Andreas Leha

Dr. Andreas Leha

orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
1 June 2019 in Parkinsonism & Related Disorders
Verified
Journal Article
Closed access
MBMatthias Boerger
Matthias Boerger
SFSebastian Funke
Sebastian Funke
ALAndreas Leha
Andreas Leha
ARAnna-Elisa Roser
Anna-Elisa Roser
AWAnn-Katrin Wuestemann
Ann-Katrin Wuestemann
Paul LingorPaul Lingor
Paul Lingor

1 February 2020 in Neurobiology of Disease
Verified
Journal Article
Open access
FMFabian Maass
Fabian Maass
BMBernhard Michalke
Bernhard Michalke
DWDesiree Willkommen
Desiree Willkommen
ALAndreas Leha
Andreas Leha
CSClaudia Schulte
Claudia Schulte
Paul LingorPaul Lingor
Paul Lingor
The aim of the study was to validate a predictive biomarker machine learning model for the classification of Parkinson's disease (PD) and age-matched controls (AMC), based on bioelement abundance in the cerebrospinal fluid (CSF). For this multicentric trial, participants were enrolled from four different centers. CSF was collected according to standardized protocols. For bioelement determination, CSF samples were subjected to inductively coupled plasma mass spectrometry. A predefined Support Vector Machine (SVM) model, trained on a previous discovery cohort was applied for differentiation, based on the levels of six different bioelements. 82 PD patients, 68 age-matched controls and 7 additional Normal Pressure Hydrocephalus (NPH) patients were included to validate a predefined SVM model. Six differentiating elements (As, Fe, Mg, Ni, Se, Sr) were quantified. Based on their levels, SVM was successfully applied to a new local cohort (AUROC 0.76, Sensitivity 0.80, Specificity 0.83), without taking any additional features into account. The same model did not discriminate PD and AMCs / NPH from three external cohorts, likely due to center effects. However, discrimination was possible in cohorts with a full elemental data set, now using center-specific discovery cohorts and a cross validated approach (AUROC 0.78 and 0.88, respectively). Pooled PD CSF iron levels showed a clear correlation with disease duration (p = .0001). In summary, bioelemental CSF patterns, obtained by mass spectrometry and integrated into a predictive model yield the potential to facilitate the differentiation of PD and AMC. Center-specific biases interfere with application in external cohorts. This must be carefully addressed using center-defined, local reference values and models.

6 February 2025 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
MTMalte Tölle
Malte Tölle
PGPhilipp Garthe
Philipp Garthe
CSClemens Scherer
Clemens Scherer
JSJan Moritz Seliger
Jan Moritz Seliger
ALAndreas Leha
Andreas Leha
SESandy Engelhardt
Sandy Engelhardt
Federated learning is a renowned technique for utilizing decentralized data while preserving privacy. However, real-world applications often face challenges like partially labeled datasets, where only a few locations have certain expert annotations, leaving large portions of unlabeled data unused. Leveraging these could enhance transformer architectures’ ability in regimes with small and diversely annotated sets. We conduct the largest federated cardiac CT analysis to date (n = 8, 104) in a real-world setting across eight hospitals. Our two-step semi-supervised strategy distills knowledge from task-specific CNNs into a transformer. First, CNNs predict on unlabeled data per label type and then the transformer learns from these predictions with label-specific heads. This improves predictive accuracy and enables simultaneous learning of all partial labels across the federation, and outperforms UNet-based models in generalizability on downstream tasks. Code and model weights are made openly available for leveraging future cardiac CT analysis.

16 October 2020 in Cancers
Verified
Journal Article
Open access
PDF file
JUJohannes Uhlig
Johannes Uhlig
ALAndreas Leha
Andreas Leha
LDLaura Delonge
Laura Delonge
AHAnna-Maria Haack
Anna-Maria Haack
BSBrian Shuch
Brian Shuch
AUAnnemarie Uhlig
Annemarie Uhlig
This study evaluates the diagnostic performance of radiomic features and machine learning algorithms for renal tumor subtype assessment in venous computed tomography (CT) studies from clinical routine. Patients undergoing surgical resection and histopathological assessment of renal tumors at a tertiary referral center between 2012 and 2019 were included. Preoperative venous-phase CTs from multiple referring imaging centers were segmented, and standardized radiomic features extracted. After preprocessing, class imbalance handling, and feature selection, machine learning algorithms were used to predict renal tumor subtypes using 10-fold cross validation, assessed as multiclass area under the curve (AUC). In total, n = 201 patients were included (73.7% male; mean age 66 ± 11 years), with n = 131 clear cell renal cell carcinomas (ccRCC), n = 29 papillary RCC, n = 11 chromophobe RCC, n = 16 oncocytomas, and n = 14 angiomyolipomas (AML). An extreme gradient boosting algorithm demonstrated the highest accuracy (multiclass area under the curve (AUC) = 0.72). The worst discrimination was evident for oncocytomas vs. AML and oncocytomas vs. chromophobe RCC (AUC = 0.55 and AUC = 0.45, respectively). In sensitivity analyses excluding oncocytomas, a random forest algorithm showed the highest accuracy, with multiclass AUC = 0.78. Radiomic feature analyses from venous-phase CT acquired in clinical practice with subsequent machine learning can discriminate renal tumor subtypes with moderate accuracy. The classification of oncocytomas seems to be the most complex with the lowest accuracy.

17 March 2023 in European Heart Journal - Digital Health
Verified
Journal Article
Open access
PDF file
ALAndreas Leha
Andreas Leha
CHCynthia Huber
Cynthia Huber
TFTim Friede
Tim Friede
TBTimm Bauer
Timm Bauer
ABAndreas Beckmann
Andreas Beckmann
TSTim Seidler
Tim Seidler
Aims: Identification of high-risk patients and individualized decision support based on objective criteria for rapid discharge after transcatheter aortic valve implantation (TAVI) are key requirements in the context of contemporary TAVI treatment. This study aimed to predict 30-day mortality following TAVI based on machine learning (ML) using data from the German Aortic Valve Registry. Methods and results: Mortality risk was determined using a random forest ML model that was condensed in the newly developed TAVI Risk Machine (TRIM) scores, designed to represent clinically meaningful risk modelling before (TRIMpre) and in particular after (TRIMpost) TAVI. Algorithm was trained and cross-validated on data of 22 283 patients (729 died within 30 days post-TAVI) and generalisation was examined on data of 5864 patients (146 died). TRIMpost demonstrated significantly better performance than traditional scores [C-statistics value, 0.79; 95% confidence interval (CI)] [0.74; 0.83] compared to Society of Thoracic Surgeons (STS) with C-statistics value 0.69; 95%-CI [0.65; 0.74]). An abridged (aTRIMpost) score comprising 25 features (calculated using a web interface) exhibited significantly higher performance than traditional scores (C-statistics value, 0.74; 95%-CI [0.70; 0.78]). Validation on external data of 6693 patients (205 died within 30 days post-TAVI) of the Swiss TAVI Registry confirmed significantly better performance for the TRIMpost (C-statistics value 0.75, 95%-CI [0.72; 0.79]) compared to STS (C-statistics value 0.67, CI [0.63; 0.70]). Conclusion: TRIM scores demonstrate good performance for risk estimation before and after TAVI. Together with clinical judgement, they may support standardised and objective decision-making before and after TAVI.

27 April 2020 in JBMR Plus
Verified
Journal Article
Open access
PDF file
DWDeborah Wilde
Deborah Wilde
LWLara Wilken
Lara Wilken
BSBettina Stamm
Bettina Stamm
CHChristina Heppner
Christina Heppner
ALAndreas Leha
Andreas Leha
HSHeide Siggelkow
Heide Siggelkow
In hypoparathyroidism (HypoPT), patients suffer severely from reduced quality of life. The complexity of HypoPT demands a disease‐specific control instrument to characterize symptom load. We employed a newly developed disease‐specific Hypoparathyroid Patient Questionnaire (the HPQ 40/28) to investigate and quantify HypoPT patients' complaints and contributing factors. In this cross‐sectional, two‐center study, patients with postsurgical HypoPT (n = 49) were matched for gender and age and compared with patients having undergone thyroid surgery without HypoPT (n = 39) and patients with primary hyperparathyroidism (n = 35). The HPQ 40/28 was completed when patients visited the respective center. Clinical background information, blood tests, and current medication were documented by the physician. Serum calcium lay within the reference range in 87% of HypoPT patients, serum phosphate in 95.7%, and calcium–phosphate product (CPP) in 100%. HPQ 40/28 scores for the scales “pain and cramps” (PaC), “neurovegetative symptoms” (NVS), “numbness or tingling,” and “heart palpitations” were significantly elevated in comparison with control groups. Correlations between complaints and laboratory parameters could be demonstrated in the HypoPT group, with serum calcium correlating with NVS (r = 0.309, p < 0.05) and serum phosphate with loss of vitality (r = 0.349, p < 0.05). CPP was the main contributor to symptom load with an influence on PaC (r = 0.295, p < 0.05), loss of vitality (r = 0.498, p < 0.001), numbness or tingling (r = 0.328, p < 0.05), and memory problems (r = 0.296, p < 0.05). In conclusion, the newly developed HPQ 40/28 successfully identified and quantified symptoms typical in HypoPT patients. Using the HPQ 40/28, the CPP was identified as the predominant factor in the severity of complaints in HypoPT. © 2020 The Authors. JBMR Plus published by Wiley Periodicals, Inc. on behalf of American Society for Bone and Mineral Research.