High-quality human transcription is essential for training and improving Automatic Speech Recognition (ASR) models. Recent study~\cite{libricrowd} has found that every 1% worse transcription Word Error Rate (WER) increases approximately 2% ASR WER by using the transcriptions to train ASR models. Transcription errors are inevitable for even highly-trained annotators. However, few studies have explored human transcription correction. Error correction methods for other problems, such as ASR error correction and grammatical error correction, do not perform sufficiently for this problem. Therefore, we propose HTEC for Human Transcription Error Correction. HTEC consists of two stages: Trans-Checker, an error detection model that predicts and masks erroneous words, and Trans-Filler, a sequence-to-sequence generative model that fills masked positions. We propose a holistic list of correction operations, including four novel operations handling deletion errors. We further propose a variant of embeddings that incorporates phoneme information into the input of the transformer. HTEC outperforms other methods by a large margin and surpasses human annotators by 2.2% to 4.5% in WER. Finally, we deployed HTEC to assist human annotators and showed HTEC is particularly effective as a co-pilot, which improves transcription quality by 15.1% without sacrificing transcription velocity.

Data augmentation is a common practice to help generalization in the procedure of deep model training. In the context of physiological time series classification, previous research has primarily focused on label-invariant data augmentation methods. However, another class of augmentation techniques (\textit{i.e., Mixup}) that emerged in the computer vision field has yet to be fully explored in the time series domain. In this study, we systematically review the mix-based augmentations, including mixup, cutmix, and manifold mixup, on six physiological datasets, evaluating their performance across different sensory data and classification tasks. Our results demonstrate that the three mix-based augmentations can consistently improve the performance on the six datasets. More importantly, the improvement does not rely on expert knowledge or extensive parameter tuning. Lastly, we provide an overview of the unique properties of the mix-based augmentation methods and highlight the potential benefits of using the mix-based augmentation in physiological time series data.

Current deep learning-based solutions for image analysis tasks are commonly incapable of handling problems to which multiple different plausible solutions exist. In response, posterior-based methods such as conditional Diffusion Models and Invertible Neural Networks have emerged; however, their translation is hampered by a lack of research on adequate validation. In other words, the way progress is measured often does not reflect the needs of the driving practical application. Closing this gap in the literature, we present the first systematic framework for the application-driven validation of posterior-based methods in inverse problems. As a methodological novelty, it adopts key principles from the field of object detection validation, which has a long history of addressing the question of how to locate and match multiple object instances in an image. Treating modes as instances enables us to perform mode-centric validation, using well-interpretable metrics from the application perspective. We demonstrate the value of our framework through instantiations for a synthetic toy example and two medical vision use cases: pose estimation in surgery and imaging-based quantification of functional tissue parameters for diagnostics. Our framework offers key advantages over common approaches to posterior validation in all three examples and could thus revolutionize performance assessment in inverse problems.

Aims. The purpose of this study is to create a multi-stage machine learning model to predict cardiac resynchronization therapy (CRT) response for heart failure (HF) patients. This model exploits uncertainty quantification to recommend additional collection of single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) variables if baseline clinical variables and features from electrocardiogram (ECG) are not sufficient. Methods. 218 patients who underwent rest-gated SPECT MPI were enrolled in this study. CRT response was defined as an increase in left ventricular ejection fraction (LVEF) > 5% at a 6 month follow-up. A multi-stage ML model was created by combining two ensemble models. Results. The response rate for CRT was 55.5% (n = 121) with overall male gender 61.0% (n = 133), an average age of 62.0, and LVEF of 27.7. The multi-stage model performed similarly to Ensemble 2 (which utilized the additional SPECT data) with AUC of 0.75 vs. 0.77, accuracy of 0.71 vs. 0.69, sensitivity of 0.70 vs. 0.72, and specificity 0.72 vs. 0.65, respectively. However, the multi-stage model only required SPECT MPI data for 52.7% of the patients across all folds. Conclusions. By using rule-based logic stemming from uncertainty quantification, the multi-stage model was able to reduce the need for additional SPECT MPI data acquisition without sacrificing performance.

In the current ML field models are getting larger and more complex, and data used for model training are also getting larger in quantity and higher in dimensions. Therefore, in order to train better models, and save training time and computational resources, a good Feature Selection (FS) method in the preprocessing stage is necessary. Feature importance (FI) is of great importance since it is the basis of feature selection. Therefore, this paper creatively introduces the calculation of PN (the probability of Necessity), PN (the probability of Sufficiency), and PNS (the probability of Necessity and Sufficiency) of Causality into quantifying feature importance and creates 3 new FI measuring methods---- PN-FI, which means how much importance a feature has in image recognition tasks, PS-FI that means how much importance a feature has in image generating tasks, and PNS-FI which measures both. The main body of this paper is three RCTs, with whose results we show how PS-FI, PN-FI, and PNS-FI of 3 features----dog nose, dog eyes, and dog mouth are calculated. The experiments show that firstly, FI values are intervals with tight upper and lower bounds. Secondly, the feature dog eyes has the most importance while the other two have almost the same. Thirdly, the bounds of PNS and PN are tighter than that of PS's.

Fair feature selection for classification decision tasks has recently garnered significant attention from researchers. However, existing fair feature selection algorithms fall short of providing a full explanation of the causal relationship between features and sensitive attributes, potentially impacting the accuracy of fair feature identification. To address this issue, we propose a Fair Causal Feature Selection algorithm, called FairCFS. Specifically, FairCFS constructs a localized causal graph that identifies the Markov blankets of class and sensitive variables, to block the transmission of sensitive information for selecting fair causal features. Extensive experiments on seven public real-world datasets validate that FairCFS has comparable accuracy compared to eight state-of-the-art feature selection algorithms, while presenting more superior fairness.

Several artificial neural networks (ANNs) have been developed recently to predict the prognosis of different types of cancer based on the tumor transcriptome. However, they have not demonstrated significantly better performance than the regularized Cox proportional hazards regression model. Training an ANN is challenging with a limited number of data samples and a high-dimensional feature space. Recent advancements in image classification have shown that contrastive learning (CL) can facilitate further learning tasks by learning good feature representation from a limited number of data samples. In this paper, we applied supervised CL to tumor gene expression and clinical data to learn feature representations in a low-dimensional space. We then used these learned features to train a Cox model for predicting cancer prognosis. Using data from The Cancer Genome Atlas (TCGA), we demonstrated that our CL-based Cox model (CLCox) significantly outperformed existing methods in predicting the prognosis of 19 types of cancer considered. We also developed CL-based classifiers to classify tumors into different risk groups and showed that CL can significantly improve classification accuracy. Specifically, our CL-based classifiers achieved an area under the receiver operating characteristic curve (AUC) of greater than 0.8 for 14 types of cancer and and an AUC of greater than 0.9 for 2 types of cancer. CLCox models and CL-based classifiers trained with TCGA lung cancer and prostate cancer data were validated with the data of two independent cohorts.

Early warning systems (EWS) are predictive tools at the center of recent efforts to improve graduation rates in public schools across the United States. These systems assist in targeting interventions to individual students by predicting which students are at risk of dropping out. Despite significant investments in their widespread adoption, there remain large gaps in our understanding of the efficacy of EWS, and the role of statistical risk scores in education. In this work, we draw on nearly a decade's worth of data from a system used throughout Wisconsin to provide the first large-scale evaluation of the long-term impact of EWS on graduation outcomes. We present empirical evidence that the prediction system accurately sorts students by their dropout risk. We also find that it may have caused a single-digit percentage increase in graduation rates, though our empirical analyses cannot reliably rule out that there has been no positive treatment effect. Going beyond a retrospective evaluation of DEWS, we draw attention to a central question at the heart of the use of EWS: Are individual risk scores necessary for effectively targeting interventions? We propose a simple mechanism that only uses information about students' environments -- such as their schools, and districts -- and argue that this mechanism can target interventions just as efficiently as the individual risk score-based mechanism. Our argument holds even if individual predictions are highly accurate and effective interventions exist. In addition to motivating this simple targeting mechanism, our work provides a novel empirical backbone for the robust qualitative understanding among education researchers that dropout is structurally determined. Combined, our insights call into question the marginal value of individual predictions in settings where outcomes are driven by high levels of inequality.

We studied the capability of automated machine translation in the online video education space by automatically translating Khan Academy videos with state-of-the-art translation models and applying text-to-speech synthesis and audio/video synchronization to build engaging videos in target languages. We also analyzed and established two reliable translation confidence estimators based on round-trip translations in order to efficiently manage translation quality and reduce human translation effort. Finally, we developed a deployable system to deliver translated videos to end users and collect user corrections for iterative improvement.

Misinformation is a global concern and limiting its spread is critical for protecting democracy, public health, and consumers. We propose that consumers' own social media post-histories are an underutilized data source to study what leads them to share links to fake-news. In Study 1, we explore how textual cues extracted from post-histories distinguish fake-news sharers from random social media users and others in the misinformation ecosystem. Among other results, we find across two datasets that fake-news sharers use more words related to anger, religion and power. In Study 2, we show that adding textual cues from post-histories improves the accuracy of models to predict who is likely to share fake-news. In Study 3, we provide a preliminary test of two mitigation strategies deduced from Study 1 - activating religious values and reducing anger - and find that they reduce fake-news sharing and sharing more generally. In Study 4, we combine survey responses with users' verified Twitter post-histories and show that using empowering language in a fact-checking browser extension ad increases download intentions. Our research encourages marketers, misinformation scholars, and practitioners to use post-histories to develop theories and test interventions to reduce the spread of misinformation.