Description of the dataset. by Davide Ferrari (163517)

“…Our findings reveal that traditional ML models exhibit subpar performance across all training scenarios. In contrast, MOSR, specifically configured to minimize false negatives by optimizing also for the F1-Score, outperforms other ML algorithms and consistently delivers reliable results, irrespective of the training set balance with F1-Score.22 and.28 higher than any other alternative. …”

Overview of PREDICATE developed to create viral biomass reactions and predict host-based antiviral targets using host-virus models. by Nantia Leonidou (14833068)

Supporting data for “Digital immunochromatography: A bead-based bilateral zigzag flow immuno-assay with adaptive differential noise correction for rapid and precise protein detecti... by Zhiting Peng (9722516)

Location of study area and sampling sizes. by Ming-Song Zhao (757598)

“…Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. …”

S1 Data set - by Ming-Song Zhao (757598)

“…Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. …”

The flowchart of this research. by Ming-Song Zhao (757598)

“…Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. …”

SOM modeling results using characteristic bands. by Ming-Song Zhao (757598)

“…Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. …”

Key variables selected by CARS of raw spectra. by Ming-Song Zhao (757598)

“…Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. …”

SOM modeling results using full spectral bands. by Ming-Song Zhao (757598)

“…Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. …”

S1 File - by Michael Bonert (3751348)

S2 File - by Michael Bonert (3751348)

Clinical history. by Michael Bonert (3751348)

Neuroanatomical site overlap. by Michael Bonert (3751348)

Supplementary file 1_A study on a real-world data-based VTE risk prediction model for lymphoma patients.docx by Changli He (22424818)

“…Model development incorporated three imputation methods, three sampling strategies, three feature selection approaches, and nine machine learning algorithms. Predictive performance was compared across all models.…”

Data_Sheet_1_Constructing machine learning models based on non-contrast CT radiomics to predict hemorrhagic transformation after stoke: a two-center study.docx by Yue Zhang (30585)

“…Then, five ML models were established and evaluated, and the optimal ML algorithm was used to construct the clinical, radiomics, and clinical-radiomics models. …”

Data_Sheet_1_Early Prediction of Cardiogenic Shock Using Machine Learning.PDF by Yale Chang (11701611)

“…We therefore developed and evaluated retrospectively a machine learning model based on the XGBoost (XGB) algorithm which runs automatically on patient data from the electronic health record (EHR). …”

NanoDB: Research Activity Data Management System by Lorenci Gjurgjaj (19702207)

“…<p dir="ltr">NanoDB is a Python-based application developed to optimize the management of experimental data in research settings. …”

Data_Sheet_1_Utilization of a Meningitis/Encephalitis PCR panel at the University Hospital Basel – a retrospective study to develop a diagnostic decision rule.DOCX by Andrea Erba (15420463)

“…Our results highlight the need for diagnostic-stewardship interventions when utilizing this assay by implementing a stepwise approach based on a limited number of clinical and laboratory features. …”

Supplementary data by Joon Young Kim (22352152)

“…</i> The study retrospectively analyzed clinical and laboratory data from three Korean centers to develop and validate machine learning models predicting optimal methimazole dosing in children and adolescents. …”

<b>AI for imaging plant stress in invasive species </b>(dataset from the article https://doi.org/10.1093/aob/mcaf043) by Erola Fenollosa (20977421)

“…</li><li>The dataframe of extracted colour features from all leaf images and lab variables (ecophysiological predictors and variables to be predicted)</li><li>Set of scripts used for image pre-processing, features extraction, data analytsis, visualization and Machine learning algorithms training, using ImageJ, R and Python.…”