric iron. Conclusions: In summary, this study reveals the advantages of ML-based models in predicting biologic therapy in IBD patients based on pre-treatment and demographic variables. There is a need for further studies in this regard that take into account individual patient characteristics, i.e., genetics and gut microbiota, to adequately address the challenges of finding optimal treatment strategies for patients with IBD.

18 December 2022 in Healthcare
Verified
Journal Article
Open access
PDF file
AHAnnika Härtel
Annika Härtel
MPMaximilian Lukas Peters
Maximilian Lukas Peters
Karel KostevKarel Kostev
Karel Kostev
The goal of this study was to estimate the prevalence of spirometry testing among patients with asthma and chronic obstructive pulmonary disease (COPD) in general practices (GPs) in Germany. This retrospective cross-sectional study was based on data from the Disease Analyzer database (IQVIA), This retrospective cross-sectional study included all patients with at least one confirmed asthma or COPD diagnosis in one of those 50 general practices in Germany between January 2020, and January 2021, as well as at least one visit to these general practices between January 2021, and January 2022. The main outcomes of the study aimed to ascertain the proportion of spirometry testing among asthma and COPD patients between January 2021, and January 2022, overall, and separately, in men, women, six age groups (≤30, 31–40, 41–50, 51–60, 61, 70, >70), and patients who received at least one prescription of anti-asthma or anti-COPD drugs. This study included 8835 patients with asthma only, 5597 with COPD only, and 1897 with both asthma and COPD diagnoses. Of these, 27.2% of COPD patients, 7% of asthma patients, and 54.7% of asthma + COPD patients, received spirometry testing during the study period. Among COPD and asthma + COPD patients, the prevalence of spirometry testing was much higher in women than in men (COPD: 31.6% vs. 23.2%; asthma + COPD: 59.6% vs. 46.3%) and much higher in treated than in non-treated patients (COPD: 31.7% vs. 15.0%; asthma + COPD: 57.5% vs. 27.8%). The prevalence of spirometry testing was relatively low among COPD and asthma patients followed in GP practices, but usually higher in female patients, treated patients, and patients suffering from both asthma and COPD.

Verified
Journal Article
Open access
PDF file
Karel KostevKarel Kostev
Karel Kostev
BLBeate Leppert
Beate Leppert
MPMaximilian Lukas Peters
Maximilian Lukas Peters
HSHenning Sievert
Henning Sievert
MKMarcel Konrad
Marcel Konrad
MLMark Luedde
Mark Luedde
Background: Primary non-adherence (PNA)—failure to dispense a newly prescribed medication—is an early barrier to effective treatment. This study aimed to estimate PNA to oral anticoagulants in patients with atrial fibrillation (AF) in Germany and to identify associated factors. Methods: In this retrospective cohort study, first prescriptions of vitamin K antagonists (VKAs), direct thrombin inhibitors, or direct factor Xa inhibitors issued to AF patients between 2016 and 2025 in the IQVIA Disease Analyzer database were combined with pharmacy dispensing records in the Longitudinal Prescription (LRx) database. First prescriptions preceded by a dispensing of the same class within 365 days were excluded. PNA was defined as failure to dispense within 30 days; associated factors were assessed using logistic regression with generalized estimating equations. Results: The study included 57,290 first prescriptions in 53,815 patients (mean age 75.5 years; 49.7% women). PNA occurred in 10.6% (VKAs 14.4%, direct thrombin inhibitors 11.7%, direct factor Xa inhibitors 10.1%). Direct factor Xa inhibitors (odds ratio [OR] 0.67; 95% confidence interval [CI] 0.62–0.72), prior myocardial infarction (OR 0.79), and dementia (OR 0.85) were associated with lower odds of PNA, whereas ischemic heart disease (OR 1.18) and hypertension (OR 1.11) were associated with higher odds. Non-dispensing of the first prescription was strongly associated with non-dispensing of subsequent prescriptions. Conclusions: Approximately one in ten first oral anticoagulant prescriptions in AF was not dispensed within 30 days, most frequently for VKAs.

29 May 2026 in Current Oncology
Verified
Journal Article
Open access
PDF file
Karel KostevKarel Kostev
Karel Kostev
MPMaximilian Lukas Peters
Maximilian Lukas Peters
HSHenning Sievert
Henning Sievert
MKMatthias Kalder
Matthias Kalder
Background: Aromatase inhibitors (AIs) are widely used in hormone receptor-positive breast cancer but may adversely affect bone health. Evidence on their independent association with fracture risk compared with tamoxifen (TAM) remains inconsistent. Methods: In this retrospective cohort study, women with an initial prescription of TAM or AIs between 2016 and 2024 were identified in the IQVIA Longitudinal Prescription (LRx) database. Their prescription histories were combined with records from the IQVIA Disease Analyzer (DA) database using a validated co-therapy-based approach. Patients were then followed for up to five years. Kaplan–Meier analyses estimated cumulative fracture incidence, and Cox regression models assessed associations in unadjusted, age-adjusted, and fully adjusted analyses. Results: The study included 8938 TAM users and 14,594 AI users. Five-year cumulative incidence of all fractures was higher in the AI group than in the TAM group (14.8% vs. 9.2%). In fully adjusted primary analyses, AI therapy was not significantly associated with overall fracture risk (HR 1.10, 95% CI 0.99–1.23). A modest association persisted for major osteoporotic fractures (HR 1.24, 95% CI 1.05–1.46). Secondary exploratory analyses (age-stratified and fracture-type-specific models) showed patterns consistent with the primary results but were not powered or corrected for confirmatory inference. Conclusions: Aromatase inhibitor therapy was associated with a higher fracture incidence than tamoxifen, but much of this difference was explained by age and comorbidities. Both treatment-related effects and underlying patient characteristics contribute to fracture risk, underscoring the importance of individualized bone health assessment and targeted preventive strategies in women receiving endocrine therapy.