Large Language Models (LLMs) have demonstrated their efficacy across a broad spectrum of tasks in healthcare applications. However, often LLMs need to be fine-tuned on taskspecific expert-annotated data to achieve optimal performance, which can be expensive and time consuming. In this study, we fine-tune PaLM-2 (Anil et al. (2023)) with parameter efficient finetuning (PEFT) using noisy labels obtained from gemini-pro 1.0 (Google (2024)) for the detection of Schedule-of-Event (SoE) tables, which specify care plan in clinical trial protocols. We introduce a filtering mechanism to select high-confidence labels for this table classification task, thereby reducing the noise in the auto-generated labels. We show that fine-tuned PaLM-2 with those labels achieves performance that exceeds the gemini-pro 1.0 and other LLMs. Furthermore, its performance is close to a PaLM-2 fine-tuned on labels obtained from non-expert annotators. Our results show that leveraging LLM-generated labels through powerful models like gemini-pro can potentially serve as a viable strategy for improving LLM performance through fine-tuning in specialized tasks, particularly in domains where expert annotations are scarce, expensive, or time-consuming to obtain.

In this study, explainable machine learning techniques are applied to predict the toxicity of mussels in the Gulf of Trieste (Adriatic Sea) caused by harmful algal blooms. By analysing a newly created 28-year dataset containing records of toxic phytoplankton in mussel farming areas and toxin concentrations in mussels (Mytilus galloprovincialis), we train and evaluate the performance of ML models to accurately predict diarrhetic shellfish poisoning (DSP) events. The random forest model provided the best prediction of positive toxicity results based on the F1 score. Explainability methods such as permutation importance and SHAP identified key species (Dinophysis fortii and D. caudata) and environmental factors (salinity, river discharge and precipitation) as the best predictors of DSP outbreaks. These findings are important for improving early warning systems and supporting sustainable aquaculture practices.

Discovering features that set elite players apart is of great significance for eSports coaches as it enables them to arrange a more effective training program focused on improving those features. Moreover, finding such features results in a better evaluation of eSports players skills, which, besides coaches, is of interest for game developers to design games automatically adaptable to the players expertise. Sensor data combined with machine learning have already proved effective in classifying eSports players. However, the existing methods do not provide sufficient information about features that distinguish high-skilled players. In this paper, we propose an efficient method to find these features and then use them to classify players' skill levels. We first apply a time window to extract the players' sensor data, including heart rate, hand activities, etc., before and after game events in the League of Legends game. We use the extracted segments and symbolic transfer entropy to calculate connectivity features between sensors. The most relevant features are then selected using the newly developed consensus nested cross validation method. These features, representing the harmony between body parts, are finally used to find the optimum window size and classify players' skills. The classification results demonstrate a significant improvement by achieving 90.1% accuracy. Also, connectivity features between players gaze positions and keyboard, mouse, and hand activities were the most distinguishing features in classifying players' skills. The proposed method in this paper can be similarly applied to sportspeople data and potentially revolutionize the training programs in both eSports and sports industries

Mitigating hallucinations in large vision-language models (LVLMs) remains an open problem. Recent benchmarks do not address hallucinations in open-ended free-form responses, which we term "Type I hallucinations". Instead, they focus on hallucinations responding to very specific question formats -- typically a multiple-choice response regarding a particular object or attribute -- which we term "Type II hallucinations". Additionally, such benchmarks often require external API calls to models which are subject to change. In practice, we observe that a reduction in Type II hallucinations does not lead to a reduction in Type I hallucinations but rather that the two forms of hallucinations are often anti-correlated. To address this, we propose THRONE, a novel object-based automatic framework for quantitatively evaluating Type I hallucinations in LVLM free-form outputs. We use public language models (LMs) to identify hallucinations in LVLM responses and compute informative metrics. By evaluating a large selection of recent LVLMs using public datasets, we show that an improvement in existing metrics do not lead to a reduction in Type I hallucinations, and that established benchmarks for measuring Type I hallucinations are incomplete. Finally, we provide a simple and effective data augmentation method to reduce Type I and Type II hallucinations as a strong baseline.

We present AFEN (Audio Feature Ensemble Learning), a model that leverages Convolutional Neural Networks (CNN) and XGBoost in an ensemble learning fashion to perform state-of-the-art audio classification for a range of respiratory diseases. We use a meticulously selected mix of audio features which provide the salient attributes of the data and allow for accurate classification. The extracted features are then used as an input to two separate model classifiers 1) a multi-feature CNN classifier and 2) an XGBoost Classifier. The outputs of the two models are then fused with the use of soft voting. Thus, by exploiting ensemble learning, we achieve increased robustness and accuracy. We evaluate the performance of the model on a database of 920 respiratory sounds, which undergoes data augmentation techniques to increase the diversity of the data and generalizability of the model. We empirically verify that AFEN sets a new state-of-the-art using Precision and Recall as metrics, while decreasing training time by 60%.

The knowledge of type of precipitating cloud is crucial for radar based quantitative estimates of precipitation. We propose a novel model called CloudSense which uses machine learning to accurately identify the type of precipitating clouds over the complex terrain locations in the Western Ghats (WGs) of India. CloudSense uses vertical reflectivity profiles collected during July-August 2018 from an X-band radar to classify clouds into four categories namely stratiform,mixed stratiform-convective,convective and shallow clouds. The machine learning(ML) model used in CloudSense was trained using a dataset balanced by Synthetic Minority Oversampling Technique (SMOTE), with features selected based on physical characteristics relevant to different cloud types. Among various ML models evaluated Light Gradient Boosting Machine (LightGBM) demonstrate superior performance in classifying cloud types with a BAC of 0.8 and F1-Score of 0.82. CloudSense generated results are also compared against conventional radar algorithms and we find that CloudSense performs better than radar algorithms. For 200 samples tested, the radar algorithm achieved a BAC of 0.69 and F1-Score of 0.68, whereas CloudSense achieved a BAC and F1-Score of 0.77. Our results show that ML based approach can provide more accurate cloud detection and classification which would be useful to improve precipitation estimates over the complex terrain of the WG.

Privacy-enhancing blocking tools based on filter-list rules tend to break legitimate functionality. Filter-list maintainers could benefit from automated breakage detection tools that allow them to proactively fix problematic rules before deploying them to millions of users. We introduce SINBAD, an automated breakage detector that improves the accuracy over the state of the art by 20%, and is the first to detect dynamic breakage and breakage caused by style-oriented filter rules. The success of SINBAD is rooted in three innovations: (1) the use of user-reported breakage issues in forums that enable the creation of a high-quality dataset for training in which only breakage that users perceive as an issue is included; (2) the use of 'web saliency' to automatically identify user-relevant regions of a website on which to prioritize automated interactions aimed at triggering breakage; and (3) the analysis of webpages via subtrees which enables fine-grained identification of problematic filter rules.

In this paper we describe ECG-SMART-NET for identification of occlusion myocardial infarction (OMI). OMI is a severe form of heart attack characterized by complete blockage of one or more coronary arteries requiring immediate referral for cardiac catheterization to restore blood flow to the heart. Two thirds of OMI cases are difficult to visually identify from a 12-lead electrocardiogram (ECG) and can be potentially fatal if not identified in a timely fashion. Previous works on this topic are scarce, and current state-of-the-art evidence suggests that both random forests with engineered features and convolutional neural networks (CNNs) are promising approaches to improve the ECG detection of OMI. While the ResNet architecture has been successfully adapted for use with ECG recordings, it is not ideally suited to capture informative temporal features within each lead and the spatial concordance or discordance across leads. We propose a clinically informed modification of the ResNet-18 architecture. The model first learns temporal features through temporal convolutional layers with 1xk kernels followed by a spatial convolutional layer, after the residual blocks, with 12x1 kernels to learn spatial features. The new ECG-SMART-NET was benchmarked against the original ResNet-18 and other state-of-the-art models on a multisite real-word clinical dataset that consists of 10,893 ECGs from 7,297 unique patients (rate of OMI = 6.5%). ECG-SMART-NET outperformed other models in the classification of OMI with a test AUC score of 0.889 +/- 0.027 and a test average precision score of 0.587 +/- 0.087.

Objective: To detect and classify features of stigmatizing and biased language in intensive care electronic health records (EHRs) using natural language processing techniques. Materials and Methods: We first created a lexicon and regular expression lists from literature-driven stem words for linguistic features of stigmatizing patient labels, doubt markers, and scare quotes within EHRs. The lexicon was further extended using Word2Vec and GPT 3.5, and refined through human evaluation. These lexicons were used to search for matches across 18 million sentences from the de-identified Medical Information Mart for Intensive Care-III (MIMIC-III) dataset. For each linguistic bias feature, 1000 sentence matches were sampled, labeled by expert clinical and public health annotators, and used to supervised learning classifiers. Results: Lexicon development from expanded literature stem-word lists resulted in a doubt marker lexicon containing 58 expressions, and a stigmatizing labels lexicon containing 127 expressions. Classifiers for doubt markers and stigmatizing labels had the highest performance, with macro F1-scores of .84 and .79, positive-label recall and precision values ranging from .71 to .86, and accuracies aligning closely with human annotator agreement (.87). Discussion: This study demonstrated the feasibility of supervised classifiers in automatically identifying stigmatizing labels and doubt markers in medical text, and identified trends in stigmatizing language use in an EHR setting. Additional labeled data may help improve lower scare quote model performance. Conclusions: Classifiers developed in this study showed high model performance and can be applied to identify patterns and target interventions to reduce stigmatizing labels and doubt markers in healthcare systems.

In this work, we leverage machine learning techniques to identify potential biomarkers of oxygen desaturation during sleep exclusively from electroencephalogram (EEG) signals in pediatric patients with sleep apnea. Development of a machine learning technique which can successfully identify EEG signals from patients with sleep apnea as well as identify latent EEG signals which come from subjects who experience oxygen desaturations but do not themselves occur during oxygen desaturation events would provide a strong step towards developing a brain-based biomarker for sleep apnea in order to aid with easier diagnosis of this disease. We leverage a large corpus of data, and show that machine learning enables us to classify EEG signals as occurring during oxygen desaturations or not occurring during oxygen desaturations with an average 66.8% balanced accuracy. We furthermore investigate the ability of machine learning models to identify subjects who experience oxygen desaturations from EEG data that does not occur during oxygen desaturations. We conclude that there is a potential biomarker for oxygen desaturation in EEG data.