Cross-species transmission of Cryptosporidium in wild rodents from the southern region of Zhejiang Province of China and its possible impact on public health.

Wild rodents serve as reservoirs for Cryptosporidium and are overpopulated globally. However, genetic data regarding Cryptosporidium in these animals from China are limited. Here, we have determined the prevalence and genetic characteristics of Cryptosporidium among 370 wild rodents captured from three distinct locations in the southern region of Zhejiang Province, China. Fresh feces were collected from the rectum of each rodent, and DNA was extracted from them. The rodent species was identified by PCR amplifying the vertebrate cytochrome b gene. Cryptosporidium was detected by PCR amplification and amplicon sequencing the small subunit of ribosomal RNA gene. Positive samples of C. viatorum and C. parvum were further subtyped by analyzing the 60-kDa glycoprotein gene. A positive Cryptosporidium result was found in 7% (26/370) of samples, involving five rodent species: Apodemus agrarius (36), Niviventer niviventer (75), Rattus losea (18), R. norvegicus (155), and R. tanezumi (86). Their respective Cryptosporidium positive rates were 8.3%, 5.3%, 11.1%, 7.1%, and 7.0%. Sequence analysis confirmed the presence of three Cryptosporidium species: C. parvum (4), C. viatorum (1), and C. muris (1), and two genotypes: Cryptosporidium rat genotype IV (16) and C. mortiferum-like (4). Additionally, two subtypes of C. parvum (IIdA15G1 and IIpA19) and one subtype of C. viatorum (XVdA3) were detected. These results demonstrate that various wild rodent species in Zhejiang were concurrently infected with rodent-adapted and zoonotic species/genotypes of Cryptosporidium, indicating that these rodents can play a role in maintaining and dispersing this parasite into the environment and other hosts, including humans.

Title: Transmission interspécifique de Cryptosporidium chez les rongeurs sauvages de la région sud de la province chinoise du Zhejiang et son impact possible sur la santé publique. Abstract: Les rongeurs sauvages servent de réservoirs à Cryptosporidium et ont des grandes populations à l'échelle mondiale. Cependant, les données génétiques concernant Cryptosporidium chez ces animaux en Chine sont limitées. Ici, nous avons déterminé la prévalence et les caractéristiques génétiques de Cryptosporidium parmi 370 rongeurs sauvages capturés dans trois endroits distincts de la région sud de la province du Zhejiang, en Chine. Des excréments frais ont été collectés dans le rectum de chaque rongeur et l'ADN en a été extrait. L'espèce de rongeur a été identifiée par amplification par PCR du gène du cytochrome b des vertébrés. Cryptosporidium a été détecté par amplification PCR et séquençage d'amplicons de la petite sous-unité du gène de l'ARN ribosomal. Les échantillons positifs de C. viatorum et C. parvum ont ensuite été sous-typés en analysant le gène de la glycoprotéine de 60 kDa. Un résultat positif pour Cryptosporidium a été trouvé dans 7 % (26/370) des échantillons, impliquant cinq espèces de rongeurs : Apodemus agrarius (36), Niviventer niviventer (75), Rattus losea (18), R. norvegicus (155) et R. tanezumi (86). Leurs taux respectifs de positivité pour Cryptosporidium étaient de 8,3 %, 5,3 %, 11,1 %, 7,1 % et 7,0 %. L'analyse des séquences a confirmé la présence de trois espèces de Cryptosporidium : C. parvum (4), C. viatorum (1) et C. muris (1), et de deux génotypes : Cryptosporidium génotype IV de rat (16) et C. mortiferum-like (4). De plus, deux sous-types de C. parvum (IIdA15G1 et IIpA19) et un sous-type de C. viatorum (XVdA3) ont été détectés. Ces résultats démontrent que diverses espèces de rongeurs sauvages du Zhejiang sont simultanément infectées par des espèces/génotypes de Cryptosporidium zoonotiques et adaptés aux rongeurs, ce qui indique que ces rongeurs peuvent jouer un rôle dans le maintien et la dispersion de ce parasite dans l'environnement et d'autres hôtes, y compris les humains.

A vulnerability detection method for IoT protocol based on parallel fuzzy algorithm.

The Internet of Things communication protocol is prone to security vulnerabilities when facing increasing types and scales of network attacks, which can affect the communication security of the Internet of Things. It is crucial to effectively detect these vulnerabilities in order to improve the security of IoT communication protocols and promptly fix them. Therefore, this study proposes a distributed IoT communication protocol vulnerability detection method based on an improved parallelized fuzzy testing algorithm. Firstly, based on design principles and by comparing different communication protocols, a communication architecture for the distribution network's Internet of Things was constructed, and the communication protocols were formalized and decomposed. Next, preprocess the vulnerability detection samples, and then use genetic algorithm to improve the parallelized fuzzy testing algorithm to perform vulnerability detection. Through this improved algorithm, the missed detection rate and false detection rate can be effectively reduced, thereby improving the security of IoT communication protocols. The experimental results show that the highest missed detection rate of this method is only 4.0 %, and the false detection rate is low, with high detection efficiency. This indicates that the method has good performance and reliability in detecting vulnerabilities in IoT communication protocols.

Ensemble learning enhances the precision of preliminary detection of primary hepatocellular carcinoma based on serological and demographic indices.

Primary hepatocellular carcinoma (PHC) is associated with high rates of morbidity and malignancy in China and throughout the world. In clinical practice, a combination of ultrasound and alpha-fetoprotein (AFP) measurement is frequently employed for initial screening. However, the accuracy of this approach often falls short of the desired standard. Consequently, this study aimed to investigate the enhancement of precision of preliminary detection of PHC by ensemble learning techniques. To achieve this, 712 patients with PHC and 1887 healthy controls were enrolled for the assessment of four ensemble learning methods, namely, Random Forest (RF), LightGBM, Xgboost, and Catboost. A total of eleven characteristics, comprising nine serological indices and two demographic indices, were selected from the participants for use in detecting PHC. The findings identified an optimal feature subset consisting of eight features, namely AFP, albumin (ALB), alanine aminotransferase (ALT), platelets (PLT), age, alkaline phosphatase (ALP), hemoglobin (Hb), and body mass index (BMI), that achieved the highest classification accuracy of 96.62%. This emphasizes the importance of the collective use of these features in PHC diagnosis. In conclusion, the results provide evidence that the integration of serological and demographic indices together with ensemble learning models, can contribute to the precision of preliminary diagnosis of PHC.

A Comprehensive Review of Innovative Paradigms in Microbial Detection and Antimicrobial Resistance: Beyond Traditional Cultural Methods.

Microbial detection and antimicrobial resistance (AMR) surveillance are critical components of public health efforts to combat infectious diseases and preserve the efficacy of antimicrobial agents. While foundational in microbial identification, traditional cultural methods are often laborious, time-consuming, and limited in their ability to detect AMR markers. In response to these challenges, innovative paradigms have emerged, leveraging advances in molecular biology, genomics, proteomics, nanotechnology, and bioinformatics. This comprehensive review provides an overview of innovative approaches beyond traditional cultural methods for microbial detection and AMR surveillance. Molecular-based techniques such as polymerase chain reaction (PCR) and next-generation sequencing (NGS) offer enhanced sensitivity and specificity, enabling the rapid identification of microbial pathogens and AMR determinants. Mass spectrometry-based methods provide rapid and accurate detection of microbial biomarkers, including matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) and biosensor technologies. Nanotechnology approaches, such as nanoparticle-based assays and nanopore sequencing, offer novel platforms for sensitive and label-free detection of pathogens and AMR markers. Embracing these innovative paradigms holds immense promise for improving disease diagnosis, antibiotic stewardship, and AMR containment efforts. However, challenges such as cost, standardization, and integration with existing healthcare systems must be addressed to realize the full potential of these technologies. By fostering interdisciplinary collaboration and innovation, we can strengthen our ability to detect, monitor, and combat AMR, safeguarding public health for generations.

Testing an online screening for autism in the COVID-19 pandemic: a psychometric study of the Q-CHAT-24 in Chilean toddlers.

Background: The aim of this study was to examine some psychometric characteristics of the Chilean-adapted version of the Quantitative Checklist for Autism in Toddlers (Q-CHAT-24) (24) in a group of unselected children (community sample). This version was administered remotely through an online version during the pandemic period to caregivers of children, aged 18-24 months, registered in four primary care polyclinics of the Health Service Araucanía Sur, Chile. Methods: An intentional non-probabilistic sampling was used. Three hundred and thirteen toddlers were examined. Participants completed an online version of the Q-CHAT-24 which was disseminated through the REDCap platform. Evidence of reliability through internal consistency and evidence of predictive validity through ROC curve analysis were realized. Results: The mean age of the children evaluated was 21.16 months. The Shapiro-Wilk test revealed that Q-CHAT-24 scores was normally distributed. 71 cases (23.12%) scored 38 points or more on the Q-CHAT-24, qualifying as Autistic Risk. 48 cases (15.63%) were confirmed as autistic through the ADOS-2 Module T. All items were positively correlated with Q-CHAT-24 total score. All items were positively correlated with Q-CHAT-24 total score. Internal consistency was acceptable for the Q-CHAT-24 (Cronbach ´s α=0.78). The internal consistencies were analyzed for the Q-CHAT-24 Factors, and they were good for factor 1 "Communication and Social Interaction" (Cronbach ´s α=0.85) and acceptable for factor 2 "Restrictive and Repetitive Patterns" (Cronbach ´s α=0.74). Receiver operating characteristic (ROC) curve analyses were performed. The AUC values were 0.93 with statistical significance (p<0.01). For the cut-off point of 38, the Sensitivity, Specificity and Youden index values were 0.89, 0.8 and 0.7, respectively. The Positive Predictive Value (PPV) was 86% and the Negative Predictive Value (NPV) was 85%. Conclusions: In accordance with the objectives of this study, evidence of reliability and predictive validity was demonstrated for the Q-CHAT-24 in this Chilean population. More importantly, this study provides Sensitivity and Specificity data for a remote application version of an autism screening tool already validated in Chile. The implications of this have to do with the possibility of establishing a remote assessment system for children at risk of autism on a population scale.

Residual and bidirectional LSTM for epileptic seizure detection.

Electroencephalogram (EEG) plays a pivotal role in the detection and analysis of epileptic seizures, which affects over 70 million people in the world. Nonetheless, the visual interpretation of EEG signals for epilepsy detection is laborious and time-consuming. To tackle this open challenge, we introduce a straightforward yet efficient hybrid deep learning approach, named ResBiLSTM, for detecting epileptic seizures using EEG signals. Firstly, a one-dimensional residual neural network (ResNet) is tailored to adeptly extract the local spatial features of EEG signals. Subsequently, the acquired features are input into a bidirectional long short-term memory (BiLSTM) layer to model temporal dependencies. These output features are further processed through two fully connected layers to achieve the final epileptic seizure detection. The performance of ResBiLSTM is assessed on the epileptic seizure datasets provided by the University of Bonn and Temple University Hospital (TUH). The ResBiLSTM model achieves epileptic seizure detection accuracy rates of 98.88-100% in binary and ternary classifications on the Bonn dataset. Experimental outcomes for seizure recognition across seven epilepsy seizure types on the TUH seizure corpus (TUSZ) dataset indicate that the ResBiLSTM model attains a classification accuracy of 95.03% and a weighted F1 score of 95.03% with 10-fold cross-validation. These findings illustrate that ResBiLSTM outperforms several recent deep learning state-of-the-art approaches.

Winter wheat ear counting based on improved YOLOv7x and Kalman filter tracking algorithm with video streaming.

Accurate and real-time field wheat ear counting is of great significance for wheat yield prediction, genetic breeding and optimized planting management. In order to realize wheat ear detection and counting under the large-resolution Unmanned Aerial Vehicle (UAV) video, Space to depth (SPD) module was added to the deep learning model YOLOv7x. The Normalized Gaussian Wasserstein Distance (NWD) Loss function is designed to create a new detection model YOLOv7xSPD. The precision, recall, F1 score and AP of the model on the test set are 95.85%, 94.71%, 95.28%, and 94.99%, respectively. The AP value is 1.67% higher than that of YOLOv7x, and 10.41%, 39.32%, 2.96%, and 0.22% higher than that of Faster RCNN, SSD, YOLOv5s, and YOLOv7. YOLOv7xSPD is combined with the Kalman filter tracking and the Hungarian matching algorithm to establish a wheat ear counting model with the video flow, called YOLOv7xSPD Counter, which can realize real-time counting of wheat ears in the field. In the video with a resolution of 3840×2160, the detection frame rate of YOLOv7xSPD Counter is about 5.5FPS. The counting results are highly correlated with the ground truth number (R2 = 0.99), and can provide model basis for wheat yield prediction, genetic breeding and optimized planting management.

Mutual learning with memory for semi-supervised pest detection.

Effectively monitoring pest-infested areas by computer vision is essential in precision agriculture in order to minimize yield losses and create early scientific preventative solutions. However, the scale variation, complex background, and dense distribution of pests bring challenges to accurate detection when utilizing vision technology. Simultaneously, supervised learning-based object detection heavily depends on abundant labeled data, which poses practical difficulties. To overcome these obstacles, in this paper, we put forward innovative semi-supervised pest detection, PestTeacher. The framework effectively mitigates the issues of confirmation bias and instability among detection results across different iterations. To address the issue of leakage caused by the weak features of pests, we propose the Spatial-aware Multi-Resolution Feature Extraction (SMFE) module. Furthermore, we introduce a Region Proposal Network (RPN) module with a cascading architecture. This module is specifically designed to generate higher-quality anchors, which are crucial for accurate object detection. We evaluated the performance of our method on two datasets: the corn borer dataset and the Pest24 dataset. The corn borer dataset encompasses data from various corn growth cycles, while the Pest24 dataset is a large-scale, multi-pest image dataset consisting of 24 classes and 25k images. Experimental results demonstrate that the enhanced model achieves approximately 80% effectiveness with only 20% of the training set supervised in both the corn borer dataset and Pest24 dataset. Compared to the baseline model SoftTeacher, our model improves mAP @0.5 (mean Average Precision) at 7.3 compared to that of SoftTeacher at 4.6. This method offers theoretical research and technical references for automated pest identification and management.

Evaluation of dried blood spots for Epstein-Barr virus nucleic acid testing.

Epstein-Barr virus (EBV) is a ubiquitous and oncogenic virus that is associated with various malignancies and non-malignant diseases and EBV DNA detection is widely used for the diagnosis and prognosis prediction for these diseases. The dried blood spots (DBS) sampling method holds great potential as an alternative to venous blood samples in geographically remote areas, for individuals with disabilities, or for newborn blood collection. Therefore, the objective of this study was to assess the viability of detecting EBV DNA load from DBS. Matched whole blood and DBS samples were collected for EBV DNA extraction and quantification detection. EBV DNA detection in DBS presented a specificity of 100 %. At different EBV DNA viral load in whole blood, the sensitivity of EBV DNA detection in DBS was 38.78 % (≥1 copies/mL), 43.18 % (≥500 copies/mL), 58.63 % (≥1000 copies/mL), 71.43 % (≥2000 copies/mL), 82.35 % (≥4000 copies/mL), and 92.86 % (≥5000 copies/mL), respectively. These results indicated that the sensitivity of EBV DNA detection in DBS increased with elevating viral load. Moreover, there was good correlation between EBV DNA levels measured in whole blood and DBS, and on average, the viral load measured in whole blood was about 6-fold higher than in DBS. Our research firstly demonstrated the feasibility of using DBS for qualitative and semi-quantitative detection of EBV DNA for diagnosis and surveillance of EBV-related diseases.

Disparities in spatiotemporal clustering of maternal mental health conditions before and during the COVID-19 pandemic.

Mounting evidence indicates the worsening of maternal mental health conditions during the COVID-19 pandemic. Mental health conditions are the leading cause of preventable death during the perinatal and postpartum periods. Our study sought to detect space-time patterns in the distribution of maternal mental health conditions in pregnant women before (2016-2019) and during (2020-2021) the COVID-19 pandemic in North Carolina, USA. Using the space-time Poisson model in SaTScan, we performed univariate and multivariate cluster analysis of emergency department (ED) visits for perinatal mood and anxiety disorders (PMAD), severe mental illness (SMI), maternal mental disorders of pregnancy (MDP), suicidal thoughts, and suicide attempts during the pre-pandemic and pandemic periods. Clusters were adjusted for age, race, and insurance type. Significant multivariate and univariate PMAD, SMI, and MDP clustering persisted across both periods in North Carolina, while univariate clustering for both suicide outcomes decreased during the pandemic. Local relative risk (RR) for all conditions increased drastically in select locations. The number of zip code tabulation areas (ZCTAs) included in clusters decreased, while the proportion of urban locations included in clusters increased for non-suicide outcomes. Average yearly case counts for all maternal mental health outcomes increased during the pandemic. Results provide contextual and spatial information concerning at-risk maternal populations with a high burden of perinatal mental health disorders before and during the pandemic and emphasize the necessity of urgent and targeted expansion of mental health resources in select communities.

In situ construction of covalent-organic framework on hydrogen-bond organic framework: Fluorescence detection and removal of 4-nitrophenol and metamitron in aqueous media.

A multifunctional COF@HOF (ETTA-DFP@TCBP-HOF) composite is prepared by adding red-fluorescent ETTA-DFP COF to the blue-fluorescent TCBP-HOF preparation system through molecular hydrogen bonding or π - π stacking interactions in situ one-pot synthesis. ETTA-DFP@TCBP-HOF is a multifunctional material for the quantitative detection and simultaneous adsorption of 4-nitrophenol (4-NP) and metamitron (MET) in aqueous solution. As a dual-emission fluorescent sensor, the ETTA-DFP@TCBP-HOF has both fluorescence of TCBP-HOF at 474 nm and ETTA-DFP COF at 592 nm, which shows a ratiometric response to 4-NP and MET with high selectivity, good sensitivity, good anti-interference performance and fast response. As a adsorbent, ETTA-DFP@TCBP-HOF displays rapid adsorption kinetics, and acceptable adsorption capacity for 4-NP and MET. In conclusion, this work constructs a novel multifunctional hybrid material with dual-emission center of HOF and COF, which can not only be used as a ratiometric fluorescent probe for detection, but also for removal of hazardous pollutants, suggesting a new strategy for environmental remediation and human health.

Oleaginous fungi: a promising source of biofuels and nutraceuticals with enhanced lipid production strategies.

Oleaginous fungi have attracted a great deal of interest for their potency to accumulate high amounts of lipids (more than 20% of biomass dry weight) and polyunsaturated fatty acids (PUFAs), which have a variety of industrial and biological applications. Lipids of plant and animal origin are related to some restrictions and thus lead to attention towards oleaginous microorganisms as reliable substitute resources. Lipids are traditionally biosynthesized intra-cellularly and involved in the building structure of a variety of cellular compartments. In oleaginous fungi, under certain conditions of elevated carbon ratio and decreased nitrogen in the growth medium, a change in metabolic pathway occurred by switching the whole central carbon metabolism to fatty acid anabolism, which subsequently resulted in high lipid accumulation. The present review illustrates the bio-lipid structure, fatty acid classes and biosynthesis within oleaginous fungi with certain key enzymes, and the advantages of oleaginous fungi over other lipid bio-sources. Qualitative and quantitative techniques for detecting the lipid accumulation capability of oleaginous microbes including visual, and analytical (convenient and non-convenient) were debated. Factors affecting lipid production, and different approaches followed to enhance the lipid content in oleaginous yeasts and fungi, including optimization, utilization of cost-effective wastes, co-culturing, as well as metabolic and genetic engineering, were discussed. A better understanding of the oleaginous fungi regarding screening, detection, and maximization of lipid content using different strategies could help to discover new potent oleaginous isolates, exploit and recycle low-cost wastes, and improve the efficiency of bio-lipids cumulation with biotechnological significance.

First Report of Fruit Rot Disease on melon (Cucumis melo L.) Caused by Fusarium ipomoeae in China.

Fusarium rot on melon fruit has become an important postharvest disease for producers worldwide, typically involving multiple Fusarium pathogens (Khuna et al. 2022; Medeiros Araújo et al. 2021). In 2022, Fusarium fruit rot of muskmelon (Cucumis melo var. conomon) occurred sporadically in a field at Huainan Academy of Agricultural Sciences (32.658193º N, 117.064922º E) with an incidence of about 10%. Among these diseased muskmelons, a fruit exhibiting a white to yellowish colony athe intersection of the diseased and healthy tissues was collected and labeled TGGF22-17. The streak plate method was employed to isolate fungal spores on Bengal Red PDA (potato dextrose agar), which were then incubated at 25℃ in darkness. Following isolation and purification, a single-spore strain, TGGF22-17, was obtained and analyzed using morphological characters on PDA, synthetic nutrient agar (SNA) and carnation leaf agar (CLA) (Leslie and Summerell 2006), along with molecular identification. Colours were rated according to the color charts of Kornerup and Wanscher (1978). Based on the colony morphology on PDA, the isolate displayed a rosy buff or buff color with a white to buff margin. The colony margin was undulate, with the reverse transitioning from amber-yellow to honey-yellow. Aerial macroconidia on SNA were thin-walled, hyaline, mostly 3-5 septate, falcate, and measured 18.5-46.4 (x̄=34.2) × 2.9-4.8 (x̄ =3.9) µm in size (n =50). Sporodochial macroconidia on CLA were mostly five-septate with long apical and basal cells, exhibiting dorsiventral curvature. They were hyaline, with the apical cell hooked to tapering and the basal cell foot-shaped, measuring 46.5-89.6 (x̄ =72.3) × 3.5-5.0 (x̄ =4.3) µm in size (n = 100). Portions of three loci (TEF-1α, RPB1 and RPB2) were amplified and sequenced as described by Wang et al. (2019). Sequences were deposited in GenBank with accession number PP196583 to PP196585. The three gene sequences (TEF-1α, RPB1 and RPB2) of strain TGGF2022-17 shared 99.5% (629/632bp), 97.9% (1508/1540 bp) and 99.9% (1608/1609 bp) identity to the ex-type strain F. ipomoeae LC12165 respectively by pairwise DNA alignments on the FUSARIOID-ID database (https://www.fusarium.org). Phylogenetic analysis of the partial TEF-1α and RPB2 sequences with PhyloSuite (Zhang et al. 2020) showed the isolated fungus clustered with F. ipomoeae. Based on the morphological and phylogenetic analyses, TGGF22-17 was identified as F. ipomoeae. Pathogenicity tests were performed on healthy melons, which were surface-sterilized with 75% alcohol and wounded using a sterilized inoculation needle. A 4-mm diameter plug from a 7-day-old SNA culture of TGGF22-17 was aseptically inserted in the middle of the wound, sealed with plastic bag after absorbent cotton was included to maintain moisture. Five melons were each inoculated at three points. Noncolonized PDA agar plugs served as the negative control. The inoculated and uninoculated plugs were removed approximately 48 hours after inoculation. The melon inoculated with TGGF22-17 exhibited water-soaked black lesions 48h post-inoculation, resulting in a 100% infection rate (15/15). After 7 days, mycelium was obseved on the inoculated melons. No disease symptoms were observed on the uninoculated melons. To fulfill Koch's postulates, fungi were isolated from the inoculated fruit and confirmed as F. ipomoeae by morphological observation. Fusarium ipomoeae has been reported to cause fruit rot on winter squash (Cucurbita maxima) in Japan (Kitabayashi et al. 2023). To our knowledge, this is the first report of fruit rot on muskmelon caused by F. ipomoeae in China and this report will be valuable for monitoring and management of fruit rot disease on muskmelons.

Effects of Medicaid managed care on early detection of cancer: Evidence from mandatory Medicaid managed care program in Pennsylvania.

OBJECTIVE: To examine changes in late- versus early-stage diagnosis of cancer associated with the introduction of mandatory Medicaid managed care (MMC) in Pennsylvania. DATA SOURCES AND STUDY SETTING: We analyzed data from the Pennsylvania cancer registry (2010-2018) for adult Medicaid beneficiaries aged 21-64 newly diagnosed with a solid tumor. To ascertain Medicaid and managed care status around diagnosis, we linked the cancer registry to statewide hospital-based facility records collected by an independent state agency (Pennsylvania Health Care Cost Containment Council). STUDY DESIGN: We leveraged a natural experiment arising from county-level variation in mandatory MMC in Pennsylvania. Using a stacked difference-in-differences design, we compared changes in the probability of late-stage cancer diagnosis among those residing in counties that newly transitioned to mandatory managed care to contemporaneous changes among those in counties with mature MMC programs. DATA COLLECTION/EXTRACTION METHODS: N/A. PRINCIPAL FINDINGS: Mandatory MMC was associated with a reduced probability of late-stage cancer diagnosis (-3.9 percentage points; 95% CI: -7.2, -0.5; p = 0.02), particularly for screening-amenable cancers (-5.5 percentage points; 95% CI: -10.4, -0.6; p = 0.03). We found no significant changes in late-stage diagnosis among non-screening amenable cancers. CONCLUSIONS: In Pennsylvania, the implementation of mandatory MMC for adult Medicaid beneficiaries was associated with earlier stage of diagnosis among newly diagnosed cancer patients with Medicaid, especially those diagnosed with screening-amenable cancers. Considering that over half of the sample was diagnosed with late-stage cancer even after the transition to mandatory MMC, Medicaid programs and managed care organizations should continue to carefully monitor receipt of cancer screening and design strategies to reduce barriers to guideline-concordant screening or diagnostic procedures.

An Overview of the ADReSS-M Signal Processing Grand Challenge on Multilingual Alzheimer's Dementia Recognition Through Spontaneous Speech.

The ADReSS-M Signal Processing Grand Challenge was held at the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023. The challenge targeted difficult automatic prediction problems of great societal and medical relevance, namely, the detection of Alzheimer's Dementia (AD) and the estimation of cognitive test scoress. Participants were invited to create models for the assessment of cognitive function based on spontaneous speech data. Most of these models employed signal processing and machine learning methods. The ADReSS-M challenge was designed to assess the extent to which predictive models built based on speech in one language generalise to another language. The language data compiled and made available for ADReSS-M comprised English, for model training, and Greek, for model testing and validation. To the best of our knowledge no previous shared research task investigated acoustic features of the speech signal or linguistic characteristics in the context of multilingual AD detection. This paper describes the context of the ADReSS-M challenge, its data sets, its predictive tasks, the evaluation methodology we employed, our baseline models and results, and the top five submissions. The paper concludes with a summary discussion of the ADReSS-M results, and our critical assessment of the future outlook in this field.

Tri-Flow-YOLO: Counter helps to improve cross-domain object detection.

The excellence of intelligent detection models has been widely recognized, but in terms of cross-domain scenes, they still face performance degradation and low accuracy. A multi-supervised Tri-Flow-YOLO model is proposed to improve the accuracy of objects with various scales under cross-domain conditions. Based on the full-supervised traditional detection branch of YOLOv5, another two mutually supporting task branches are designed intently. In brief, we add unsupervised adversarial classification training flow to the backend, to realize the feature alignment requirements and improve the cross-domain performance stability of the model. Meanwhile, a weakly-supervised object counting flow is proposed to improve the model's attention to all the objects and the detection ability is efficiently enforced. In addition, I-Mosaic and iCIOU are designed especially for small hard objects, enriching the positive samples during the training process. With the auxiliary of both improved strategies, the imbalance of positive and negative samples in the anchor-based model is relieved accordingly. The experimental results show that the improved Tri-Flow-YOLO model achieves 56.0 mAP in the Cityscapes→Foggy-Cityscapes task, and 49.8 mAP in the VOC→Clipart task.

A comprehensive standardized dataset of numerous pomegranate fruit diseases for deep learning.

Pomegranate fruit disease detection and classification based on computer vision remains challenging because of various diseases, building the task of collecting or creating datasets is extremely difficult. The usage of machine learning and deep learning in farming has increased significantly in recent years. For developing precise and consistent machine learning models and reducing misclassification in real-time situations, efficient and clean datasets are a key obligation. The current pomegranate fruit diseases classification standardized and publicly accessible datasets for agriculture are not adequate to train the models efficiently. To address this issue, our primary goal of the current study is to create an image dataset of pomegranate fruits of numerous diseases that is ready to use and publicly available. We have composed 5 types of pomegranate fruit healthy and diseases from different places like Ballari, Bengaluru, Bagalakote, Etc. These images were taken from July to October 2023. The dataset contains 5099 pomegranate fruit images which are labeled and classified into 5 types: Healthy, Bacterial blight, Anthracnose, Cercospora fruit spot, and Alternaria fruit spot. The dataset comprises 5 folders entitled with corresponding diseases. This dataset might be useful for locating pomegranate diseases in other nations as well as increasing the production of pomegranate yield. This dataset is extremely useful for researchers of machine learning or deep learning in the field of agriculture for emerging computer vision applications.

Improving skin cancer detection by Raman spectroscopy using convolutional neural networks and data augmentation.

Background: Our previous studies have demonstrated that Raman spectroscopy could be used for skin cancer detection with good sensitivity and specificity. The objective of this study is to determine if skin cancer detection can be further improved by combining deep neural networks and Raman spectroscopy. Patients and methods: Raman spectra of 731 skin lesions were included in this study, containing 340 cancerous and precancerous lesions (melanoma, basal cell carcinoma, squamous cell carcinoma and actinic keratosis) and 391 benign lesions (melanocytic nevus and seborrheic keratosis). One-dimensional convolutional neural networks (1D-CNN) were developed for Raman spectral classification. The stratified samples were divided randomly into training (70%), validation (10%) and test set (20%), and were repeated 56 times using parallel computing. Different data augmentation strategies were implemented for the training dataset, including added random noise, spectral shift, spectral combination and artificially synthesized Raman spectra using one-dimensional generative adversarial networks (1D-GAN). The area under the receiver operating characteristic curve (ROC AUC) was used as a measure of the diagnostic performance. Conventional machine learning approaches, including partial least squares for discriminant analysis (PLS-DA), principal component and linear discriminant analysis (PC-LDA), support vector machine (SVM), and logistic regression (LR) were evaluated for comparison with the same data splitting scheme as the 1D-CNN. Results: The ROC AUC of the test dataset based on the original training spectra were 0.886±0.022 (1D-CNN), 0.870±0.028 (PLS-DA), 0.875±0.033 (PC-LDA), 0.864±0.027 (SVM), and 0.525±0.045 (LR), which were improved to 0.909±0.021 (1D-CNN), 0.899±0.022 (PLS-DA), 0.895±0.022 (PC-LDA), 0.901±0.020 (SVM), and 0.897±0.021 (LR) respectively after augmentation of the training dataset (p<0.0001, Wilcoxon test). Paired analyses of 1D-CNN with conventional machine learning approaches showed that 1D-CNN had a 1-3% improvement (p<0.001, Wilcoxon test). Conclusions: Data augmentation not only improved the performance of both deep neural networks and conventional machine learning techniques by 2-4%, but also improved the performance of the models on spectra with higher noise or spectral shifting. Convolutional neural networks slightly outperformed conventional machine learning approaches for skin cancer detection by Raman spectroscopy.

Newborn and infant hearing screening for early detection of hearing loss in Nairobi, Kenya.

Background: Early detection of hearing loss and subsequent intervention leads to better speech, language and educational outcomes giving way to improved social economic prospects in adult life. This can be achieved through establishing newborn and infant hearing screening programs. Objective: To determine the prevalence of hearing loss in newborns and infants in Nairobi, Kenya. Methods: A cross-sectional pilot study was conducted at the National hospital and at a sub county hospital immunization clinic. A total of 9,963 babies aged 0-3 years, were enrolled in the hearing screening program through convenient sampling over a period of nine months. A case history was administered followed by Distortion Product Oto-acoustic emissions (DPOAEs) and automated auditory brainstem response (AABR) hearing screening. Results: The screening coverage rate was 98.6% (9963/10,104). The referral rate for the initial screen was 3.6% (356/ 9,963), the return rate for follow-up rescreening was 72% (258 babies out of 356) with a lost to follow-up rate of 28% (98/356). The referral rate of the second screen was 10% (26/258). All the 26 babies referred from the second screen returned for diagnostic hearing evaluation and were confirmed with hearing loss, yielding a prevalence of 3/1000. Conclusions: Establishing universal newborn and infant hearing screening programs is essential for early detection and intervention for hearing loss. Data management and efficient follow-up systems are an integral part of achieving diagnostic confirmation of hearing loss and early intervention.

One or two things we know about concept drift-a survey on monitoring in evolving environments. Part A: detecting concept drift.

The world surrounding us is subject to constant change. These changes, frequently described as concept drift, influence many industrial and technical processes. As they can lead to malfunctions and other anomalous behavior, which may be safety-critical in many scenarios, detecting and analyzing concept drift is crucial. In this study, we provide a literature review focusing on concept drift in unsupervised data streams. While many surveys focus on supervised data streams, so far, there is no work reviewing the unsupervised setting. However, this setting is of particular relevance for monitoring and anomaly detection which are directly applicable to many tasks and challenges in engineering. This survey provides a taxonomy of existing work on unsupervised drift detection. In addition to providing a comprehensive literature review, it offers precise mathematical definitions of the considered problems and contains standardized experiments on parametric artificial datasets allowing for a direct comparison of different detection strategies. Thus, the suitability of different schemes can be analyzed systematically, and guidelines for their usage in real-world scenarios can be provided.