Daan van Den Broek

Daan van Den Broek

Auto-generated profile, based on publicly available information

Daan van Den Broek

Finnish Meteorological Institute Helsinki Finland

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
26 May 2025 in Journal of the American Medical Informatics Association
Verified
Journal Article
Open access
MYMelda Yeghaian
Melda Yeghaian
ZBZuhir Bodalal
Zuhir Bodalal
DBDaan van Den Broek
Daan van Den Broek
JHJohn B A G Haanen
John B A G Haanen
RBRegina GH Beets-Tan
Regina GH Beets-Tan
MGMarcel van Gerven
Marcel van Gerven
Objectives: Immunotherapies have revolutionized the landscape of cancer treatments. However, our understanding of response patterns in advanced cancers treated with immunotherapy remains limited. By leveraging routinely collected noninvasive longitudinal and multimodal data with artificial intelligence, we could unlock the potential to transform immunotherapy for cancer patients, paving the way for personalized treatment approaches. Materials and Methods: In this study, we developed a novel artificial neural network architecture, multimodal transformer-based simple temporal attention (MMTSimTA) network, building upon a combination of recent successful developments. We integrated pre- and on-treatment blood measurements, prescribed medications, and CT-based volumes of organs from a large pan-cancer cohort of 694 patients treated with immunotherapy to predict mortality at 3, 6, 9, and 12 months. Different variants of our extended MMTSimTA network were implemented and compared to baseline methods, incorporating intermediate and late fusion-based integration methods. Results: The strongest prognostic performance was demonstrated using a variant of the MMTSimTA model with area under the curves of 0.84 ± 0.04, 0.83 ± 0.02, 0.82 ± 0.02, 0.81 ± 0.03 for 3-, 6-, 9-, and 12-month survival prediction, respectively. Discussion: Our findings show that integrating noninvasive longitudinal data using our novel architecture yields an improved multimodal prognostic performance, especially in short-term survival prediction. Conclusion: Our study demonstrates that multimodal longitudinal integration of noninvasive data using deep learning may offer a promising approach for personalized prognostication in immunotherapy-treated cancer patients.

15 March 2024 in Geophysical Research Letters
Verified
Journal Article
Open access
PDF file
MRMika Rantanen
Mika Rantanen
DBDaan van Den Broek
Daan van Den Broek
JCJoona Cornér
Joona Cornér
VSVictoria Sinclair
Victoria Sinclair
MJMilla M. Johansson
Milla M. Johansson
KJKirsti Jylhä
Kirsti Jylhä
In the Baltic Sea, sea level variations are often very pronounced. During the winter season, storm surges caused by strong extratropical cyclones (ETCs) can have major societal impacts on coastal cities. In this study, using reanalysis‐based cyclone tracks and in‐situ tide gauge records, we show that serial cyclone clustering (SCC) leads to higher sea levels in the Baltic Sea than situations where only one ETC passes the tide gauge. Consequently, almost half of extreme sea level events in the Baltic Sea are associated with cyclone clustering periods. For example, in Helsinki, 45% of the extreme sea level events coincided with SCC periods of three or more ETCs, while only 6% of the events coincided with a single ETC. Our study represents a significant advance in the understanding of the factors influencing sea level variations in the Baltic Sea.

15 April 2025 in Geophysical Research Letters
Verified
Journal Article
Open access
DBDaan van Den Broek
Daan van Den Broek
GUGabin H. Urbancic
Gabin H. Urbancic
MRMika Rantanen
Mika Rantanen
TVTimo Vihma
Timo Vihma
The Svalbard archipelago region is one of the fastest warming regions in the world. The majority of warming has occurred in wintertime, although the summer season has also been warming approximately linearly since 1980. Nevertheless, in recent years, many monthly and seasonal temperature records have been set in summer, with 2024 breaking its mean summer and August temperature records by the largest margins in the measurement history. In this study, we examine 2024s temperature extremes. The mean August temperature stands out as falling outside of the climatological distribution even after accounting for the warming trend. Our findings suggest that 2024s records are a result of an unprecedented combination of persistent atmospheric patterns and interaction with the warming seas. Given the exceptional nature of these temperature extremes, we recommend further research to the potential increase in the persistence of weather and the consequences of associated temperature extremes.

7 August 2024 in Neuro-Oncology
Verified
Journal Article
Closed access
JWJ W Tijmen van der Wel
J W Tijmen van der Wel
MBMirjam C Boelens
Mirjam C Boelens
MJMerel Jebbink
Merel Jebbink
SSSietske A Smulders
Sietske A Smulders
KMKlaartje W Maas
Klaartje W Maas
DBDieta Brandsma
Dieta Brandsma
Background: Diagnosis and treatment of leptomeningeal metastases (LM) in epidermal growth factor receptor mutation-positive (EGFRm +) non-small-cell lung carcinoma (NSCLC) is challenging. We aimed to identify resistance mechanisms (RM) to osimertinib in cerebrospinal fluid (CSF) and plasma. Methods: EGFRm + patients with new or progressive LM during osimertinib were enrolled. NGS Ampliseq was performed on DNA isolated from CSF. Patients were prescribed osimertinib dose escalation (DE, 160 mg QD) following lumbar puncture. Clinical and radiological response was evaluated 4 weeks after osimertinib DE. Results: Twenty-eight patients were included. The driver mutation was identified in 93% of CSF samples (n = 26). Seven (27%) harbored ≥1 RM. Twenty-five patients (89%) were prescribed osimertinib DE. Four weeks afterwards, symptoms improved in 5 patients, stabilized in 9 and worsened in 11 patients. Twenty-one (84%) patients underwent MR imaging. Four showed radiological improvement, 14 stabilization, and 3 worsening. Conclusions: In 27% of patients, an RM was found in CSF ctDNA, none of which are targetable at the time of writing, and the clinical efficacy of osimertinib DE seems limited. There is much to gain in diagnostic as well as therapeutic strategies in EGFRm + NSCLC LM.

24 December 2025
Verified
Journal Article
Open access
CRCarmen Rubio-Alarcón
Carmen Rubio-Alarcón
AGAndrew Georgiadis
Andrew Georgiadis
IFIngrid A Franken
Ingrid A Franken
HWHaoyue Wang
Haoyue Wang
SNSietske C M W van Nassau
Sietske C M W van Nassau
OGOther Members of the PLCRC-MEDOCC Group
Other Members of the PLCRC-MEDOCC Group
Circulating tumour DNA (ctDNA) is a promising biomarker to guide clinical decision-making. The aim of this study was to investigate the prognostic value of postoperative ctDNA in patients with stage III colon cancer who received adjuvant chemotherapy (ACT). PROVENC3 was a multicentre prospective study of patients who underwent resection of pathological stage III colon cancer. Blood samples were collected at a median of 13 (interquartile range 4-20) days after resection. The presence of minimal residual disease was determined using Labcorp® Plasma Detect™, a novel tumour-informed whole genome sequencing (WGS) ctDNA test. The primary endpoint was 3-year time to recurrence (TTR). ctDNA status was further combined with pathological risk status to investigate the combined prognostic value. The median follow-up of the 209 patients who were included was 40 months. In total, 28 patients (13%) had detectable ctDNA after surgery. Postoperative ctDNA-positive patients had a worse TTR compared with ctDNA-negative patients (HR 6.2 (95% c.i. 3.4 to 11.2); P < 0.001). Of all ctDNA-positive patients, 36% did not develop recurrences during 3-year follow-up. Detectable ctDNA after ACT was associated with worse TTR (HR 7.9 (95% c.i. 3.9 to 15.9); P < 0.001). ctDNA status combined with pathological risk classification resulted in a 3-year recurrence risk that varied from 82% for pathological high-risk (pT4/N2) ctDNA-positive patients to 7% for pathological low-risk (pT1-3 N1) ctDNA-negative patients (HR 28.5 (95% c.i. 10.5 to 77.2); P < 0.001). Postoperative ctDNA detection using a tumour-informed WGS test improves prognosis stratification in stage III colon cancer and may help to personalize adjuvant treatment.

16 April 2024 in Geoscientific Model Development
Verified
Journal Article
Open access
PDF file
CBClément Bouvier
Clément Bouvier
DBDaan van Den Broek
Daan van Den Broek
MEMadeleine Ekblom
Madeleine Ekblom
VSVictoria Sinclair
Victoria Sinclair
This article presents a description of an analytical, stable, and flexible initial background state for both dry and moist baroclinic wave simulation on an aquaplanet in order to test the dynamical core of numerical weather prediction models and study the dynamics and evolution of extratropical cyclones. The initial background state is derived from an analytical zonal wind speed field, or jet structure, and the hydrostatic primitive equations for moist adiabatic and frictionless flow in spherical coordinates. A baroclinic wave can develop if a perturbation is added to the zonal wind speed field. This new baroclinic wave configuration has been implemented in the Open Integrated Forecasting System (OpenIFS) CY43R3, a global numerical weather prediction model developed by the European Centre for Medium-Range Weather Forecasts. In total, seven parameters can be used to control the generation of the initial background state and hence the development of the baroclinic waves in the OpenIFS configuration file: the jet's width, the jet's height, the maximum zonal mean wind speed of the jet, the horizontal mean of the surface virtual temperature, the surface relative humidity, the lapse rate, and the surface roughness. Nine dry and nine moist initial background states have been generated to test their stability without perturbations. The meteorological stability of the initial states is investigated by examining the spatial distributions of the equivalent potential temperature, the absolute vorticity, and the Brunt–Väisälä frequency. Moreover, the root mean square error (RMSE) of the zonal wind speed has been computed to assess their numerical stability. Finally, six dry and six moist initial background state have been used with an unbalanced perturbation to ensure that the baroclinic life cycles that develop are physically realistic. The resulting baroclinic wave is shown to be sensitive to the jet's width. This configuration for baroclinic wave simulations will be used to create a large ensemble of baroclinic life cycles to study how extratropical cyclones may evolve in the future.