Treatment response to ursodeoxycholic acid in primary biliary cholangitis: A systematic review and meta-analysis.

BACKGROUND: Several ursodeoxycholic acid (UDCA) treatment response definitions have been introduced in primary biliary cholangitis (PBC). However, the lack of a gold standard results in heterogeneity in second-line treatment research and clinical practice. AIMS: This study aimed to explore which UDCA treatment response endpoint serves as the most accurate predictive model of long-term outcome. METHODS: A systematic review and meta-analysis of UDCA treatment response endpoints (and corresponding validations) were performed. RESULTS: Sixteen individual UDCA treatment response endpoints and 96 external validations were found. Barcelona, Paris-1, Paris-2, Rotterdam, Toronto and GLOBE and UK-PBC Risk Scores are currently most robustly validated in external populations. The results show that the continuous models (GLOBE and UK-PBC Risk Scores) serve as the most accurate predictive models. Besides standard UDCA treatment response endpoints, the alkaline phosphatase and total bilirubin normalization has been suggested as a new therapeutic target. CONCLUSIONS: The GLOBE and UK-PBC Risk Scores are the most suitable for the real-world allocation of second-line therapies (obeticholic acid and fibrates). However, in the wake of the recent findings, alkaline phosphatase and total bilirubin normalization should be the primary outcome in trial research in PBC.

Towards annotation-efficient segmentation via image-to-image translation.

An important challenge and limiting factor in deep learning methods for medical imaging segmentation is the lack of available of annotated data to properly train models. For the specific task of tumor segmentation, the process entails clinicians labeling every slice of volumetric scans for every patient, which becomes prohibitive at the scale of datasets required to train neural networks to optimal performance. To address this, we propose a novel semi-supervised framework that allows training any segmentation (encoder-decoder) model using only information readily available in radiological data, namely the presence of a tumor in the image, in addition to a few annotated images. Specifically, we conjecture that a generative model performing domain translation on this weak label - healthy vs diseased scans - helps achieve tumor segmentation. The proposed GenSeg method first disentangles tumoral tissue from healthy "background" tissue. The latent representation is separated into (1) the common background information across both domains, and (2) the unique tumoral information. GenSeg then achieves diseased-to-healthy image translation by decoding a healthy version of the image from just the common representation, as well as a residual image that allows adding back the tumors. The same decoder that produces this residual tumor image, also outputs a tumor segmentation. Implicit data augmentation is achieved by re-using the same framework for healthy-to-diseased image translation, where a residual tumor image is produced from a prior distribution. By performing both image translation and segmentation simultaneously, GenSeg allows training on only partially annotated datasets. To test the framework, we trained U-Net-like architectures using GenSeg and evaluated their performance on 3 variants of a synthetic task, as well as on 2 benchmark datasets: brain tumor segmentation in MRI (derived from BraTS) and liver metastasis segmentation in CT (derived from LiTS). Our method outperforms the baseline semi-supervised (autoencoder and mean teacher) and supervised segmentation methods, with improvements ranging between 8-14% Dice score on the brain task and 5-8% on the liver task, when only 1% of the training images were annotated. These results show the proposed framework is ideal at addressing the problem of training deep segmentation models when a large portion of the available data is unlabeled and unpaired, a common issue in tumor segmentation.

Comparison of CNN-Learned vs. Handcrafted Features for Detection of Parkinson's Disease Dysgraphia in a Multilingual Dataset.

Parkinson's disease dysgraphia (PDYS), one of the earliest signs of Parkinson's disease (PD), has been researched as a promising biomarker of PD and as the target of a noninvasive and inexpensive approach to monitoring the progress of the disease. However, although several approaches to supportive PDYS diagnosis have been proposed (mainly based on handcrafted features (HF) extracted from online handwriting or the utilization of deep neural networks), it remains unclear which approach provides the highest discrimination power and how these approaches can be transferred between different datasets and languages. This study aims to compare classification performance based on two types of features: features automatically extracted by a pretrained convolutional neural network (CNN) and HF designed by human experts. Both approaches are evaluated on a multilingual dataset collected from 143 PD patients and 151 healthy controls in the Czech Republic, United States, Colombia, and Hungary. The subjects performed the spiral drawing task (SDT; a language-independent task) and the sentence writing task (SWT; a language-dependent task). Models based on logistic regression and gradient boosting were trained in several scenarios, specifically single language (SL), leave one language out (LOLO), and all languages combined (ALC). We found that the HF slightly outperformed the CNN-extracted features in all considered evaluation scenarios for the SWT. In detail, the following balanced accuracy (BACC) scores were achieved: SL-0.65 (HF), 0.58 (CNN); LOLO-0.65 (HF), 0.57 (CNN); and ALC-0.69 (HF), 0.66 (CNN). However, in the case of the SDT, features extracted by a CNN provided competitive results: SL-0.66 (HF), 0.62 (CNN); LOLO-0.56 (HF), 0.54 (CNN); and ALC-0.60 (HF), 0.60 (CNN). In summary, regarding the SWT, the HF outperformed the CNN-extracted features over 6% (mean BACC of 0.66 for HF, and 0.60 for CNN). In the case of the SDT, both feature sets provided almost identical classification performance (mean BACC of 0.60 for HF, and 0.58 for CNN).

Convolutional neural network ensemble for Parkinson's disease detection from voice recordings.

The computerized detection of Parkinson's disease (PD) will facilitate population screening and frequent monitoring and provide a more objective measure of symptoms, benefiting both patients and healthcare providers. Dysarthria is an early symptom of the disease and examining it for computerized diagnosis and monitoring has been proposed. Deep learning-based approaches have advantages for such applications because they do not require manual feature extraction, and while this approach has achieved excellent results in speech recognition, its utilization in the detection of pathological voices is limited. In this work, we present an ensemble of convolutional neural networks (CNNs) for the detection of PD from the voice recordings of 50 healthy people and 50 people with PD obtained from PC-GITA, a publicly available database. We propose a multiple-fine-tuning method to train the base CNN. This approach reduces the semantical gap between the source task that has been used for network pretraining and the target task by expanding the training process by including training on another dataset. Training and testing were performed for each vowel separately, and a 10-fold validation was performed to test the models. The performance was measured by using accuracy, sensitivity, specificity and area under the ROC curve (AUC). The results show that this approach was able to distinguish between the voices of people with PD and those of healthy people for all vowels. While there were small differences between the different vowels, the best performance was when/a/was considered; we achieved 99% accuracy, 86.2% sensitivity, 93.3% specificity and 89.6% AUC. This shows that the method has potential for use in clinical practice for the screening, diagnosis and monitoring of PD, with the advantage that vowel-based voice recordings can be performed online without requiring additional hardware.

Artificial Intelligence and Its Application to Minimal Hepatic Encephalopathy Diagnosis.

Hepatic encephalopathy (HE) is a brain dysfunction caused by liver insufficiency and/or portosystemic shunting. HE manifests as a spectrum of neurological or psychiatric abnormalities. Diagnosis of overt HE (OHE) is based on the typical clinical manifestation, but covert HE (CHE) has only very subtle clinical signs and minimal HE (MHE) is detected only by specialized time-consuming psychometric tests, for which there is still no universally accepted gold standard. Significant progress has been made in artificial intelligence and its application to medicine. In this review, we introduce how artificial intelligence has been used to diagnose minimal hepatic encephalopathy thus far, and we discuss its further potential in analyzing speech and handwriting data, which are probably the most accessible data for evaluating the cognitive state of the patient.

External Validation of UDCA Response Score in Slovak and Croatian Patients with Primary Biliary Cholangitis.

Background: Ursodeoxycholic acid response score (URS) is a prognostic model that estimates the baseline probability of treatment response after 12 months of ursodeoxycholic acid (UDCA) therapy in patients with primary biliary cholangitis (PBC). Aim: To independently evaluate the predictive performance of the URS model. Methods: We used a cohort of Slovak and Croatian treatment-naïve PBC patients to quantify the discrimination ability using the area under receiver operating characteristic curve (AUROC) and its 95% confidence interval (CI). Furthermore, we evaluated the calibration using calibration belts. The primary outcome was treatment response after 12 months of UDCA therapy defined as values of alkaline phosphatase ≤1.67 × upper limit of normal. Results: One hundred and ninety-four patients were included. Median pretreatment age was 56 years (interquartile range 49-62). Treatment response was achieved in 79.38% of patients. AUROC of the URS was 0.81 (95% CI 0.73-0.88) and the calibration belt revealed that response rates were correctly estimated by predicted probabilities. Conclusion: Our results confirm that the URS can be used in treatment-naïve PBC patients for estimating the treatment response probability after 12 months of UDCA therapy.