By Carrot or by Stick: The Influence of Encouraging and Discouraging Facial Feedback on Implicit Rule Learning.

Implicit learning refers to the process of unconsciously learning complex knowledge through feedback. Previous studies investigated the influences of different types of feedback (e.g., social and non-social feedback) on implicit learning. This study focused on the social information presented in the learning situation and tried to explore the effects of different social feedback on implicit rule learning. We assigned participants randomly into an encouraging facial feedback group (happy expression for correct answer, neutral but not negative expression for incorrect answer) and a discouraging facial feedback group (neutral but not happy expression for correct answer, negative expression for incorrect answer). The implicit learning task included four difficulty levels, and social feedback was presented in the learning phase but not the testing phase in two experiments. The only difference between the two experiments was that the sad face used as negative feedback in Experiment 1 was replaced with an angry face in Experiment 2 to enhance the ecological validity of the discouraging facial feedback group. These two experiments yielded consistent results: the performances in the encouraging facial feedback group were more accurate in both the learning and the testing phases at all difficulty levels. These findings indicated that the influence of encouraging social feedback for a better implicit learning achievement was stable and established a new groundwork for future research on incentive-based education, making it critical to investigate the impact of various forms of encouraging-based education on learning.

The Role of In-Group and Out-Group Facial Feedback in Implicit Rule Learning.

Implicit learning refers to the fact that people acquire new knowledge (structures or rules) without conscious awareness. Previous studies have shown that implicit learning is affected by feedback. However, few studies have investigated the role of social feedback in implicit learning concretely. Here, we conducted two experiments to explore how in-group and out-group facial feedback impact different difficulty levels of implicit rule learning. In Experiment 1, the Chinese participants in each group could only see one type of facial feedback, i.e., either in-group (East Asian) or out-group (Western) faces, and learned the implicit rule through happy and sad facial expressions. The only difference between Experiment 2 and Experiment 1 was that the participants saw both the in-group and out-group faces before group assignment to strengthen the contrast between the two group identities. The results showed that only in Experiment 2 but not Experiment 1 was there a significant interaction effect in the accuracy of tasks between the difficulty levels and groups. For the lowest difficulty level, the learning accuracy of the in-group facial feedback group was significantly higher than that of the out-group facial feedback group, whereas this did not happen at the two highest levels of difficulty. In conclusion, when the contrast of group identities was highlighted, out-group feedback reduced the accuracy of the least difficult task; on the contrary, there was no accuracy difference between out-group and in-group feedback conditions. These findings have extensively important implications for our understanding of implicit learning and improving teaching achievement in the context of educational internationalization.

Building a trustworthy AI differential diagnosis application for Crohn's disease and intestinal tuberculosis.

BACKGROUND: Differentiating between Crohn's disease (CD) and intestinal tuberculosis (ITB) with endoscopy is challenging. We aim to perform more accurate endoscopic diagnosis between CD and ITB by building a trustworthy AI differential diagnosis application. METHODS: A total of 1271 electronic health record (EHR) patients who had undergone colonoscopies at Peking Union Medical College Hospital (PUMCH) and were clinically diagnosed with CD (n = 875) or ITB (n = 396) were used in this study. We build a workflow to make diagnoses with EHRs and mine differential diagnosis features; this involves finetuning the pretrained language models, distilling them into a light and efficient TextCNN model, interpreting the neural network and selecting differential attribution features, and then adopting manual feature checking and carrying out debias training. RESULTS: The accuracy of debiased TextCNN on differential diagnosis between CD and ITB is 0.83 (CR F1: 0.87, ITB F1: 0.77), which is the best among the baselines. On the noisy validation set, its accuracy was 0.70 (CR F1: 0.87, ITB: 0.69), which was significantly higher than that of models without debias. We also find that the debiased model more easily mines the diagnostically significant features. The debiased TextCNN unearthed 39 diagnostic features in the form of phrases, 17 of which were key diagnostic features recognized by the guidelines. CONCLUSION: We build a trustworthy AI differential diagnosis application for differentiating between CD and ITB focusing on accuracy, interpretability and robustness. The classifiers perform well, and the features which had statistical significance were in agreement with clinical guidelines.

Multimodal learning on graphs for disease relation extraction.

Disease knowledge graphs have emerged as a powerful tool for artificial intelligence to connect, organize, and access diverse information about diseases. Relations between disease concepts are often distributed across multiple datasets, including unstructured plain text datasets and incomplete disease knowledge graphs. Extracting disease relations from multimodal data sources is thus crucial for constructing accurate and comprehensive disease knowledge graphs. We introduce REMAP, a multimodal approach for disease relation extraction. The REMAP machine learning approach jointly embeds a partial, incomplete knowledge graph and a medical language dataset into a compact latent vector space, aligning the multimodal embeddings for optimal disease relation extraction. Additionally, REMAP utilizes a decoupled model structure to enable inference in single-modal data, which can be applied under missing modality scenarios. We apply the REMAP approach to a disease knowledge graph with 96,913 relations and a text dataset of 1.24 million sentences. On a dataset annotated by human experts, REMAP improves language-based disease relation extraction by 10.0% (accuracy) and 17.2% (F1-score) by fusing disease knowledge graphs with language information. Furthermore, REMAP leverages text information to recommend new relationships in the knowledge graph, outperforming graph-based methods by 8.4% (accuracy) and 10.4% (F1-score). REMAP is a flexible multimodal approach for extracting disease relations by fusing structured knowledge and language information. This approach provides a powerful model to easily find, access, and evaluate relations between disease concepts.

Maternal Th17/Treg Cytokines and Small Extracellular Vesicles in Plasma as Potential Biomarkers for Preeclampsia.

Preeclampsia is one of the most serious pregnancy complications. It may be caused by immunological changes in the early placental microenvironment. The contents of small EVs may serve as biomarkers of pregnancy complications. Evidence suggests that the balance between T helper 17 (Th17) and regulatory T (Treg) cells are critical for preventing preeclampsia. The study recruited 39 pregnant women with preeclampsia and 127 healthy pregnant women. We assessed the levels of both Th17 and Treg cytokines (IL-10, IL-17, IL-21, IL-22, and TGF-ß) in their plasma and small EVs. We found significant differences in the levels of all cytokines in the plasma between the two groups during the second trimester. We also observed significant differences between the two groups in the levels of EV-encapsulated cytokines IL-21, IL-22, and TGF-ß, as well as in total small EVs, during the second trimester. The ROC analysis showed that the classification efficiency (AUC) of TGF-ß in small EVs was 0.81. TGF-ß had the best discriminant ability of all the single EV biomarkers tested, the cross-validation of the accuracy was 0.89. Th17 and Treg cytokines in plasma and small EVs may contribute to maternal immune activation and clarify the potential mechanisms of small EVs and cytokines in preeclampsia.

Development and validation of a web-based prediction tool on minor physical anomalies for schizophrenia.

In support of the neurodevelopmental model of schizophrenia, minor physical anomalies (MPAs) have been suggested as biomarkers and potential pathophysiological significance for schizophrenia. However, an integrated, clinically useful tool that used qualitative and quantitative MPAs to visualize and predict schizophrenia risk while characterizing the degree of importance of MPA items was lacking. We recruited a training set and a validation set, including 463 schizophrenia patients and 281 healthy controls to conduct logistic regression and the least absolute shrinkage and selection operator (Lasso) regression to select the best parameters of MPAs and constructed nomograms. Two nomograms were built to show the weights of these predictors. In the logistic regression model, 11 out of a total of 68 parameters were identified as the best MPA items for distinguishing between patients with schizophrenia and controls, including hair whorls, epicanthus, adherent ear lobes, high palate, furrowed tongue, hyperconvex fingernails, a large gap between first and second toes, skull height, nasal width, mouth width, and palate width. The Lasso regression model included the same variables of the logistic regression model, except for nasal width, and further included two items (interpupillary distance and soft ears) to assess the risk of schizophrenia. The results of the validation dataset verified the efficacy of the nomograms with the area under the curve 0.84 and 0.85 in the logistic regression model and lasso regression model, respectively. This study provides an easy-to-use tool based on validated risk models of schizophrenia and reflects a divergence in development between schizophrenia patients and healthy controls ( https://www.szprediction.net/ ).

Can natural language processing help differentiate inflammatory intestinal diseases in China? Models applying random forest and convolutional neural network approaches.

BACKGROUND: Differentiating between ulcerative colitis (UC), Crohn's disease (CD) and intestinal tuberculosis (ITB) using endoscopy is challenging. We aimed to realize automatic differential diagnosis among these diseases through machine learning algorithms. METHODS: A total of 6399 consecutive patients (5128 UC, 875 CD and 396 ITB) who had undergone colonoscopy examinations in the Peking Union Medical College Hospital from January 2008 to November 2018 were enrolled. The input was the description of the endoscopic image in the form of free text. Word segmentation and key word filtering were conducted as data preprocessing. Random forest (RF) and convolutional neural network (CNN) approaches were applied to different disease entities. Three two-class classifiers (UC and CD, UC and ITB, and CD and ITB) and a three-class classifier (UC, CD and ITB) were built. RESULTS: The classifiers built in this research performed well, and the CNN had better performance in general. The RF sensitivities/specificities of UC-CD, UC-ITB, and CD-ITB were 0.89/0.84, 0.83/0.82, and 0.72/0.77, respectively, while the values for the CNN of CD-ITB were 0.90/0.77. The precisions/recalls of UC-CD-ITB when employing RF were 0.97/0.97, 0.65/0.53, and 0.68/0.76, respectively, and when employing the CNN were 0.99/0.97, 0.87/0.83, and 0.52/0.81, respectively. CONCLUSIONS: Classifiers built by RF and CNN approaches had excellent performance when classifying UC with CD or ITB. For the differentiation of CD and ITB, high specificity and sensitivity were achieved as well. Artificial intelligence through machine learning is very promising in helping unexperienced endoscopists differentiate inflammatory intestinal diseases. CONFERENCE: The abstract of this article has won the first prize of the Young Investigator Award during the Asian Pacific Digestive Week (APDW) 2019 held in Kolkata, India.

Long-distance disorder-disorder relation extraction with bootstrapped noisy data.

OBJECTIVE: Artificial intelligence in healthcare increasingly relies on relations in knowledge graphs for algorithm development. However, many important relations are not well covered in existing knowledge graphs. We aim to develop a novel long-distance relation extraction algorithm that leverages the article section structure and is trained with bootstrapped noisy data to identify important relations for diagnosis, including may cause, may be caused by, and differential diagnosis. METHODS: Known relations were extracted from semistructured web pages and a relational database and were paired with sentences containing corresponding medical concepts to form training data. The sentence form was extended to allow one concept to be in the title. An attention mechanism was applied to reduce the effect of noisily labeled sentences. Section structure embedding was added to provide additional context for relation expressions. Graph information was further incorporated into the model to differentiate the target relations whose expressions were often similar and interwoven. RESULTS: The extended sentence form allowed 1.75 times as many relations and 2.17 times as many sentences to be found compared to the conventional form. The various components of the proposed model all added to the accuracy. Overall, the positive sample accuracy of the proposed model was 9 percentage points higher than baseline deep learning models and 13 percentage points higher than naïve Bayes and support vector machines. CONCLUSION: Our bootstrap data preparation method and the extended sentence form could form a large training dataset to enable algorithm development and data mining efforts. Section structure embedding and graph information significantly increased prediction accuracy.

Detection of heterozygous mutation in hook microtubule-tethering protein 1 in three patients with decapitated and decaudated spermatozoa syndrome.

BACKGROUND: The mechanism of intramanchette transport is crucial to the transformation of sperm tail and the nuclear condensation during spermiogenesis. Although few dysfunctional proteins could result in abnormal junction between the head and tail of spermatozoon, little is known about the genetic cues in this process. OBJECTIVE: Based on patients with severe decapitated and decaudated spermatozoa (DDS) syndrome, the study aimed to validate whether new mutation exists on their Hook microtubule-tethering protein 1 (HOOK1) genes and follow their results of assisted reproduction treatment (ART). METHODS: 7 severe teratozoospermia patients with DDS (proportion >95%) and three relative members in one pedigree were collected to sequence the whole genomic DNA. The fertilisation rates (FRs) of these patients were followed. Morphological observation and interspecies intracytoplasmic sperm injection (ICSI) assays were applied. RESULTS: A novel missense mutation of A to G (p.Q286R) in patients with DDS (n=3/7) was found in the HOOK1 gene, which was inherited from the mother in one patient. This variant was absent in 160 fertile population-matched control individuals. Morphological observation showed that almost all the DDS broke into decaudated heads and headless tails at the implantation fossa or the basal plate. The clinical studies indicated that the mutation might cause reduced FRs on both ART (FR=18.07%) and interspecies ICSI (FR=16.98%). CONCLUSIONS: An unreported mutation in HOOK1 gene was identified, which might be responsible to some patients with DDS. Further studies need to uncover the molecular mechanism of spermiogenesis for genomic therapy.

Porous honeycomb structures formed from interconnected MnO2 sheets on CNT-coated substrates for flexible all-solid-state supercapacitors.

The use of lightweight and easily-fabricated MnO2/carbon nanotube (CNT)-based flexible networks as binder-free electrodes and a polyvinyl alcohol/H2SO4 electrolyte for the formation of stretchable solid-state supercapacitors was examined. The active electrodes were fabricated from 3D honeycomb porous MnO2 assembled from cross-walled and interconnected sheet-architectural MnO2 on CNT-based plastic substrates (denoted as honeycomb MnO2/CNT textiles).These substrates were fabricated through a simple two-step procedure involving the coating of multi-walled carbon nanotubes (MWCNTs) onto commercial textiles by a dipping-drying process and subsequent electrodeposition of the interconnected MnO2 sheets onto the MWCNT-coated textile. With such unique MnO2 architectures integrated onto CNT flexible films, good performance was achieved with a specific capacitance of 324 F/g at 0.5 A/g. A maximum energy density of 7.2 Wh/kg and a power density as high as 3.3 kW/kg were exhibited by the honeycomb MnO2/CNT network device, which is comparable to the performance of other carbon-based and metal oxide/carbon-based solid-state supercapacitor devices. Specifically, the long-term cycling stability of this material is excellent, with almost no loss of its initial capacitance and good Coulombic efficiency of 82% after 5000 cycles. These impressive results identify these materials as a promising candidate for use in environmentally friendly, low-cost, and high-performance flexible energy-storage devices.

[Studies on preparative technology and quantitative determination for extracts of total saponin in roof of Panax japonicus].

OBJECTIVE: To explore the optimum extraction and purification condition of the total saponins in the root of Panax japonicus (RPJ), and establish its quality control methods. METHOD: Designed L16 (4(5)) orthogonal test with the extraction rate of total saponins as index, to determine the rational extraction process, and the techniques of water-saturated n-butanol extraction and acetone precipitation were applied to purify the alcohol extract of RPJ. Total saponins were detected by spectrophotometry and its triterpenoidal sapogenin oleanolic acid detected by HPLC. RESULT: The optimum conditions of total saponins from RPJ was as follows: the material was pulverized, dipped in 60% ethanol aqueous solution as extract solvent at 10 times of volume, and refluxed 3 times for 3 h each time. Extractant of water-saturated n-butanol with extraction times of 3 and precipitant of acetone with precipitation amount of 4-5 times were included in the purification process, which would obtain the quality products. The content of total saponins could reach to 83.48%, and oleanolic acid to 38.30%. CONCLUSION: The optimized preparative technology is stable, convenient and practical. The extract rate of RPJ was high and steady with this technology, which provided new evidence for industrializing production of the plant and developing new drug.