Explore the vast range of titles available.

The purpose of this study is to examine existing deep learning techniques for addressing class imbalanced data. Effective classification with imbalanced data is an important area of research, as high class imbalance is naturally inherent in many real-world applications, e.g., fraud detection and cancer detection. Moreover, highly imbalanced data poses added difficulty, as most learners will exhibit bias towards the majority class, and in extreme cases, may ignore the minority class altogether. Class imbalance has been studied thoroughly over the last two decades using traditional machine learning models, i.e. non-deep learning. Despite recent advances in deep learning, along with its increasing popularity, very little empirical work in the area of deep learning with class imbalance exists. Having achieved record-breaking performance results in several complex domains, investigating the use of deep neural networks for problems containing high levels of class imbalance is of great interest. Available studies regarding class imbalance and deep learning are surveyed in order to better understand the efficacy of deep learning when applied to class imbalanced data. This survey discusses the implementation details and experimental results for each study, and offers additional insight into their strengths and weaknesses. Several areas of focus include: data complexity, architectures tested, performance interpretation, ease of use, big data application, and generalization to other domains. We have found that research in this area is very limited, that most existing work focuses on computer vision tasks with convolutional neural networks, and that the effects of big data are rarely considered. Several traditional methods for class imbalance, e.g. data sampling and cost-sensitive learning, prove to be applicable in deep learning, while more advanced methods that exploit neural network feature learning abilities show promising results. The survey concludes with a discussion that highlights various gaps in deep learning from class imbalanced data for the purpose of guiding future research.

Access to affordable healthcare is a nationwide concern that impacts a large majority of the United States population. Medicare is a Federal Government healthcare program that provides affordable health insurance to the elderly population and individuals with select disabilities. Unfortunately, there is a significant amount of fraud, waste, and abuse within the Medicare system that costs taxpayers billions of dollars and puts beneficiaries’ health and welfare at risk. Previous work has shown that publicly available Medicare claims data can be leveraged to construct machine learning models capable of automating fraud detection, but challenges associated with class-imbalanced big data hinder performance. With a minority class size of 0.03% and an opportunity to improve existing results, we use the Medicare fraud detection task to compare six deep learning methods designed to address the class imbalance problem. Data-level techniques used in this study include random over-sampling (ROS), random under-sampling (RUS), and a hybrid ROS–RUS. The algorithm-level techniques evaluated include a cost-sensitive loss function, the Focal Loss , and the Mean False Error Loss . A range of class ratios are tested by varying sample rates and desirable class-wise performance is achieved by identifying optimal decision thresholds for each model. Neural networks are evaluated on a 20% holdout test set, and results are reported using the area under the receiver operating characteristic curve (AUC). Results show that ROS and ROS–RUS perform significantly better than baseline and algorithm-level methods with average AUC scores of 0.8505 and 0.8509, while ROS–RUS maximizes efficiency with a 4× speedup in training time. Plain RUS outperforms baseline methods with up to 30× improvements in training time, and all algorithm-level methods are found to produce more stable decision boundaries than baseline methods. Thresholding results suggest that the decision threshold always be optimized using a validation set, as we observe a strong linear relationship between the minority class size and the optimal threshold. To the best of our knowledge, this is the first study to compare multiple data-level and algorithm-level deep learning methods across a range of class distributions. Additional contributions include a unique analysis of the relationship between minority class size and optimal decision threshold and state-of-the-art performance on the given Medicare fraud detection task.

Using the wrong metrics to gauge classification of highly imbalanced Big Data may hide important information in experimental results. However, we find that analysis of metrics for performance evaluation and what they can hide or reveal is rarely covered in related works. Therefore, we address that gap by analyzing multiple popular performance metrics on three Big Data classification tasks. To the best of our knowledge, we are the first to utilize three new Medicare insurance claims datasets which became publicly available in 2021. These datasets are all highly imbalanced. Furthermore, the datasets are comprised of completely different data. We evaluate the performance of five ensemble learners in the Machine Learning task of Medicare fraud detection. Random Undersampling (RUS) is applied to induce five class ratios. The classifiers are evaluated with both the Area Under the Receiver Operating Characteristic Curve (AUC), and Area Under the Precision Recall Curve (AUPRC) metrics. We show that AUPRC provides a better insight into classification performance. Our findings reveal that the AUC metric hides the performance impact of RUS. However, classification results in terms of AUPRC show RUS has a detrimental effect. We show that, for highly imbalanced Big Data, the AUC metric fails to capture information about precision scores and false positive counts that the AUPRC metric reveals. Our contribution is to show AUPRC is a more effective metric for evaluating the performance of classifiers when working with highly imbalanced Big Data.

Output thresholding is well-suited for addressing class imbalance, since the technique does not increase dataset size, run the risk of discarding important instances, or modify an existing learner. Through the use of the Credit Card Fraud Detection Dataset, this study proposes a threshold optimization approach that factors in the constraint True Positive Rate (TPR) ≥ True Negative Rate (TNR). Our findings indicate that an increase of the Area Under the Precision–Recall Curve (AUPRC) score is associated with an improvement in threshold-based classification scores, while an increase of positive class prior probability causes optimal thresholds to increase. In addition, we discovered that best overall results for the selection of an optimal threshold are obtained without the use of Random Undersampling (RUS). Furthermore, with the exception of AUPRC, we established that the default threshold yields good performance scores at a balanced class ratio. Our evaluation of four threshold optimization techniques, eight threshold-dependent metrics, and two threshold-agnostic metrics defines the uniqueness of this research.

Training predictive models with class-imbalanced data has proven to be a difficult task. This problem is well studied, but the era of big data is producing more extreme levels of imbalance that are increasingly difficult to model. We use three data sets of varying complexity to evaluate data sampling strategies for treating high class imbalance with deep neural networks and big data. Sampling rates are varied to create training distributions with positive class sizes from 0.025%–90%. The area under the receiver operating characteristics curve is used to compare performance, and thresholding is used to maximize class performance. Random over-sampling (ROS) consistently outperforms under-sampling (RUS) and baseline methods. The majority class proves susceptible to misrepresentation when using RUS, and results suggest that each data set is uniquely sensitive to imbalance and sample size. The hybrid ROS-RUS maximizes performance and efficiency, and is our preferred method for treating high imbalance within big data problems.

Automated methods for detecting fraudulent healthcare providers have the potential to save billions of dollars in healthcare costs and improve the overall quality of patient care. This study presents a data-centric approach to improve healthcare fraud classification performance and reliability using Medicare claims data. Publicly available data from the Centers for Medicare & Medicaid Services (CMS) are used to construct nine large-scale labeled data sets for supervised learning. First, we leverage CMS data to curate the 2013–2019 Part B, Part D, and Durable Medical Equipment, Prosthetics, Orthotics, and Supplies (DMEPOS) Medicare fraud classification data sets. We provide a review of each data set and data preparation techniques to create Medicare data sets for supervised learning and we propose an improved data labeling process. Next, we enrich the original Medicare fraud data sets with up to 58 new provider summary features. Finally, we address a common model evaluation pitfall and propose an adjusted cross-validation technique that mitigates target leakage to provide reliable evaluation results. Each data set is evaluated on the Medicare fraud classification task using extreme gradient boosting and random forest learners, multiple complementary performance metrics, and 95% confidence intervals. Results show that the new enriched data sets consistently outperform the original Medicare data sets that are currently used in related works. Our results encourage the data-centric machine learning workflow and provide a strong foundation for data understanding and preparation techniques for machine learning applications in healthcare fraud.

Purpose Epithelial ovarian carcinoma (EOC) is the most lethal of all human gynecologic malignancies. We previously reported that vaccination of female mice with the extracellular domain of anti-Müllerian hormone receptor II (AMHR2-ED) in complete Freund’s adjuvant (CFA) generates AMHR2-ED specific immunoglobulin G (IgG) that provides prevention and therapy against murine EOCs. Although CFA is the “gold standard” adjuvant in animal studies, it is not approved for human use because it often induces painful granulomas and abscesses. Thus, the objective of this study is to identify an alternative adjuvant to CFA for use in our ovarian cancer vaccine clinical trials. Materials and Methods Because it has been used successfully without serious adverse effects in numerous human clinical trials, we selected the IgG-inducing squalene-based adjuvant, AddaVax™, for evaluation of its ability to facilitate vaccine-induced prevention and treatment of EOC in mice. To this end, we immunized female C57BL/6 mice with recombinant mouse AMHR2-ED emulsified with either AddaVax or CFA as adjuvant and compared the results. Results We found that formulation of the AMHR2-ED vaccine with AddaVax adjuvant induced high serum titers of IgG and significant inhibition of EOC growth with significantly enhanced overall survival of mice using both prevention and therapeutic protocols. These results were compared favorably with results obtained using CFA as an adjuvant in the AMHR2-ED vaccine. Conclusion Our data indicate that the AMHR2-ED vaccine formulated with AddaVax may be used in human clinical trials and thereby serve as a novel and effective way to control human EOC.

BackgroundTesticular cancer is the most common male neoplasm occurring in men between the ages of 20 and 34. Although germ-line testicular tumors respond favorably to current standard of care, testicular stromal cell (TSC) tumors derived from Sertoli cells or Leydig cells often fail to respond to chemotherapy or radiation therapy and have a 5-year overall survival significantly lower than the more common and more treatable germ line testicular tumors.MethodsTo improve outcomes for TSC cancer, we have developed a therapeutic vaccine targeting inhibin-α, a protein produced by normal Sertoli and Leydig cells of the testes and expressed in the majority of TSC tumors.ResultsWe found that vaccination against recombinant mouse inhibin-α provides protection and therapy against transplantable I-10 mouse TSC tumors in male BALB/c mice. Similarly, we found that vaccination with the immunodominant p215-234 peptide of inhibin-α (Inα 215-234) inhibits the growth of autochthonous TSC tumors occurring in male SJL.AMH-SV40Tag transgenic mice. The tumor immunity and enhanced overall survival induced by inhibin-α vaccination may be passively transferred into naive male BALB/c recipients with either CD4+ T cells, B220+ B cells, or sera from inhibin-α primed mice.ConclusionsConsidering the lack of any alternative effective treatment for chemo- and radiation-resistant TSC tumors, our results provide for the first time a rational basis for immune-mediated control of these aggressive and lethal variants of testicular cancer.

Anti-Müllerian hormone receptor, type II (AMHR2), is a differentiation protein expressed in 90% of primary epithelial ovarian carcinomas (EOCs), the most deadly gynecologic malignancy. We propose that AMHR2 may serve as a useful target for vaccination against EOC. To this end, we generated the recombinant 399-amino acid cytoplasmic domain of mouse AMHR2 (AMHR2-CD) and tested its efficacy as a vaccine target in inhibiting growth of the ID8 transplantable EOC cell line in C57BL/6 mice and in preventing growth of autochthonous EOCs that occur spontaneously in transgenic mice. We found that AMHR2-CD immunization of C57BL/6 females induced a prominent antigen-specific proinflammatory CD4+ T cell response that resulted in a mild transient autoimmune oophoritis that resolved rapidly with no detectable lingering adverse effects on ovarian function. AMHR2-CD vaccination significantly inhibited ID8 tumor growth when administered either prophylactically or therapeutically, and protection against EOC growth was passively transferred into naive recipients with AMHR2-CD-primed CD4+ T cells but not with primed B cells. In addition, prophylactic AMHR2-CD vaccination of TgMISIIR-TAg transgenic mice significantly inhibited growth of autochthonous EOCs and provided a 41.7% increase in mean overall survival. We conclude that AMHR2-CD vaccination provides effective immunotherapy of EOC with relatively benign autoimmune complications.

Immunologically targeting α-lactalbumin, a breast-specific protein highly expressed in breast carcinomas but absent from nonlactating mammary cells, provides protection against breast cancer in mice. This strategy may protect women against breast cancer in their post–child-bearing years, when lactation is readily avoidable and risk for developing breast cancer is high. Although vaccination is most effective when used to prevent disease, cancer vaccine development has focused predominantly on providing therapy against established growing tumors 1 . The difficulty in developing prophylactic cancer vaccines is primarily due to the fact that tumor antigens are variations of self proteins and would probably mediate profound autoimmune complications if used in a preventive vaccine setting 2 . Here we use several mouse breast cancer models to define a prototypic strategy for prophylactic cancer vaccination. We selected α-lactalbumin as our target vaccine autoantigen because it is a breast-specific differentiation protein expressed in high amounts in the majority of human breast carcinomas 3 , 4 , 5 and in mammary epithelial cells only during lactation 6 , 7 , 8 , 9 . We found that immunoreactivity against α-lactalbumin provides substantial protection and therapy against growth of autochthonous tumors in transgenic mouse models of breast cancer and against 4T1 transplantable breast tumors in BALB/c mice. Because α-lactalbumin is conditionally expressed only during lactation, vaccination-induced prophylaxis occurs without any detectable inflammation in normal nonlactating breast tissue. Thus, α-lactalbumin vaccination may provide safe and effective protection against the development of breast cancer for women in their post–child-bearing, premenopausal years, when lactation is readily avoidable and risk for developing breast cancer is high 10 .