Predicting the efficiency of arsenic immobilization in soils by biochar using machine learning.

Arsenic (As) pollution in soils is a pervasive environmental issue. Biochar immobilization offers a promising solution for addressing soil As contamination. The efficiency of biochar in immobilizing As in soils primarily hinges on the characteristics of both the soil and the biochar. However, the influence of a specific property on As immobilization varies among different studies, and the development and application of arsenic passivation materials based on biochar often rely on empirical knowledge. To enhance immobilization efficiency and reduce labor and time costs, a machine learning (ML) model was employed to predict As immobilization efficiency before biochar application. In this study, we collected a dataset comprising 182 data points on As immobilization efficiency from 17 publications to construct three ML models. The results demonstrated that the random forest (RF) model outperformed gradient boost regression tree and support vector regression models in predictive performance. Relative importance analysis and partial dependence plots based on the RF model were conducted to identify the most crucial factors influencing As immobilization. These findings highlighted the significant roles of biochar application time and biochar pH in As immobilization efficiency in soils. Furthermore, the study revealed that Fe-modified biochar exhibited a substantial improvement in As immobilization. These insights can facilitate targeted biochar property design and optimization of biochar application conditions to enhance As immobilization efficiency.

Rapid detection of colored and colorless macro- and micro-plastics in complex environment via near-infrared spectroscopy and machine learning.

To better understand the migration behavior of plastic fragments in the environment, development of rapid non-destructive methods for in-situ identification and characterization of plastic fragments is necessary. However, most of the studies had focused only on colored plastic fragments, ignoring colorless plastic fragments and the effects of different environmental media (backgrounds), thus underestimating their abundance. To address this issue, the present study used near-infrared spectroscopy to compare the identification of colored and colorless plastic fragments based on partial least squares-discriminant analysis (PLS-DA), extreme gradient boost, support vector machine and random forest classifier. The effects of polymer color, type, thickness, and background on the plastic fragments classification were evaluated. PLS-DA presented the best and most stable outcome, with higher robustness and lower misclassification rate. All models frequently misinterpreted colorless plastic fragments and its background when the fragment thickness was less than 0.1mm. A two-stage modeling method, which first distinguishes the plastic types and then identifies colorless plastic fragments that had been misclassified as background, was proposed. The method presented an accuracy higher than 99% in different backgrounds. In summary, this study developed a novel method for rapid and synchronous identification of colored and colorless plastic fragments under complex environmental backgrounds.

Learning curve of robotic pancreatoduodenectomy by a single surgeon with extensive laparoscopic pancreatoduodenectomy experience.

With the development of robotic systems, robotic pancreatoduodenectomies (RPDs) have been increasingly performed. However, the number of cases required by surgeons with extensive laparoscopic pancreatoduodenectomy (LPD) experience to overcome the learning curve of RPD remains unclear. Therefore, we aimed to analyze and explore the impact of different phases of the learning curve of RPD on perioperative outcomes. Clinical data were prospectively collected and retrospectively analyzed for 100 consecutive patients who underwent RPD performed by a single surgeon. This surgeon had previous experience with LPD, having performed 127 LPDs with low morbidity. The learning curve for RPD was analyzed using the cumulative sum (CUSUM) method based on operation time, and perioperative outcomes were compared between the learning and proficiency phases. Between April 2020 and November 2022, one hundred patients (56 men, 44 women) were included in this study. Based on the CUSUM curve of operation time, the learning curve for RPD was divided into two phases: phase I was the learning phase (cases 1-33) and phase II was the proficiency phase (cases 34-100). The operation time during the proficiency phase was significantly shorter than that during the learning phase. In the learning phase of RPD, no significant increases were observed in estimated blood loss, conversion to laparotomy, severe complications, postoperative pancreatic hemorrhage, clinical pancreatic fistula, or other perioperative complications compared to the proficiency phases of either RPD or LPD. A surgeon with extensive prior experience in LPD can safely surmount the RPD learning curve without increasing morbidity in the learning phase. The proficiency was significantly improved after accumulating experience of 33 RPD cases.

A Machine Learning Approach to Identify C Type Lectin Domain (CTLD) Containing Proteins.

Lectins are sugar interacting proteins which bind specific glycans reversibly and have ubiquitous presence in all forms of life. They have diverse biological functions such as cell signaling, molecular recognition, etc. C-type lectins (CTL) are a group of proteins from the lectin family which have been studied extensively in animals and are reported to be involved in immune functions, carcinogenesis, cell signaling, etc. The carbohydrate recognition domain (CRD) in CTL has a highly variable protein sequence and proteins carrying this domain are also referred to as C-type lectin domain containing proteins (CTLD). Because of this low sequence homology, identification of CTLD from hypothetical proteins in the sequenced genomes using homology based programs has limitations. Machine learning (ML) tools use characteristic features to identify homologous sequences and it has been used to develop a tool for identification of CTLD. Initially 500 sequences of well annotated CTLD and 500 sequences of non CTLD were used in developing the machine learning model. The classifier program Linear SVC from sci kit library of python was used and characteristic features in CTLD sequences like dipeptide and tripeptide composition were used as training attributes in various classifiers. A precision, recall and multiple correlation coefficient (MCC) value of 0.92, 0.91 and 0.82 respectively were obtained when tested on external test set. On fine tuning of the parameters like kernel, C value, gamma, degree and increasing number of non CTLD sequences there was improvement in precision, recall and MCC and the corresponding values were 0.99, 0.99 and 0.96. New CTLD have also been identified in the hypothetical segment of human genome using the trained model. The tool is available on our local server for interested users.

Open-world electrocardiogram classification via domain knowledge-driven contrastive learning.

Automatic electrocardiogram (ECG) classification provides valuable auxiliary information for assisting disease diagnosis and has received much attention in research. The success of existing classification models relies on fitting the labeled samples for every ECG type. However, in practice, well-annotated ECG datasets usually cover only limited ECG types. It thus raises an issue: conventional classification models trained with limited ECG types can only identify those ECG types that have already been observed in the training set, but fail to recognize unseen (or unknown) ECG types that exist in the wild and are not included in training data. In this work, we investigate an important problem called open-world ECG classification that can predict fine-grained observed ECG classes and identify unseen classes. Accordingly, we propose a customized method that first incorporates clinical knowledge into contrastive learning by generating "hard negative" samples to guide learning diagnostic ECG features (i.e., distinguishable representations), and then performs multi-hypersphere learning to learn compact ECG representations for classification. The experiment results on 12-lead ECG datasets (CPSC2018, PTB-XL, and Georgia) demonstrate that the proposed method outperforms the state-of-the-art methods. Specifically, our method achieves superior accuracy than the comparative methods on the unseen ECG class and certain seen classes. Overall, the investigated problem (i.e., open-world ECG classification) helps to draw attention to the reliability of automatic ECG diagnosis, and the proposed method is proven effective in tackling the challenges. The code and datasets are released at https://github.com/betterzhou/Open_World_ECG_Classification.

Dual-stage feedback network for lightweight color image compression artifact reduction.

Lossy image coding techniques usually result in various undesirable compression artifacts. Recently, deep convolutional neural networks have seen encouraging advances in compression artifact reduction. However, most of them focus on the restoration of the luma channel without considering the chroma components. Besides, most deep convolutional neural networks are hard to deploy in practical applications because of their high model complexity. In this article, we propose a dual-stage feedback network (DSFN) for lightweight color image compression artifact reduction. Specifically, we propose a novel curriculum learning strategy to drive a DSFN to reduce color image compression artifacts in a luma-to-RGB manner. In the first stage, the DSFN is dedicated to reconstructing the luma channel, whose high-level features containing rich structural information are then rerouted to the second stage by a feedback connection to guide the RGB image restoration. Furthermore, we present a novel enhanced feedback block for efficient high-level feature extraction, in which an adaptive iterative self-refinement module is carefully designed to refine the low-level features progressively, and an enhanced separable convolution is advanced to exploit multiscale image information fully. Extensive experiments show the notable advantage of our DSFN over several state-of-the-art methods in both quantitative indices and visual effects with lower model complexity.

Optimistic sequential multi-agent reinforcement learning with motivational communication.

Centralized Training with Decentralized Execution (CTDE) is a prevalent paradigm in the field of fully cooperative Multi-Agent Reinforcement Learning (MARL). Existing algorithms often encounter two major problems: independent strategies tend to underestimate the potential value of actions, leading to the convergence on sub-optimal Nash Equilibria (NE); some communication paradigms introduce added complexity to the learning process, complicating the focus on the essential elements of the messages. To address these challenges, we propose a novel method called Optimistic Sequential Soft Actor Critic with Motivational Communication (OSSMC). The key idea of OSSMC is to utilize a greedy-driven approach to explore the potential value of individual policies, named optimistic Q-values, which serve as an upper bound for the Q-value of the current policy. We then integrate a sequential update mechanism with optimistic Q-value for agents, aiming to ensure monotonic improvement in the joint policy optimization process. Moreover, we establish motivational communication modules for each agent to disseminate motivational messages to promote cooperative behaviors. Finally, we employ a value regularization strategy from the Soft Actor Critic (SAC) method to maximize entropy and improve exploration capabilities. The performance of OSSMC was rigorously evaluated against a series of challenging benchmark sets. Empirical results demonstrate that OSSMC not only surpasses current baseline algorithms but also exhibits a more rapid convergence rate.

A two-stage importance-aware subgraph convolutional network based on multi-source sensors for cross-domain fault diagnosis.

Graph convolutional networks (GCNs) as the emerging neural networks have shown great success in Prognostics and Health Management because they can not only extract node features but can also mine relationship between nodes in the graph data. However, the most existing GCNs-based methods are still limited by graph quality, variable working conditions, and limited data, making them difficult to obtain remarkable performance. Therefore, it is proposed in this paper a two stage importance-aware subgraph convolutional network based on multi-source sensors named I2SGCN to address the above-mentioned limitations. In the real-world scenarios, it is found that the diagnostic performance of the most existing GCNs is commonly bounded by the graph quality because it is hard to get high quality through a single sensor. Therefore, we leveraged multi-source sensors to construct graphs that contain more fault-based information of mechanical equipment. Then, we discovered that unsupervised domain adaptation (UDA) methods only use single stage to achieve cross-domain fault diagnosis and ignore more refined feature extraction, which can make the representations contained in the features inadequate. Hence, it is proposed the two-stage fault diagnosis in the whole framework to achieve UDA. In the first stage, the multiple-instance learning is adopted to obtain the importance factor of each sensor towards preliminary fault diagnosis. In the second stage, it is proposed I2SGCN to achieve refined cross-domain fault diagnosis. Moreover, we observed that deficient and limited data may cause label bias and biased training, leading to reduced generalization capacity of the proposed method. Therefore, we constructed the feature-based graph and importance-based graph to jointly mine more effective relationship and then presented a subgraph learning strategy, which not only enriches sufficient and complementary features but also regularizes the training. Comprehensive experiments conducted on four case studies demonstrate the effectiveness and superiority of the proposed method for cross-domain fault diagnosis, which outperforms the state-of-the art methods.

A cross-temporal contrastive disentangled model for ancient Chinese understanding.

Ancient Chinese is a crucial bridge for understanding Chinese history and culture. Most existing works utilize high-resource modern Chinese to understand low-resource ancient Chinese, but they fail to fully consider the semantic and syntactic gaps between them due to their changes over time, resulting in the misunderstanding of ancient Chinese. Hence, we propose a novel language pre-training framework for ancient Chinese understanding based on the Cross-temporal Contrastive Disentanglement Model (CCDM), which bridges the gap between modern and ancient Chinese with their parallel corpus. Specifically, we first explore a cross-temporal data augmentation method by disentangling and reconstructing the parallel ancient-modern corpus. It is noteworthy that the proposed decoupling strategy takes full account of the cross-temporal character between ancient and modern Chinese. Then, cross-temporal contrastive learning is exploited to train the model by fully leveraging the cross-temporal information. Finally, the trained language model is utilized for downstream tasks. We conduct extensive experiments on six ancient Chinese understanding tasks. Results demonstrate that our model outperforms the state-of-the-art baselines. Our framework also holds potential applicability to other languages that have undergone evolutionary changes, leading to shifts in syntax and semantics.1.

What interprofessional education teaching and learning approaches are being implemented in baccalaureate health professional curricula in wound care education? A scoping review.

AIM: This scoping review aimed to explore the interprofessional curriculum content and teaching approaches specific to wound care education in baccalaureate health courses internationally. BACKGROUND: Interprofessional education is defined as occurring when future health practitioners learn with, from and about each other with the goal of improving health outcomes. The management of wounds is a global public health issue with the World Health Organization recognising wound care is best managed by an interprofessional team. The preparedness of health professional graduates to engage in interprofessional education is essential to design and deliver coordinated health services that are person-centred and improve health outcomes. There is a lack of evidence however about how to prepare baccalaureate students in an interprofessional context, specifically in wound care. DESIGN: A scoping review was conducted using the framework of Arksey and O'Malley and reported using the PRISMA checklist for scoping reviews. METHODS: A comprehensive search of the literature was conducted in MEDLINE (via EBSCOhost), CINAHL PLUS (via EBSCOhost), Pubmed and Embase databases published between 2012 and October 2023. Reference lists of included studies were also searched. Studies which were peer reviewed, written in English with a focus on interprofessional education in wound care were included in the review. The process of reviewing titles and abstracts was conducted by two independent reviewers. Data were extracted, key characteristics mapped and a narrative analysis of findings was reported. RESULTS: Three studies were included in this review. All the reviewed papers reported collaborative learning activities between different health professional groups relating to wound care, although there was no consistent approach to what wound care content was delivered or how it was delivered. Only one study reported that the delivery of content was completed by staff from multiple professional groups. Evaluation of the included studies related to either the effectiveness of the interprofessional education or wound care rather than both concepts. CONCLUSIONS: Due to the limited number of studies included in this review, it was difficult to draw conclusions about the effectiveness of interprofessional approaches to wound care. It may be possible that interprofessional wound care is currently being undertaken but not formally evaluated. This itself is problematic. It is imperative to equip healthcare students with the knowledge and skills necessary to provide safe, effective interprofessional care. Evidence on the effectiveness of educational programs is urgently needed. REGISTRATION NUMBER: to be included in abstract after acceptance.

RACGAP1 is a pivotal gene in lung adenocarcinoma-associated membranous nephropathy: Based on comprehensive bioinformatics analysis and machine learning.

BACKGROUND: This study performs a detailed bioinformatics and machine learning analysis to investigate the genetic foundations of membranous nephropathy (MN) in lung adenocarcinoma (LUAD). METHODS: In this study, the gene expression profiles of MN microarray datasets (GSE99339) and LUAD dataset (GSE43767) were downloaded from the Gene Expression Omnibus database, common differentially expressed genes (DEGs) were obtained using the limma R package. The biological functions were analyzed with R Cluster Profiler package according to Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses. Machine learning algorithms, including LASSO regression, support vector machine (SVM), Random Forest, and Boruta analysis, were applied to identify hubgenes linked to LUAD-associated MN. These genes' prognostic values were evaluated in the TCGA-LUAD cohort and validated through immunohistochemistry on renal biopsy specimens. RESULTS: A total of 36 DEGs in common were identified for downstream analyses. Functional enrichment analysis highlighted the involvement of the Toll-like receptor 4 pathway and several immune recognition pathways in LUAD-associated MN. COL3A1, PSENEN, RACGAP1, and TNFRSF10B were identified as hub genes in LUAD-associated MN using machine learning algorithms. ROC analysis demonstrated their effective discrimination of MN with high accuracy. Survival analysis showed that lung adenocarcinoma patients with higher expression of these genes had significantly reduced overall survival. In patients with lung adenocarcinoma-associated MN, RACGAP1, COL3A1, PSENEN, and TNFRSF10B were higher expressed in the glomerular, especially RACGAP1, indicating an important role in the pathogenesis of LUAD-associated membranous nephropathy. CONCLUSIONS: Our study underscores the critical role of RACGAP1, COL3A1, PSENEN, and TNFRSF10B in the development of LUAD-associated MN, providing important insights for future research and the development of potential therapeutic strategies.

Understanding benefits of a college student-homebound adult partnership program to support aging in place: An exploratory study.

The need for effective approaches to support aging and homebound adults is recognized internationally and domestically. This exploratory study sought to understand the proximal benefits of an intergenerational program in Delaware, USA that connected homebound individuals with college students. The primary goal was to describe program impacts on home-bound community residents to inform future research, program planning, and implementation. Outcomes of interest included quality of life, well-being, and independence. Semi-structured interviews were conducted with 19 participants recruited from a nonprofit partner. Findings yielded seven unique themes: emotional fulfillment, special feelings of support from a rare "unconditional" relationship, assistance with tasks, close connection with someone not ordinarily met, intergenerational understanding, someone to talk to, and appreciation. Additionally, the research team applied the RE-AIM (Reach, Effectiveness, Adoption, Implementation, Maintenance) framework, to contextualize the approach and findings. Results inform future evaluation efforts of homebound visiting programs, which may seek to incorporate outcome indicators aligned with these themes and serve as a foundation for future quantitative measures of impact.

Anomaly detection in the veterinary antibiotic prescription surveillance system (IS ABV).

Antibiotic resistance is one of the major concerns in veterinary and human medicine and poses a considerable threat to both human and animal health. It has been shown that over- or misuse of antibiotics is one of the primary drivers of antibiotic resistance. To develop the surveillance of antibiotic use, Switzerland introduced the "Informationssystem Antibiotika in der Veterinärmedizin" (IS ABV) in 2019, mandating electronic registration of antibiotic prescriptions by all veterinarians in Switzerland. However, initial data analysis revealed a considerable amount of implausible data entries, potentially compromising data quality and reliability. These anomalies may be caused by input errors, inaccuracies, incorrect or aberrant master data or data transmission and make analysis impossible. To address this issue efficiently, we propose a two-stage anomaly detection framework utilizing machine learning algorithms. In this study, our primary focus was on cattle treatments with either single or group therapy, as they were the species with the highest prescription volume. However, not all outliers are necessarily incorrect; some may be legitimate but unusual antibiotic treatments. Thus, expert review plays a crucial role in distinguishing outliers, that are correct from actual errors. Initially, relevant prescription variables were extracted and pre-processed with a custom-built scaler. A set of unsupervised algorithms calculated the probability of each data point and identified the most likely outliers. In collaboration with experts, we annotated anomalies and established anomaly thresholds for each production type and active substance. These expert-annotated labels were then used to fine-tune the final supervised classification algorithms. With this methodology, we identified 22,816 anomalies from a total of 1,994,170 prescriptions in cattle (1.1 %). Cattle with no further specified production type had the most (2 %) anomalies with 7758 out of 379,995. The anomalies were consistently identified and comprised prescriptions with too high and too low dosages. Random Forest achieved a ROC-AUC score of 0.994, (95 % CI: 0.992, 0.995) and a F1-Score of 0.962 (95 % CI: 0.958, 0.966) for single treatments. The versatility of this framework allows its adaptation to other species within IS ABV and potentially to other prescription-based surveillance systems. If applied regularly to uploaded prescriptions, it should reduce input errors over time, improving the validity of the data in the long term.

Learning disabilities in children with hearing loss: A systematic review.

PURPOSE: The main aim of this systematic review was to investigate the possible association between hearing loss [and/or history of otitis media with effusion (OME)] and learning difficulties in children. Secondary aims were to: (i) investigate if deaf and hard of hearing (DHH) children with learning difficulties might show different clinical and neuropsychological features compared with those with other neurodevelopmental disorders; (ii) identify possible predictors of learning difficulty in DHH children. METHODS: A review was conducted of the scientific literature reported by Pubmed, Cochrane and Scopus databases. The following inclusion criteria were used: (i) studies published after 2000; (ii) studies conducted considering subjects with age < 18 years; (iii) studies considering patients who showed both learning difficulties and hearing loss and/or episodes of OME; (iv) articles written in English. The exclusion criteria were: (i) presence in the studied cohort of any other proven comorbidities, other than hearing loss and/or OME; (ii) non-original studies. RESULTS: A total of 924 studies were identified. Four were reviewed after applying the above criteria. From their analysis it emerged that: (i) children with hearing loss who had undergone a diagnostic and rehabilitation program before 6 months of age had better levels of K readiness and language and literacy skills compared to those who had undergone it after 6 months; (ii) higher frequency of episodes of OME and the presence of a conductive hearing loss during the period of language acquisition was associated to lower scores in reading skills; (iii) reading difficulties found in subjects with hearing loss had similar characteristics to those with language difficulties. CONCLUSIONS: There is a dearth of information about this topic. Further investigations are therefore necessary on children of various ages with hearing loss to disclose learning difficulties in reading and writing abilities using current diagnostic tools.

Machine learning-aided unveiling the relationship between chemical pretreatment and methane production of lignocellulosic waste.

Chemical pretreatment is a common method to enhance the cumulative methane yield (CMY) of lignocellulosic waste (LW) but its effectiveness is subject to various factors, and accurate estimation of methane production of pretreated LW remains a challenge. Here, based on 254 LW samples, a machine learning (ML) model to predict the methane production performance of pretreated feedstock was constructed using two automated ML platforms (tree-based pipeline optimization tool and neural network intelligence). Furthermore, the interactive effects of pretreatment conditions, feedstock properties, and digestion conditions on methane production of pretreated LW were studied through model interpretability analysis. The optimal ML model performed well on the validation set, and the digestion time, pretreatment agent, and lignin content (LC) were found to be key factors affecting the methane production of pretreated LW. If the LC in the raw LW was lower than 15%, the maximum CMY might be achieved using the NaOH, KOH, and alkaline hydrogen peroxide (AHP) with concentrations of 3.8%, 4.4%, and 4.5%, respectively. On the other hand, if LC was higher than 15%, only high concentrations of AHP exceeding 4% could significantly increase methane production. This study provides valuable guidance for optimizing pretreatment process, comparing different chemical pretreatment approaches, and regulating the operation of large-scale biogas plants.

Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report.

Radiation therapy plays a crucial role in cancer treatment, necessitating precise delivery of radiation to tumors while sparing healthy tissues over multiple days. Computed tomography (CT) is integral for treatment planning, offering electron density data crucial for accurate dose calculations. However, accurately representing patient anatomy is challenging, especially in adaptive radiotherapy, where CT is not acquired daily. Magnetic resonance imaging (MRI) provides superior soft-tissue contrast. Still, it lacks electron density information, while cone beam CT (CBCT) lacks direct electron density calibration and is mainly used for patient positioning. Adopting MRI-only or CBCT-based adaptive radiotherapy eliminates the need for CT planning but presents challenges. Synthetic CT (sCT) generation techniques aim to address these challenges by using image synthesis to bridge the gap between MRI, CBCT, and CT. The SynthRAD2023 challenge was organized to compare synthetic CT generation methods using multi-center ground truth data from 1080 patients, divided into two tasks: (1) MRI-to-CT and (2) CBCT-to-CT. The evaluation included image similarity and dose-based metrics from proton and photon plans. The challenge attracted significant participation, with 617 registrations and 22/17 valid submissions for tasks 1/2. Top-performing teams achieved high structural similarity indices (≥0.87/0.90) and gamma pass rates for photon (≥98.1%/99.0%) and proton (≥97.3%/97.0%) plans. However, no significant correlation was found between image similarity metrics and dose accuracy, emphasizing the need for dose evaluation when assessing the clinical applicability of sCT. SynthRAD2023 facilitated the investigation and benchmarking of sCT generation techniques, providing insights for developing MRI-only and CBCT-based adaptive radiotherapy. It showcased the growing capacity of deep learning to produce high-quality sCT, reducing reliance on conventional CT for treatment planning.

Examining individual and contextual predictors of disability in Chinese older adults: A machine learning approach.

BACKGROUND: There is a large gap of understanding the determinants of disability, especially the contextual characteristics. Therefore, this study aimed to examine the important predictors of disability in Chinese older adults based on the social ecological framework. METHODS: We used the China Health and Retirement Longitudinal Study to examine predictors of disability, defined as self-report of any difficulty for six activity of daily living items. We restricted analytical sample to older adults aged 65 or above (N=1816). We considered 44 predictors, including personal-, behavioral-, interpersonal-, community-, and policy-level characteristics. The built-in variable importance measure (VIM) of random forest and SHapley Additive exPlanations (SHAP) were applied to assess key predictors of disability. A multilevel logit regression was further used to examine the associations of individual and contextual characteristics with disability. RESULTS: The mean age of study sample was 72.62 years old (standard deviation: 5.77). During a 2-year of follow-up, 518 (28.52 %) of them developed into disability. Walking speed, age, and peak expiratory flow were the top important predictors in both VIM and SHAP. Contextual characteristics such as humidity, PM2.5, temperature, normalized difference vegetation index, and landscape also showed promise in predicting disability. Multilevel logit regression showed that people with male gender, arthritis, vision impairment, unable to finish semi tandem, no social activity, lower grip strength, and higher waist circumference, had much higher risk of disability. CONCLUSION: Disability prevention strategies should specifically focus on multilevel factors such as individual and contextual characteristics, although the latter is warranted to be verified in future studies.

Fine-grained subphenotypes in acute kidney injury populations based on deep clustering: Derivation and interpretation.

BACKGROUND: Acute kidney injury (AKI) is associated with increased mortality in critically ill patients. Due to differences in the etiology and pathophysiological mechanism, the current AKI criteria put it an embarrassment to evaluate clinical therapy and prognosis. OBJECTIVE: We aimed to identify subphenotypes based on routinely collected clinical data to expose the unique pathophysiologic patterns. METHODS: A retrospective study was conducted based on the Medical Information Mart for Intensive Care IV (MIMIC-IV) and the eICU Collaborative Research Database (eICU-CRD), and a deep clustering approach was conducted to derive subphenotypes. We conducted further analysis to uncover the underlying clinical patterns and interpret the subphenotype derivation. RESULTS: We studied 14,189 and 19,382 patients with AKI within 48 h of ICU admission in the two datasets, respectively. Through our approach, we identified seven distinct AKI subphenotypes with mortality heterogeneity in each cohort. These subphenotypes displayed significant variations in demographics, comorbidities, levels of laboratory measurements, and survival patterns. Notably, the subphenotypes could not be effectively characterized using the Kidney Disease: Improving Global Outcomes (KDIGO) criteria alone. Therefore, we uncovered the unique underlying characteristics of each subphenotype through model-based interpretation. To assess the usability of the subphenotypes, we conducted an evaluation, which yielded a micro-Area Under the Receiver Operating Characteristic (AUROC) of 0.81 in the single-center cohort and 0.83 in the multi-center cohort within 48-hour of admission. CONCLUSION: We derived highly characteristic, interpretable, and usable AKI subphenotypes that exhibited superior prognostic values.

Using deep learning for predicting the dynamic evolution of breast cancer migration.

BACKGROUND: Breast cancer (BC) remains a prevalent health concern, with metastasis as the main driver of mortality. A detailed understanding of metastatic processes, particularly cell migration, is fundamental to improve therapeutic strategies. The wound healing assay, a traditional two-dimensional (2D) model, offers insights into cell migration but presents scalability issues due to data scarcity, arising from its manual and labor-intensive nature. METHOD: To overcome these limitations, this study introduces the Prediction Wound Progression Framework (PWPF), an innovative approach utilizing Deep Learning (DL) and artificial data generation. The PWPF comprises a DL model initially trained on artificial data that simulates wound healing in MCF-7 BC cell monolayers and spheres, which is subsequently fine-tuned on real-world data. RESULTS: Our results underscore the model's effectiveness in analyzing and predicting cell migration dynamics within the wound healing context, thus enhancing the usability of 2D models. The PWPF significantly contributes to a better understanding of cell migration processes in BC and expands the possibilities for research into wound healing mechanisms. CONCLUSIONS: These advancements in automated cell migration analysis hold the potential for more comprehensive and scalable studies in the future. Our dataset, models, and code are publicly available at https://github.com/frangam/wound-healing.

An unrolled neural network for accelerated dynamic MRI based on second-order half-quadratic splitting model.

The reconstruction of dynamic magnetic resonance images from incomplete k-space data has sparked significant research interest due to its potential to reduce scan time. However, traditional iterative optimization algorithms fail to faithfully reconstruct images at higher acceleration factors and incur long reconstruction time. Furthermore, end-to-end deep learning-based reconstruction algorithms suffer from large model parameters and lack robustness in the reconstruction results. Recently, unrolled deep learning models, have shown immense potential in algorithm stability and applicability flexibility. In this paper, we propose an unrolled deep learning network based on a second-order Half-Quadratic Splitting(HQS) algorithm, where the forward propagation process of this framework strictly follows the computational flow of the HQS algorithm. In particular, we propose a degradation-aware module by associating random sampling patterns with intermediate variables to guide the iterative process. We introduce the Information Fusion Transformer(IFT) to extract both local and non-local prior information from image sequences, thereby removing aliasing artifacts resulting from random undersampling. Finally, we impose low-rank constraints within the HQS algorithm to further enhance the reconstruction results. The experiments demonstrate that each component module of our proposed model contributes to the improvement of the reconstruction task. Our proposed method achieves comparably satisfying performance to the state-of-the-art methods and it exhibits excellent generalization capabilities across different sampling masks. At the low acceleration factor, there is a 0.7% enhancement in the PSNR. Furthermore, when the acceleration factor reached 8 and 12, the PSNR achieves an improvement of 3.4% and 5.8% respectively.