Jens Kleesiek

Country flagGermany

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (8)

BACKGROUND Unstructured clinical text remains a major barrier to interoperable data reuse and large-scale secondary analysis in healthcare. Large language models (LLMs) have the potential to automate the extraction of structured clinical information; however, their application is limited by the scarcity of high-quality annotated training data. OBJECTIVE - METHODS We evaluated an LLM–based pipeline for extracting structured clinical information from cancer-related discharge letters and mapping it to representations compatible with Fast Healthcare Interoperability Resources (FHIR). To enable large-scale supervised training, we developed a random sample generator that creates synthetic discharge letters using Qwen3 235B by randomly sampling and aggregating structured FHIR data from 41,175 cancer patients. The resulting synthetic discharge letters (n=75k) were paired with their originating structured data, forming a large-scale dataset for fine-tuning MedGemma 27B. Evaluation was conducted on the synthetic test dataset (n=7,500), real-world discharge letters (n=30) which are evaluated by physicians and a medical student, and a comparative one-shot approach using open-source models (Qwen3, LLaMA, and GPT-OSS). RESULTS The fine-tuned model achieved high extraction performance across multiple clinical entities, including full ICD diagnosis codes (F1 = 0.84), tumor-related information (0.99), laboratory values (0.99), medication names and dosages (0.99), and ATC medication codes (0.94). Extraction of procedure-related information was more challenging but remained reliable, with F1 scores of 0.63 for OPS codes and 0.90 for procedure descriptions. In a one-shot comparison of general-purpose LLMs with the fine-tuned model, the fine-tuned model consistently outperformed general-purpose LLMs in nearly all extraction categories. When applied to real-world discharge letters, performance remained robust, with F1 scores of 78.9% for ICD diagnoses, 86.1% for tumor-related information, 93% for medications, and 61.3% for procedures. CONCLUSIONS These results demonstrate that synthetic text generation from structured clinical data enables effective and scalable training of LLMs for extracting interoperable, multi-entity clinical information from unstructured documentation.

Year:

2026

Objective To address the challenges of data heterogeneity and manual feature engineering in clinical predictive modeling, we introduce FHIR-Former, an open-source framework integrating Fast Healthcare Interoperability Resources (FHIR) with large language models (LLMs) to automate and standardize clinical prediction tasks. Materials and Methods FHIR-Former dynamically processes structured (eg, lab results, medications) and unstructured (eg, clinical notes) data from FHIR resources. The pipeline supports multiple classification tasks, including 30-day readmission, imaging study prediction, and ICD code classification. Leveraging open-source LLMs (GeBERTa), we trained models on 1.1 million data points across ten FHIR resources using retrospective inpatient data (2018-2024). Hyperparameters were optimized via Bayesian methods, and outputs were mapped to FHIR RiskAssessment resources for interoperability. Results FHIR-Former achieved an F1-score of 70.7% and accuracy of 72.9% for 30-day readmission, 51.8% F1-score (88.1% accuracy) for mortality prediction, and 61% macro F1-score for imaging study classification. The ICD code prediction model attained 94% accuracy. Performance demonstrated promising performance for readmission and showed scalability across tasks without manual feature engineering. Discussion FHIR-Former eliminates institution-specific preprocessing by adapting to diverse FHIR implementations, enabling seamless integration of multimodal data. Its configurable architecture outperformed prior frameworks reliant on static inputs or limited to unstructured text. Real-time risk scores embedded in FHIR servers enhance clinical workflows without disrupting existing practices. Conclusion By harmonizing FHIR standardization with LLM flexibility, FHIR-Former advances scalable, interoperable predictive modeling in healthcare. The open-source framework facilitates automation, improves resource allocation, and supports personalized decision-making, bridging gaps between AI innovation and clinical practice.

Year:

2025

Biomedical research projects involving large patient cohorts are increasingly complex, both in terms of data modalities and number of samples. Such projects require robust data management solutions to foster data integrity, reproducibility and secondary use compliant with the FAIR (Findability, Accessibility, Interoperability, and Reusability) principles. SATURN3, a national German consortium with 17 project partner sites investigates intratumoral heterogeneity in three hard-to-treat cancers using patient biosamples actively collected at six project centers. The complex multicenter workflow of SATURN3 thereby includes multiple analyte types across bulk and single-cell sequencing, and spatial omics technologies. To avoid the risk of data loss and de-synchronization across the partner sites, metadata harmonization and documentation in a central infrastructure is essential. In addition, real-time monitoring of the processing status of the samples must be transparently accessible to all project partners throughout the project. This use case goes far beyond the documentation capabilities of spreadsheets or locally shared files that are susceptible to security vulnerabilities, versioning mistakes, data loss and type conversion errors. Existing data management tools are often too complex to set up or lack the necessary flexibility to be adopted for specific project needs. To address these challenges, we introduce LiMeTrack, an online biosample management platform with customizable and user-friendly data entry schemes and a real-time dashboard for providing an overview of project and sample status. LiMeTrack simplifies the creation and export of standardized sample sheets, streamlining subsequent bioinformatics analyses and biomedical research workflows. By integrating real-time monitoring with robust sample tracking and data management, LiMeTrack improves research transparency and reproducibility, ensures data integrity and optimizes workflows, making it a powerful solution for sample management in modern multicenter biomedical research scenarios.

Year:

2025

Clear cell renal cell carcinoma (ccRCC) is characterized by marked histological heterogeneity, encompassing its vasculature. Here, we introduce PropSegNet, a learning-based algorithm that segments and classifies three distinct vascular patterns in CD31-stained tissue sections. Integrating transcriptomic features, our work identifies a trajectory from high- to low-branching vessel architecture that co-evolves with the loss of proximal tubular cell traits in tumor cells. Furthermore, low-branching vessels form niches enriched with T cells and antigen-presenting cells. Mechanistically, air-liquid-interface cultures of patient-derived tumor fragments confirm that low-branching vessel features associate with T cell infiltration resulting in reduced viability under IL-2 rich conditions. Post-hoc transcriptomic analyses from two phase III clinical trials demonstrate that patients with tumors exhibiting an inflamed, low-branching vascular phenotype benefit most from the addition of immune checkpoint inhibition to anti-angiogenic treatment. These findings provide a rationale for prospective evaluation of vascular patterns and vessel-immune cell niches as potential biomarkers in ccRCC.

Year:

2025

Most clinical information is encoded as free text, not accessible for quantitative analysis. This study presents an open-source pipeline using the local large language model (LLM) “Llama 2” to extract quantitative information from clinical text and evaluates its performance in identifying features of decompensated liver cirrhosis. The LLM identified five key clinical features in a zero- and one-shot manner from 500 patient medical histories in the MIMIC IV dataset. We compared LLMs of three sizes and various prompt engineering approaches, with predictions compared against ground truth from three blinded medical experts. Our pipeline achieved high accuracy, detecting liver cirrhosis with 100% sensitivity and 96% specificity. High sensitivities and specificities were also yielded for detecting ascites (95%, 95%), confusion (76%, 94%), abdominal pain (84%, 97%), and shortness of breath (87%, 97%) using the 70 billion parameter model, which outperformed smaller versions. Our study successfully demonstrates the capability of locally deployed LLMs to extract clinical information from free text with low hardware requirements.

Year:

2024

The Sparsely Annotated Region and Organ Segmentation (SAROS) dataset was created using data from The Cancer Imaging Archive (TCIA) to provide a large open-access CT dataset with high-quality annotations of body landmarks. In-house segmentation models were employed to generate annotation proposals on randomly selected cases from TCIA. The dataset includes 13 semantic body region labels (abdominal/thoracic cavity, bones, brain, breast implant, mediastinum, muscle, parotid/submandibular/thyroid glands, pericardium, spinal cord, subcutaneous tissue) and six body part labels (left/right arm/leg, head, torso). Case selection was based on the DICOM series description, gender, and imaging protocol, resulting in 882 patients (438 female) for a total of 900 CTs. Manual review and correction of proposals were conducted in a continuous quality control cycle. Only every fifth axial slice was annotated, yielding 20150 annotated slices from 28 data collections. For the reproducibility on downstream tasks, five cross-validation folds and a test set were pre-defined. The SAROS dataset serves as an open-access resource for training and evaluating novel segmentation models, covering various scanner vendors and diseases.

Year:

2024

Purpose : Interpreting chest radiographs (CXR) remains challenging due to the ambiguity of overlapping structures such as the lungs, heart, and bones. To address this issue, we propose a novel method for extracting fine-grained anatom- ical structures in CXR using pseudo-labeling of three-dimensional computed tomography (CT) scans. Methods : We created a large-scale dataset of 10,021 thoracic CTs with 157 labels and applied an ensemble of 3D anatomy segmentation models to extract anatomical pseudo-labels. These labels were projected onto a two-dimensional plane, similar to the CXR, allowing the training of detailed semantic segmentation models for CXR without any manual annotation effort. Results : Our resulting segmentation models demonstrated remarkable performance on CXR, with a high average model-annotator agreement between two radiologists with mIoU scores of 0.93 and 0.85 for frontal and lateral anatomy, while inter-annotator agreement remained at 0.95 and 0.83 mIoU. Our anatom- ical segmentations allowed for the accurate extraction of relevant explainable medical features such as the cardio-thoracic-ratio. Conclusion : Our method of volumetric pseudo-labeling paired with CT projection offers a promising approach for detailed anatomical segmentation of CXR with a high agreement with human annotators. This technique may have important clinical implications, particularly in the analysis of various thoracic pathologies.

Year:

2024

PURPOSE Quantifying treatment response to gastroesophageal junction (GEJ) adenocarcinomas is crucial to provide an optimal therapeutic strategy. Routinely taken tissue samples provide an opportunity to enhance existing positron emission tomography-computed tomography (PET/CT)–based therapy response evaluation. Our objective was to investigate if deep learning (DL) algorithms are capable of predicting the therapy response of patients with GEJ adenocarcinoma to neoadjuvant chemotherapy on the basis of histologic tissue samples. METHODS This diagnostic study recruited 67 patients with I-III GEJ adenocarcinoma from the multicentric nonrandomized MEMORI trial including three German university hospitals TUM (University Hospital Rechts der Isar, Munich), LMU (Hospital of the Ludwig-Maximilians-University, Munich), and UME (University Hospital Essen, Essen). All patients underwent baseline PET/CT scans and esophageal biopsy before and 14-21 days after treatment initiation. Treatment response was defined as a ≥35% decrease in SUVmax from baseline. Several DL algorithms were developed to predict PET/CT-based responders and nonresponders to neoadjuvant chemotherapy using digitized histopathologic whole slide images (WSIs). RESULTS The resulting models were trained on TUM (n = 25 pretherapy, n = 47 on-therapy) patients and evaluated on our internal validation cohort from LMU and UME (n = 17 pretherapy, n = 15 on-therapy). Compared with multiple architectures, the best pretherapy network achieves an area under the receiver operating characteristic curve (AUROC) of 0.81 (95% CI, 0.61 to 1.00), an area under the precision-recall curve (AUPRC) of 0.82 (95% CI, 0.61 to 1.00), a balanced accuracy of 0.78 (95% CI, 0.60 to 0.94), and a Matthews correlation coefficient (MCC) of 0.55 (95% CI, 0.18 to 0.88). The best on-therapy network achieves an AUROC of 0.84 (95% CI, 0.64 to 1.00), an AUPRC of 0.82 (95% CI, 0.56 to 1.00), a balanced accuracy of 0.80 (95% CI, 0.65 to 1.00), and a MCC of 0.71 (95% CI, 0.38 to 1.00). CONCLUSION Our results show that DL algorithms can predict treatment response to neoadjuvant chemotherapy using WSI with high accuracy even before therapy initiation, suggesting the presence of predictive morphologic tissue biomarkers.

Year:

2023

Collaborators (13)

Michael Hölzel

Director/MD, Professor

University Hospital Bonn

GERMANY
View details

Niklas Klümper

University Hospital Bonn

GERMANY
View details

Glen Kristiansen

-

GERMANY
View details

Jörg Ellinger

University Hospital Bonn

GERMANY
View details

Jakob Nikolas Kather

Chair of Clinical Artificial Intelligence

TU Dresden

GERMANY
View details

Fabian Hörst

University Hospital Essen

GERMANY
View details

Christoph M. Friedrich

Head of Department

Technische Universität Dortmund

GERMANY
View details

Elisabeth Livingstone

University Hospital Essen

GERMANY
View details

Roland Schwarz

Professor

-

GERMANY
View details

Jens Siveke

Director

Deutsches Krebsforschungszentrum

GERMANY
View details

Constantin Seibold

Karlsruher Institut für Technologie

GERMANY
View details

Alexander Effland

University of Bonn

GERMANY
View details

Felix Nensa

University Hospital Essen

GERMANY
View details