While investigating methods to predict small molecule potencies, we found random forests or support vector machines paired with extended-connectivity fingerprints (ECFP) consistently outperformed recently developed methods. A detailed investigation into regression algorithms and molecular fingerprints revealed gradient-boosted decision trees, particularly CatBoost, in conjunction with a combination of ECFP, Avalon, and ErG fingerprints, as well as 200 molecular properties, to be most effective. Incorporating a graph neural network fingerprint further enhanced performance. We successfully validated our model across 22 Therapeutics Data Commons ADMET benchmarks. Our findings underscore the significance of richer molecular representations for accurate property prediction.

Recent research has shown that artificial intelligence (AI) models can exhibit bias in performance when trained using data that are imbalanced by protected attribute(s). Most work to date has focused on deep learning models, but classical AI techniques that make use of hand-crafted features may also be susceptible to such bias. In this paper we investigate the potential for race bias in random forest (RF) models trained using radiomics features. Our application is prediction of tumour molecular subtype from dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) of breast cancer patients. Our results show that radiomics features derived from DCE-MRI data do contain race-identifiable information, and that RF models can be trained to predict White and Black race from these data with 60-70% accuracy, depending on the subset of features used. Furthermore, RF models trained to predict tumour molecular subtype using race-imbalanced data seem to produce biased behaviour, exhibiting better performance on test data from the race on which they were trained.

Privacy-preserving learning of gradient boosting decision trees (GBDT) has the potential for strong utility-privacy tradeoffs for tabular data, such as census data or medical meta data: classical GBDT learners can extract non-linear patterns from small sized datasets. The state-of-the-art notion for provable privacy-properties is differential privacy, which requires that the impact of single data points is limited and deniable. We introduce a novel differentially private GBDT learner and utilize four main techniques to improve the utility-privacy tradeoff. (1) We use an improved noise scaling approach with tighter accounting of privacy leakage of a decision tree leaf compared to prior work, resulting in noise that in expectation scales with $O(1/n)$, for $n$ data points. (2) We integrate individual R\'enyi filters to our method to learn from data points that have been underutilized during an iterative training process, which -- potentially of independent interest -- results in a natural yet effective insight to learning streams of non-i.i.d. data. (3) We incorporate the concept of random decision tree splits to concentrate privacy budget on learning leaves. (4) We deploy subsampling for privacy amplification. Our evaluation shows for the Abalone dataset ($<4k$ training data points) a $R^2$-score of $0.39$ for $\varepsilon=0.15$, which the closest prior work only achieved for $\varepsilon=10.0$. On the Adult dataset ($50k$ training data points) we achieve test error of $18.7\,\%$ for $\varepsilon=0.07$ which the closest prior work only achieved for $\varepsilon=1.0$. For the Abalone dataset for $\varepsilon=0.54$ we achieve $R^2$-score of $0.47$ which is very close to the $R^2$-score of $0.54$ for the nonprivate version of GBDT. For the Adult dataset for $\varepsilon=0.54$ we achieve test error $17.1\,\%$ which is very close to the test error $13.7\,\%$ of the nonprivate version of GBDT.

Federated Learning (FL) [1] is a novel machine learning paradigm where multiple parties collaboratively build machine learning models without centralizing their data. The concept of FL was first proposed by Google in 2016 [2] to describe a cross-device scenario where millions of mobile devices are coordinated by a central server while local data are not transferred. This concept is soon extended to a cross-silo collaboration scenario among organizations [3], where a small number of reliable organizations join a federation to train a machine learning model. In [3], FL is, for the first time, categorized into three categories based on how data is partitioned in the sample and feature space: Horizontal Federated Learning (HFL), Vertical Federated Learning (VFL) and Federated Transfer Learning (FTL) (See Figure 1). HFL refers to the FL setting where participants share the same feature space while holding different samples. For example, Google uses HFL to allow mobile phone users to use their dataset to collaboratively train a next-word prediction model [2]. VFL refers to the FL setting where datasets share the same samples/users while holding different features. For example, Webank uses VFL to collaborate with an invoice agency to build financial risk models for their enterprise customers [4].

This study explored the potential of gait analysis as a tool for assessing post-injury complications, e.g., infection, malunion, or hardware irritation, in patients with lower extremity fractures. The research focused on the proficiency of supervised machine learning models predicting complications using consecutive gait datasets. We identified patients with lower extremity fractures at an academic center. Patients underwent gait analysis with a chest-mounted IMU device. Using software, raw gait data was preprocessed, emphasizing 12 essential gait variables. Machine learning models including XGBoost, Logistic Regression, SVM, LightGBM, and Random Forest were trained, tested, and evaluated. Attention was given to class imbalance, addressed using SMOTE. We introduced a methodology to compute the Rate of Change (ROC) for gait variables, independent of the time difference between gait analyses. XGBoost was the optimal model both before and after applying SMOTE. Prior to SMOTE, the model achieved an average test AUC of 0.90 (95% CI: [0.79, 1.00]) and test accuracy of 86% (95% CI: [75%, 97%]). Feature importance analysis attributed importance to the duration between injury and gait analysis. Data patterns showed early physiological compensations, followed by stabilization phases, emphasizing prompt gait analysis. This study underscores the potential of machine learning, particularly XGBoost, in gait analysis for orthopedic care. Predicting post-injury complications, early gait assessment becomes vital, revealing intervention points. The findings support a shift in orthopedics towards a data-informed approach, enhancing patient outcomes.

The COVID-19 pandemic has left a lasting impact on individuals, with many experiencing persistent symptoms, including inflammation, in the post-acute phase of the disease. Detecting and monitoring these inflammatory biomarkers is critical for timely intervention and improved patient outcomes. This study employs machine learning techniques to automate the identification of persistent inflammatory biomarkers in 290 post-COVID-19 patients, based on medical data collected from hospitals in Iraq. The data encompassed a wide array of clinical parameters, such as C-reactive protein and interleukin-6 levels, patient demographics, comorbidities, and treatment histories. Rigorous data preprocessing and feature selection processes were implemented to optimize the dataset for machine learning analysis. Various machine learning algorithms, including logistic regression, random forests, support vector machines, and gradient boosting, were deployed to construct predictive models. These models exhibited promising results, showcasing high accuracy and precision in the identification of patients with persistent inflammation. The findings of this study underscore the potential of machine learning in automating the detection of persistent inflammatory biomarkers in post-COVID-19 patients. These models can serve as valuable tools for healthcare providers, facilitating early diagnosis and personalized treatment strategies for individuals at risk of persistent inflammation, ultimately contributing to improved post-acute COVID-19 care and patient well-being. Keywords: COVID-19, post-COVID-19, inflammation, biomarkers, machine learning, early detection.

The intensive care unit (ICU) comprises a complex hospital environment, where decisions made by clinicians have a high level of risk for the patients' lives. A comprehensive care pathway must then be followed to reduce p complications. Uncertain, competing and unplanned aspects within this environment increase the difficulty in uniformly implementing the care pathway. Readmission contributes to this pathway's difficulty, occurring when patients are admitted again to the ICU in a short timeframe, resulting in high mortality rates and high resource utilisation. Several works have tried to predict readmission through patients' medical information. Although they have some level of success while predicting readmission, those works do not properly assess, characterise and understand readmission prediction. This work proposes a standardised and explainable machine learning pipeline to model patient readmission on a multicentric database (i.e., the eICU cohort with 166,355 patients, 200,859 admissions and 6,021 readmissions) while validating it on monocentric (i.e., the MIMIC IV cohort with 382,278 patients, 523,740 admissions and 5,984 readmissions) and multicentric settings. Our machine learning pipeline achieved predictive performance in terms of the area of the receiver operating characteristic curve (AUC) up to 0.7 with a Random Forest classification model, yielding an overall good calibration and consistency on validation sets. From explanations provided by the constructed models, we could also derive a set of insightful conclusions, primarily on variables related to vital signs and blood tests (e.g., albumin, blood urea nitrogen and hemoglobin levels), demographics (e.g., age, and admission height and weight), and ICU-associated variables (e.g., unit type). These insights provide an invaluable source of information during clinicians' decision-making while discharging ICU patients.

In ski jumping, low repetition rates of jumps limit the effectiveness of training. Thus, increasing learning rate within every single jump is key to success. A critical element of athlete training is motor learning, which has been shown to be accelerated by feedback methods. In particular, a fine-grained control of the center of gravity in the in-run is essential. This is because the actual takeoff occurs within a blink of an eye ($\sim$300ms), thus any unbalanced body posture during the in-run will affect flight. This paper presents a smart, compact, and energy-efficient wireless sensor system for real-time performance analysis and biofeedback during ski jumping. The system operates by gauging foot pressures at three distinct points on the insoles of the ski boot at 100Hz. Foot pressure data can either be directly sent to coaches to improve their feedback, or fed into a ML model to give athletes instantaneous in-action feedback using a vibration motor in the ski boot. In the biofeedback scenario, foot pressures act as input variables for an optimized XGBoost model. We achieve a high predictive accuracy of 92.7% for center of mass predictions (dorsal shift, neutral stand, ventral shift). Subsequently, we parallelized and fine-tuned our XGBoost model for a RISC-V based low power parallel processor (GAP9), based on the PULP architecture. We demonstrate real-time detection and feedback (0.0109ms/inference) using our on-chip deployment. The proposed smart system is unobtrusive with a slim form factor (13mm baseboard, 3.2mm antenna) and a lightweight build (26g). Power consumption analysis reveals that the system's energy-efficient design enables sustained operation over multiple days (up to 300 hours) without requiring recharge.

Cybersecurity has become a significant issue in the digital era as a result of the growth in everyday computer use. Cybercriminals now engage in more than virus distribution and computer hacking. Cyberwarfare has developed as a result because it has become a threat to a nation's survival. Malware analysis serves as the first line of defence against an attack and is a significant component of cybercrime. Every day, malware attacks target a large number of computer users, businesses, and governmental agencies, causing billions of dollars in losses. Malware may evade multiple AV software with a very minor, cunning tweak made by its designers, despite the fact that security experts have a variety of tools at their disposal to identify it. To address this challenge, a new dataset called the Obfuscated Malware Dataset (OMD) has been developed. This dataset comprises 40 distinct malware families having 21924 samples, and it incorporates obfuscation techniques that mimic the strategies employed by malware creators to make their malware variations different from the original samples. The purpose of this dataset is to provide a more realistic and representative environment for evaluating the effectiveness of malware analysis techniques. Different conventional machine learning algorithms including but not limited to Support Vector Machine (SVM), Random Forrest (RF), Extreme Gradient Boosting (XGBOOST) etc are applied and contrasted. The results demonstrated that XGBoost outperformed the other algorithms, achieving an accuracy of f 82%, precision of 88%, recall of 80%, and an F1-Score of 83%.

We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods. TabPFN performs in-context learning (ICL), it learns to make predictions using sequences of labeled examples (x, f(x)) given in the input, without requiring further parameter updates. TabPFN is fully entailed in the weights of our network, which accepts training and test samples as a set-valued input and yields predictions for the entire test set in a single forward pass. TabPFN is a Prior-Data Fitted Network (PFN) and is trained offline once, to approximate Bayesian inference on synthetic datasets drawn from our prior. This prior incorporates ideas from causal reasoning: It entails a large space of structural causal models with a preference for simple structures. On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230$\times$ speedup. This increases to a 5 700$\times$ speedup when using a GPU. We also validate these results on an additional 67 small numerical datasets from OpenML. We provide all our code, the trained TabPFN, an interactive browser demo and a Colab notebook at https://github.com/automl/TabPFN.