Impact of legal recognition on the lives of the third gender: A study in Khulna district of Bangladesh.

The third gender, popularly known as 'hijra', is a gender non-conforming person residing in Bangladesh. The government of Bangladesh granted legal recognition (LR) in 2013 to acknowledge them as a third gender. Thus, using an exploratory qualitative inquiry, the study sought to understand how LR affected the lives of the third gender community in the Khulna district of Bangladesh. Thirteen participants were selected following snowball sampling, and data were collected using in-depth interviews and key informant interviews. In the domain of socio-cultural dynamics, we found that the LR had enhanced the social participation of the third gender community and given them a sense of identity. On the contrary, within the domain of economic lives, the LR has not been able to change their economic situation. Moreover, in the third domain, we observed an improved situation for the third gender population in their right to vote and political participation, but in accessing healthcare facilities, inheritance, and legal services, LR remained unsatisfactory. The study recommends promoting acceptance and reducing social stigma towards the third gender community through awareness campaigns, providing professional training programs to enable their financial independence, and enacting laws to protect their rights in Bangladesh.

Optimizing echo state networks for continuous gesture recognition in mobile devices: A comparative study.

Continuous gesture recognition can be used to enhance human-computer interaction. This can be accomplished by capturing human movement with the use of the Inertial Measurement Units in smartphones and using machine learning algorithms to predict the intended gestures. Echo State Networks (ESNs) consist of a fixed internal reservoir that is able to generate rich and diverse nonlinear dynamics in response to input signals that capture temporal dependencies within the signal. This makes ESNs well-suited for time series prediction tasks, such as continuous gesture recognition. However, their application has not been rigorously explored, with regard to gesture recognition. In this study, we sought to enhance the efficacy of ESN models in continuous gesture recognition by exploring diverse model structures, fine-tuning hyperparameters, and experimenting with various training approaches. We used three different training schemes that used the Leave-one-out Cross-validation (LOOCV) protocol to investigate the performance in real-world scenarios with different levels of data availability: Leaving out data from one user to use for testing (F1-score: 0.89), leaving out a fraction of data from all users to use in testing (F1-score: 0.96), and training and testing using LOOCV on a single user (F1-score: 0.99). The obtained results outperformed the Long Short-Term Memory (LSTM) performance from past research (F1-score: 0.87) while maintaining a low training time of approximately 13 seconds compared to 63 seconds for the LSTM model. Additionally, we further explored the performance of the ESN models through behaviour space analysis using memory capacity, Kernel Rank, and Generalization Rank. Our results demonstrate that ESNs can be optimized to achieve high performance on gesture recognition in mobile devices on multiple levels of data availability. These findings highlight the practical ability of ESNs to enhance human-computer interaction.

Diagnosing and Discussing Sexual Abuse: A Scoping Review on Training Methods for Health Care Professionals.

Purpose: Sexual abuse is a health issue with many consequences. Recognizing and discussing past sexual abuse has proven to be challenging for health care professionals. To improve overall quality of health care for sexual abuse victims, health care professionals need to be properly trained. The aim of this paper is to provide an overview of training methods for health care professionals and to report on their effectiveness. Methods: A scoping review was conducted. A broad search was executed in six databases in December 2022. Study selection was performed by two independent reviewers, followed by quality assessment and data extraction. Results: After screening of titles and abstracts and later full-text assessment for quality appraisal, seven articles were selected, consisting mostly of non-randomized trials, performed among a total of 1299 health care professionals. All studies were assessed to be of moderate to poor quality. The participants attended training courses with a wide variety of durations, settings, formats and methods. The outcomes showed improvements in self-perceived or measured knowledge, skills and confidence to discuss sexual violence. Changes in clinical practice were scarcely investigated. Training courses were most effective when a mix of didactic passive methods, such as lectures and videos, and active participatory strategies, such as discussions and roleplay, were applied. Timely iteration to reinforce retention of gained knowledge and skills also contributed to effectiveness. Participants most enjoyed incorporating opportunities for receiving feedback in small settings and sharing personal experiences. Conclusion: This scoping review summarizes on how to effectively train health care professionals. Flaws and difficulties in measuring the effectiveness of training courses were discussed. Recognition and discussion of past sexual abuse by health care providers can be effectively trained using an alternating mix of multiple active and passive training methods with room for feedback and personal experiences.

Advancing maxillofacial prosthodontics by using pre-trained convolutional neural networks: Image-based classification of the maxilla.

PURPOSE: The study aimed to compare the performance of four pre-trained convolutional neural networks in recognizing seven distinct prosthodontic scenarios involving the maxilla, as a preliminary step in developing an artificial intelligence (AI)-powered prosthesis design system. MATERIALS AND METHODS: Seven distinct classes, including cleft palate, dentulous maxillectomy, edentulous maxillectomy, reconstructed maxillectomy, completely dentulous, partially edentulous, and completely edentulous, were considered for recognition. Utilizing transfer learning and fine-tuned hyperparameters, four AI models (VGG16, Inception-ResNet-V2, DenseNet-201, and Xception) were employed. The dataset, consisting of 3541 preprocessed intraoral occlusal images, was divided into training, validation, and test sets. Model performance metrics encompassed accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC), and confusion matrix. RESULTS: VGG16, Inception-ResNet-V2, DenseNet-201, and Xception demonstrated comparable performance, with maximum test accuracies of 0.92, 0.90, 0.94, and 0.95, respectively. Xception and DenseNet-201 slightly outperformed the other models, particularly compared with InceptionResNet-V2. Precision, recall, and F1 scores exceeded 90% for most classes in Xception and DenseNet-201 and the average AUC values for all models ranged between 0.98 and 1.00. CONCLUSIONS: While DenseNet-201 and Xception demonstrated superior performance, all models consistently achieved diagnostic accuracy exceeding 90%, highlighting their potential in dental image analysis. This AI application could help work assignments based on difficulty levels and enable the development of an automated diagnosis system at patient admission. It also facilitates prosthesis designing by integrating necessary prosthesis morphology, oral function, and treatment difficulty. Furthermore, it tackles dataset size challenges in model optimization, providing valuable insights for future research.

Identifying signs and symptoms of urinary tract infection from emergency department clinical notes using large language models.

BACKGROUND: Natural language processing (NLP) tools including recently developed large language models (LLMs) have myriad potential applications in medical care and research, including the efficient labeling and classification of unstructured text such as electronic health record (EHR) notes. This opens the door to large-scale projects that rely on variables that are not typically recorded in a structured form, such as patient signs and symptoms. OBJECTIVES: This study is designed to acquaint the emergency medicine research community with the foundational elements of NLP, highlighting essential terminology, annotation methodologies, and the intricacies involved in training and evaluating NLP models. Symptom characterization is critical to urinary tract infection (UTI) diagnosis, but identification of symptoms from the EHR has historically been challenging, limiting large-scale research, public health surveillance, and EHR-based clinical decision support. We therefore developed and compared two NLP models to identify UTI symptoms from unstructured emergency department (ED) notes. METHODS: The study population consisted of patients aged ≥ 18 who presented to an ED in a northeastern U.S. health system between June 2013 and August 2021 and had a urinalysis performed. We annotated a random subset of 1250 ED clinician notes from these visits for a list of 17 UTI symptoms. We then developed two task-specific LLMs to perform the task of named entity recognition: a convolutional neural network-based model (SpaCy) and a transformer-based model designed to process longer documents (Clinical Longformer). Models were trained on 1000 notes and tested on a holdout set of 250 notes. We compared model performance (precision, recall, F1 measure) at identifying the presence or absence of UTI symptoms at the note level. RESULTS: A total of 8135 entities were identified in 1250 notes; 83.6% of notes included at least one entity. Overall F1 measure for note-level symptom identification weighted by entity frequency was 0.84 for the SpaCy model and 0.88 for the Longformer model. F1 measure for identifying presence or absence of any UTI symptom in a clinical note was 0.96 (232/250 correctly classified) for the SpaCy model and 0.98 (240/250 correctly classified) for the Longformer model. CONCLUSIONS: The study demonstrated the utility of LLMs and transformer-based models in particular for extracting UTI symptoms from unstructured ED clinical notes; models were highly accurate for detecting the presence or absence of any UTI symptom on the note level, with variable performance for individual symptoms.

Multimodal semi-supervised learning for online recognition of multi-granularity surgical workflows.

Purpose Surgical workflow recognition is a challenging task that requires understanding multiple aspects of surgery, such as gestures, phases, and steps. However, most existing methods focus on single-task or single-modal models and rely on costly annotations for training. To address these limitations, we propose a novel semi-supervised learning approach that leverages multimodal data and self-supervision to create meaningful representations for various surgical tasks. Methods Our representation learning approach conducts two processes. In the first stage, time contrastive learning is used to learn spatiotemporal visual features from video data, without any labels. In the second stage, multimodal VAE fuses the visual features with kinematic data to obtain a shared representation, which is fed into recurrent neural networks for online recognition. Results Our method is evaluated on two datasets: JIGSAWS and MISAW. We confirmed that it achieved comparable or better performance in multi-granularity workflow recognition compared to fully supervised models specialized for each task. On the JIGSAWS Suturing dataset, we achieve a gesture recognition accuracy of 83.3%. In addition, our model is more efficient in annotation usage, as it can maintain high performance with only half of the labels. On the MISAW dataset, we achieve 84.0% AD-Accuracy in phase recognition and 56.8% AD-Accuracy in step recognition. Conclusion Our multimodal representation exhibits versatility across various surgical tasks and enhances annotation efficiency. This work has significant implications for real-time decision-making systems within the operating room.

A Data-Driven Approach to Estimate Human Center of Mass State During Perturbed Locomotion Using Simulated Wearable Sensors.

Center of mass (COM) state, specifically in a local reference frame (i.e., relative to center of pressure), is an important variable for controlling and quantifying bipedal locomotion. However, this metric is not easily attainable in real time during human locomotion experiments. This information could be valuable when controlling wearable robotic exoskeletons, specifically for stability augmentation where knowledge of COM state could enable step placement planners similar to bipedal robots. Here, we explored the ability of simulated wearable sensor-driven models to rapidly estimate COM state during steady state and perturbed walking, spanning delayed estimates (i.e., estimating past state) to anticipated estimates (i.e., estimating future state). We used various simulated inertial measurement unit (IMU) sensor configurations typically found on lower limb exoskeletons and a temporal convolutional network (TCN) model throughout this analysis. We found comparable COM estimation capabilities across hip, knee, and ankle exoskeleton sensor configurations, where device type did not significantly influence error. We also found that anticipating COM state during perturbations induced a significant increase in error proportional to anticipation time. Delaying COM state estimates significantly increased accuracy for velocity estimates but not position estimates. All tested conditions resulted in models with R2 > 0.85, with a majority resulting in R2 > 0.95, emphasizing the viability of this approach. Broadly, this preliminary work using simulated IMUs supports the efficacy of wearable sensor-driven deep learning approaches to provide real-time COM state estimates for lower limb exoskeleton control or other wearable sensor-based applications, such as mobile data collection or use in real-time biofeedback.

Reichsanzeiger-GT: An OCR ground truth dataset based on the historical newspaper "Deutscher Reichsanzeiger und Preußischer Staatsanzeiger" (German Imperial Gazette and Prussian Official Gazette) (1819-1945).

Reichsanzeiger-GT is a ground truth dataset for OCR training and evaluation based on the historical German newspaper "Deutscher Reichsanzeiger und Preußischer Staatsanzeiger" (German Imperial Gazette and Prussian Official Gazette), which was published from 1819 to 1945 and printed mostly in the typeface Fraktur (Black Letter). The dataset consists of 101 newspaper pages for the years 1820-1939, that cover a wide variety of topics, page layouts (lists, tables, and advertisements) as well as different typefaces. Using the transcription software Transkribus and the open-source OCR engine Tesseract we automatically created and manually corrected layout segmentations and transcriptions for each page, resulting in 65,563 text regions, 412 table regions, 119,429 text lines and 490,679 words. By applying transcription guidelines that preserve the printing conditions, the dataset contains language and printing specific phenomena like the historical use of glyphs like long s (s), rotunda r (ꝛ), and historical currency symbols (M, ₰) among others. The dataset is provided in two variants in PAGE XML format. The first one contains ground truth data with table regions transformed to text regions for easier processing. The second variant preserves all table regions. Researchers can reuse this dataset to train new or finetune existing text recognition or layout segmentation models. The dataset can also be used to evaluate the accuracy of existing OCR models. Using specific, community driven transcription guidelines our dataset is easily interoperable and reusable with other datasets based on the same transcription level.

Expanding the Hydrophobic Cavity Surface of Azocalix[4]arene to Enable Biotin/Avidin Affinity with Controlled Release.

The development of artificial receptors that combine ultrahigh-affinity binding and controllable release for active guests holds significant importance in biomedical applications. On one hand, a complex with an exceedingly high binding affinity can resist unwanted dissociation induced by dilution effect and complex interferents within physiological environments. On the other hand, stimulus-responsive release of the guest is essential for precisely activating its function. In this context, we expanded hydrophobic cavity surface of a hypoxia-responsive azocalix[4]arene, affording Naph-SAC4A. This modification significantly enhanced its aqueous binding affinity to 1013 M-1, akin to the naturally occurring strongest recognition pair, biotin/(strept-)avidin. Consequently, Naph-SAC4A emerges as the first artificial receptor to simultaneously integrate ultrahigh recognition affinity and actively controllable release. The markedly enhanced affinity not only improved Naph-SAC4A's sensitivity in detecting rocuronium bromide in serum, but also refined the precision of hypoxia-responsive doxorubicin delivery at the cellular level, demonstrating its immense potential for diverse practical applications.

Olfactory self-recognition in two species of snake.

Mark tests, in which an animal uses a mirror to locate and examine an otherwise unnoticeable mark on its own body, are commonly used to assess self-recognition, which may have implications for self-awareness. Recently, several olfactory-reliant species have appeared to pass odour-based versions of the mark test, though it has never been attempted in reptiles. We conducted an odour-based mark test on two species of snakes, Eastern gartersnakes and ball pythons, with widely divergent ecologies (i.e. terrestrial foragers that communally brumate versus semi-arboreal ambush predators that do not). We find that gartersnakes, but not ball pythons, pass the test, and a range of control tests suggest this is based on self-recognition. Gartersnakes are more social than ball pythons, supporting recent suggestions that social species are more likely to self-recognize. These results open the door to examination of the ecology of self-recognition, and suggest that this ability may evolve in response to species-specific ecological challenges, some of which may align with complexity of social structures.

BioBBC: a multi-feature model that enhances the detection of biomedical entities.

The rapid increase in biomedical publications necessitates efficient systems to automatically handle Biomedical Named Entity Recognition (BioNER) tasks in unstructured text. However, accurately detecting biomedical entities is quite challenging due to the complexity of their names and the frequent use of abbreviations. In this paper, we propose BioBBC, a deep learning (DL) model that utilizes multi-feature embeddings and is constructed based on the BERT-BiLSTM-CRF to address the BioNER task. BioBBC consists of three main layers; an embedding layer, a Long Short-Term Memory (Bi-LSTM) layer, and a Conditional Random Fields (CRF) layer. BioBBC takes sentences from the biomedical domain as input and identifies the biomedical entities mentioned within the text. The embedding layer generates enriched contextual representation vectors of the input by learning the text through four types of embeddings: part-of-speech tags (POS tags) embedding, char-level embedding, BERT embedding, and data-specific embedding. The BiLSTM layer produces additional syntactic and semantic feature representations. Finally, the CRF layer identifies the best possible tag sequence for the input sentence. Our model is well-constructed and well-optimized for detecting different types of biomedical entities. Based on experimental results, our model outperformed state-of-the-art (SOTA) models with significant improvements based on six benchmark BioNER datasets.

Preparation of amino acid chiral ionic liquid and visual chiral recognition of glutamine and phenylalanine enantiomers.

In this paper, the amino acid chiral ionic liquid (AACIL) was prepared with L-phenylalanine and imidazole. It was characterized by CD, FT-IR, 1H NMR, and 13C NMR spectrum. The chiral recognition sensor was constructed with AACIL and Cu(II), which exhibited different chiral visual responses (solubility or color difference) to the enantiomers of glutamine (Gln) and phenylalanine (Phe). The effects of solvent, pH, time, temperature, metal ions, and other amino acids on visual chiral recognition were optimized. The minimum concentrations of Gln and Phe for visual chiral recognition were 0.20 mg/ml and 0.28 mg/ml, respectively. The mechanism of chiral recognition was investigated by FT-IR, TEM, SEM, TG, XPS, and CD. The location of the host-guest inclusion or molecular placement has been conformationally searched based on Gaussian 09 software.

Electrophysiological analysis of signal detection outcomes emphasizes the role of decisional factors in recognition memory.

Introduction: Event-related potential (ERP) studies have identified two time windows associated with recognition memory and interpreted them as reflecting two processes: familiarity and recollection. However, using relatively simple stimuli and achieving high recognition rates, most studies focused on hits and correct rejections. This leaves out some information (misses and false alarms) that according to Signal Detection Theory (SDT) is necessary to understand signal processing. Methods: We used a difficult visual recognition task with colored pictures of different categories to obtain enough of the four possible SDT outcomes and analyzed them with modern ERP methods. Results: Non-parametric analysis of these outcomes identified a single time window (470 to 670 ms) which reflected activity within fronto-central and posterior-left clusters of electrodes, indicating differential processing. The posterior-left cluster significantly distinguished all STD outcomes. The fronto-central cluster only distinguished ERPs according to the subject's response: yes vs. no. Additionally, only electrophysiological activity within the posterior-left cluster correlated with the discrimination index (d'). Discussion: We show that when all SDT outcomes are examined, ERPs of recognition memory reflect a single-time window that may reveal a bottom-up factor discriminating the history of items (i.e. memory strength), as well as a top-down factor indicating participants' decision.

Optimization of forensic identification through 3-dimensional imaging analysis of labial tooth surface using open-source software.

Purpose: The objective of this study was to determine the minimum number of teeth in the anterior dental arch that would yield accurate results for individual identification in forensic contexts. Materials and Methods: The study involved the analysis of 28 sets of 3-dimensional (3D) point cloud data, focused on the labial surface of the anterior teeth. These datasets were superimposed within each group in both genuine and imposter pairs. Group A incorporated data from the right to the left central incisor, group B from the right to the left lateral incisor, and group C from the right to the left canine. A comprehensive analysis was conducted, including the evaluation of root mean square error (RMSE) values and the distances resulting from the superimposition of dental arch segments. All analyses were conducted using CloudCompare version 2.12.4 (Telecom ParisTech and R&D, Kyiv, Ukraine). Results: The distances between genuine pairs in groups A, B, and C displayed an average range of 0.153 to 0.184 mm. In contrast, distances for imposter pairs ranged from 0.338 to 0.522 mm. RMSE values for genuine pairs showed an average range of 0.166 to 0.177, whereas those for imposter pairs ranged from 0.424 to 0.638. A statistically significant difference was observed between the distances of genuine and imposter pairs (P<0.05). Conclusion: The exceptional performance observed for the labial surfaces of anterior teeth underscores their potential as a dependable criterion for accurate 3D dental identification. This was achieved by assessing a minimum of 4 teeth.

Implementing machine learning techniques for continuous emotion prediction from uniformly segmented voice recordings.

Introduction: Emotional recognition from audio recordings is a rapidly advancing field, with significant implications for artificial intelligence and human-computer interaction. This study introduces a novel method for detecting emotions from short, 1.5 s audio samples, aiming to improve accuracy and efficiency in emotion recognition technologies. Methods: We utilized 1,510 unique audio samples from two databases in German and English to train our models. We extracted various features for emotion prediction, employing Deep Neural Networks (DNN) for general feature analysis, Convolutional Neural Networks (CNN) for spectrogram analysis, and a hybrid model combining both approaches (C-DNN). The study addressed challenges associated with dataset heterogeneity, language differences, and the complexities of audio sample trimming. Results: Our models demonstrated accuracy significantly surpassing random guessing, aligning closely with human evaluative benchmarks. This indicates the effectiveness of our approach in recognizing emotional states from brief audio clips. Discussion: Despite the challenges of integrating diverse datasets and managing short audio samples, our findings suggest considerable potential for this methodology in real-time emotion detection from continuous speech. This could contribute to improving the emotional intelligence of AI and its applications in various areas.

Examining the effects of pleasantness ratings on correct and false recognition in the DRM paradigm: accuracy, recollection and familiarity estimates.

Distinctive encoding usually increases correct recognition while also producing a reduction in false recognition. In the Deese-Roediger-McDermott (DRM) illusion this phenomenon, called the mirror effect, occurs when participants focus on unique features of each of the words in the study list. In previous studies, the pleasantness rating task, used to foster distinctive encoding, generated different patterns of results. The main aim of our research is to examine under what circumstances this task can produce the mirror effect in the DRM paradigm, based on evidence from recognition accuracy and subjective retrieval experience. In Experiment 1, a standard version (word pleasantness rating on a 5-point Likert-type scale) was used for comparison with two other encoding conditions: shallow processing (vowel identification) and a read-only control. The standard task, compared to the other conditions, increased correct recognition, but did not reduce false recognition, and this result may be affected by the number of lists presented for study. Therefore, in experiment 2, to minimize the possible effect of the so-called retention size, the number of studied lists was reduced. In addition, the standard version was compared with a supposedly more item-specific version (participants rated the pleasantness of words while thinking of a single reason for this), also including the read-only control condition. In both versions of the pleasantness rating task, more correct recognition is achieved compared to the control condition, with no differences between the two versions. In the false recognition observed here, only the specific pleasantness rating task achieved a reduction relative to the control condition. On the other hand, the subjective retrieval experience accompanied correct and false recognition in the various study conditions. Although the standard pleasantness rating task has been considered to perform item-specific processing, our results challenge that claim. Furthermore, we propose a possible boundary condition of the standard task for the reduction of false recognition in the DRM paradigm.

Automated recognition of chromosome fusion using an alignment-free natural vector method.

Chromosomal fusion is a significant form of structural variation, but research into algorithms for its identification has been limited. Most existing methods rely on synteny analysis, which necessitates manual annotations and always involves inefficient sequence alignments. In this paper, we present a novel alignment-free algorithm for chromosomal fusion recognition. Our method transforms the problem into a series of assignment problems using natural vectors and efficiently solves them with the Kuhn-Munkres algorithm. When applied to the human/gorilla and swamp buffalo/river buffalo datasets, our algorithm successfully and efficiently identifies chromosomal fusion events. Notably, our approach offers several advantages, including higher processing speeds by eliminating time-consuming alignments and removing the need for manual annotations. By an alignment-free perspective, our algorithm initially considers entire chromosomes instead of fragments to identify chromosomal structural variations, offering substantial potential to advance research in this field.

Highly selective and sensitive immunoassays for flurogestone acetate analysis in goat milk: From rational hapten design and antibody production to assay development.

The preparation of high specificity and affinity antibodies is challenging due to limited information on characteristic groups of haptens in traditional design strategy. In this study, we first predicted characteristic groups of flurogestone acetate (FGA) using quantitative analysis of molecular surface combined with atomic charge distribution. Subsequently, FGA haptens were rationally designed to expose these identified characteristic groups fully. As a result, seven monoclonal antibodies were obtained with satisfactory performance, exhibiting IC50 values from 0.17 to 0.45 µg/L and negligible cross-reactivities below 1% to other 18 hormones. The antibody recognition mechanism further confirmed hydrogen bonds and hydrophobic interactions involving predicted FGA characteristic groups and specific amino acids in the antibodies contributed to their high specificity and affinity. Finally, one selective and sensitive ic-ELISA was developed for FGA determination with a detection limit as low as 0.12 µg/L, providing an efficient tool for timely monitoring of FGA in goat milk samples.

Astaxanthin and DHA Supplementation Modulates the Maternal Undernutrition-induced Impairment of Cognitive Behavior and Synaptic Plasticity in Adult Life of Offspring's -Exploring the Molecular Mechanism.

Maternal nutrition was recognized as a significant part of brain growth and maturation in most mammalian species. Timely intervention with suitable nutraceuticals would provide long-term health benefits. We aim to unravel the molecular mechanisms of perinatal undernutrition-induced impairments in cognition and synaptic plasticity, employing animal model based on dietary nutraceutical supplementation. We treated undernourished dams at their gestational, lactational, and at both the time point with Astaxanthin (AsX) and Docosahexaenoic acid (DHA), and their pups were used as experimental animals. We evaluated the cognitive function by subjecting the pups to behavioral tests in their adult life. In addition, we assessed the expression of genes in the hippocampus related to cognitive function and synaptic plasticity. Our results showed downregulation of Brain-derived neurotrophic factor (BDNF), Neurotrophin-3 (NT-3), cAMP response-element-binding protein (CREB), and uncoupling protein-2 (UCP2) gene expression in pups born to undernourished dams in their adult life, which AsX and DHA modulated. Maternal AsX and DHA supplementation ameliorated the undernutrition-induced learning impairment in novel object recognition (NOR) tests and partially baited radial arm maze (RAM) tasks in offspring's. The expressions of Synapsin-1 and PSD-95 decreased in perinatally undernourished groups compared to control and AsX-DHA treated groups at CA1, CA2, CA3, and DG. AsX and DHA supplementation upregulated BDNF, NT-3, CREB, and UCP2 gene expressions in perinatally undernourished rats, which are involved in intracellular signaling cascades like Ras, PI3K, and PLC. The results of our study give new insights into neuronal differentiation, survival, and plasticity, indicating that the perinatal period is the critical time for reversing maternal undernutrition-induced cognitive impairment in offspring's.

Artificial intelligence for disease diagnostics still has a long way to go.

Artificial intelligence (AI) can sometimes resolve difficulties that other advanced technologies and humans cannot. In medical diagnostics, AI has the advantage of processing figure recognition, especially for images with similar characteristics that are difficult to distinguish with the naked eye. However, the mechanisms of this advanced technique should be well-addressed to elucidate clinical issues. In this letter, regarding an original study presented by Takayama et al, we suggest that the authors should effectively illustrate the mechanism and detailed procedure that artificial intelligence techniques processing the acquired images, including the recognition of non-obvious difference between the normal parts and pathological ones, which were impossible to be distinguished by naked eyes, such as the basic constitutional elements of pixels and grayscale, special molecules or even some metal ions which involved into the diseases occurrence.