Efectividad de la intervención motora temprana en el desarrollo motor de los niños con parálisis cerebral entre 3 y 5 años de edad. Revisión sistemática / Effectiveness of early motor interventions in children with cerebral palsy between 3 to 5 years of age: Systematic review

La intervención motora temprana es esencial en niños con parálisis cerebral; sin embargo, se desconoce su efectividad entre los 3 y los 5años. El objetivo fue determinar la efectividad de la intervención motora temprana en el desarrollo motor de dicha población. Se realizó una revisión sistemática de literatura acerca de intervenciones motoras tempranas realizada en diferentes bases de datos como Pubmed/Medline, PEDro, OTSeeker, Embase y LILACS. Finalmente se seleccionaron 18 artículos, de los cuales 4 presentaron cambios a favor del grupo experimental en los desenlaces desarrollo motor global y función motora manual, con la terapia de integración sensorial y la terapia de movimiento inducido por restricción, respectivamente; no obstante, los resultados no fueron estadísticamente significativos y el nivel de evidencia fue bajo. La intervención motora temprana podría incluirse con precaución para la mejoría del desarrollo motor global y la función manual. Es necesario realizar estudios de mayor calidad metodológica. (AU)

Early motor intervention is essential in children with cerebral palsy; however, it is unknown its effectiveness between 3 to 5years. The objective was to determinate the effectiveness of early motor intervention in the motor development of this population. A systematic literature search was performed in Pubmed/Medline, PEDro, OTSeeker, Embase, and LILACS. Finally, 18 articles were selected, of which 4 showed favorable changes in the experimental group in the outcomes of overall motor development and manual motor function, with sensory integration therapy and movement-induced restriction therapy, respectively; however, the results were not statistically significant, and the level of evidence was low. Early motor intervention could be cautiously considered for improving overall motor development and manual function. Higher-quality methodological studies are necessary. (AU)

Using the WHO individual near miss case review (NMCR) cycle to improve quality of emergency obstetric care and maternal outcome in Keren hospital, Eritrea: an interrupted time series analysis.

BACKGROUND: In 2016, the WHO regional office for Europe prepared a manual for conducting routine facility based individual near miss case review cycle. This study evaluates the effectiveness of the individual near miss case review (NMCR) cycle in improving quality of emergency obstetric care and maternal outcome in Keren hospital. METHODS: An interrupted time series design was used to achieve the objectives of this study. Monthly data on women with potentially life-threatening conditions (PLTCs) admitted between April 2018 and October 2022 (i.e. 33 months pre-implementation and 22 months post-implementation) were collected from medical records. Segmented regression analysis was used to assess the intervention's effect on three process and outcome measures, namely, SMO, delayed care, and substandard care. The intervention was expected a priori to show immediate improvements without time-lag followed by gradual increment in slope. Segmented regression analyses were performed using the "itsa' command in STATA. RESULTS: During the entire study period, 4365 women with potentially life threatening conditions were identified. There was a significant reduction in the post-implementation period in the proportion of mothers with PLTC who experienced SMO (- 8.86; p <  0.001), delayed care (- 8.76; p <  0.001) and substandard care (- 5.58; p <  0.001) compared to pre-implementation period. Results from the segmented regression analysis revealed that the percentage of women with SMO showed a significant 4.75% (95% CI: - 6.95 to - 2.54, p <  0.001) reduction in level followed by 0.28 percentage points monthly (95% CI: - 0.37 to - 0.14, p <  0.001) drop in trend. Similarly, a significant drop of 3.50% (95% CI: - 4.74 to - 2.26, p <  0.001) in the level of substandard care along with a significant decrease of 0.21 percentage points (95% CI: - 0.28 to - 0.14, p < 0.001) in the slope of the regression line was observed. The proportion of women who received delayed care also showed a significant 7% (95% CI: - 9.28 to - 4.68, p < 0.001) reduction in post-implementation level without significant change in slope. CONCLUSIONS: Our findings suggest that the WHO individual NMCR cycle was associated with substantial improvements in quality of emergency obstetric care and maternal outcome. The intervention also bears a great potential for scaling-up following the guidance provided in the WHO NMCR manual.

Palliative care needs of people and/or their families with serious and/or chronic health conditions in low- or middle-income country (LMIC) humanitarian settings-a systematic scoping review protocol.

BACKGROUND: Palliative care in low- or middle-income country (LMIC) humanitarian settings is a new area, experiencing a degree of increased momentum over recent years. The review contributes to this growing body of knowledge, in addition to identifying gaps for future research. The overall aim is to systematically explore the evidence on palliative care needs of patients and/or their families in LMIC humanitarian settings. METHODS: Arksey and O'Malley's (Int J Soc Res Methodol. 8:19-32, 2005) scoping review framework forms the basis of the study design, following further guidance from Levac et al. (Implement Sci 5:1-9, 2010), the Joanna Briggs Institute (JBI) Peters et al. (JBI Reviewer's Manual JBI: 406-452, 2020), and the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) from Tricco et al. (Ann Intern Med 169:467-73, 2018). This incorporates a five-step approach and the population, concept, and context (PCC) framework. Using already identified key words/terms, searches for both published research and gray literature from January 2012 to October 2022 will be undertaken using databases (likely to include Cumulative Index of Nursing and Allied Health (CINAHL), MEDLINE, Embase, Global Health, Scopus, Applied Social Science Index and Abstracts (ASSIA), Web of Science, Policy Commons, JSTOR, Library Network International Monetary Fund and World Bank, Google Advanced Search, and Google Scholar) in addition to selected pre-print sites and websites. Data selection will be undertaken based on the inclusion and exclusion criteria and will be reviewed at each stage by two reviewers, with a third to resolve any differences. Extracted data will be charted in a table. Ethical approval is not required for this review. DISCUSSION: Findings will be presented in tables and diagrams/charts, followed by a narrative description. The review will run from late October 2022 to early 2023. This is the first systematic scoping review specifically exploring the palliative care needs of patients and/or their family, in LMIC humanitarian settings. The paper from the review findings will be submitted for publication in 2023.

[Research practice and development direction of intelligent manufacturing of presonalized traditional Chinese medicine preparations].

In recent years, as people's living standards continue to improve, and the pace of life accelerates dramatically, the demand and quality of traditional Chinese medicine(TCM) services from patients continue to rise. As an essential supplement to the existing forms of TCM application, such as Chinese patent medicine, decoction, and formulated granules, presonalized TCM preparations is facing an increasing market demand. Currently, manual and semi-mechanized production are the primary production ways in presonalized TCM preparations. However, the production process control level is low, and digitalization and informatization need to be improved, which restricts the automated and intelligent development of presonalized TCM preparations. Presonalized TCM preparations faces a significant opportunity and challenge in integrating with intelligent manufacturing through research and development of intelligent equipment and core technology. This paper overviews the connotation and characteristics of intelligent manufacturing and summarizes the application of intelligent manufacturing technologies such as "Internet of things" "big data", and "artificial intelligence" in the TCM industry. Based on the innovative research and development model of "intelligent classification of TCM materials, intelligent decision making of prescription and process, and online control and intelligent production" of presonalized TCM preparations, the research practice and achievements from our research group in the field of intelligent manufacturing of presonalized TCM preparations are introduced. Ultimately, the paper proposes the direction for developing intelligent manufacturing of presonalized TCM preparations, which will provide a reference for the research and application of automation and intelligence of presonalized TCM preparations.

Repurposing non-pharmacological interventions for Alzheimer's disease through link prediction on biomedical literature.

Non-pharmaceutical interventions (NPI) have great potential to improve cognitive function but limited investigation to discover NPI repurposing for Alzheimer's Disease (AD). This is the first study to develop an innovative framework to extract and represent NPI information from biomedical literature in a knowledge graph (KG), and train link prediction models to repurpose novel NPIs for AD prevention. We constructed a comprehensive KG, called ADInt, by extracting NPI information from biomedical literature. We used the previously-created SuppKG and NPI lexicon to identify NPI entities. Four KG embedding models (i.e., TransE, RotatE, DistMult and ComplEX) and two novel graph convolutional network models (i.e., R-GCN and CompGCN) were trained and compared to learn the representation of ADInt. Models were evaluated and compared on two test sets (time slice and clinical trial ground truth) and the best performing model was used to predict novel NPIs for AD. Discovery patterns were applied to generate mechanistic pathways for high scoring candidates. The ADInt has 162,212 nodes and 1,017,284 edges. R-GCN performed best in time slice (MR = 5.2054, Hits@10 = 0.8496) and clinical trial ground truth (MR = 3.4996, Hits@10 = 0.9192) test sets. After evaluation by domain experts, 10 novel dietary supplements and 10 complementary and integrative health were proposed from the score table calculated by R-GCN. Among proposed novel NPIs, we found plausible mechanistic pathways for photodynamic therapy and Choerospondias axillaris to prevent AD, and validated psychotherapy and manual therapy techniques using real-world data analysis. The proposed framework shows potential for discovering new NPIs for AD prevention and understanding their mechanistic pathways.

Enhanced YOLO v3 for precise detection of apparent damage on bridges amidst complex backgrounds.

A bridge disease identification approach based on an enhanced YOLO v3 algorithm is suggested to increase the accuracy of apparent disease detection of concrete bridges under complex backgrounds. First, the YOLO v3 network structure is enhanced to better accommodate the dense distribution and large variation of disease scale characteristics, and the detection layer incorporates the squeeze and excitation (SE) networks attention mechanism module and spatial pyramid pooling module to strengthen the semantic feature extraction ability. Secondly, CIoU with better localization ability is selected as the loss function for training. Finally, the K-means algorithm is used for anchor frame clustering on the bridge surface disease defects dataset. 1363 datasets containing exposed reinforcement, spalling, and water erosion damage of bridges are produced, and network training is done after manual labelling and data improvement in order to test the efficacy of the algorithm described in this paper. According to the trial results, the YOLO v3 model has enhanced more than the original model in terms of precision rate, recall rate, Average Precision (AP), and other indicators. Its overall mean Average Precision (mAP) value has also grown by 5.5%. With the RTX2080Ti graphics card, the detection frame rate increases to 84 Frames Per Second, enabling more precise and real-time bridge illness detection.

Natural language processing (NLP) to facilitate abstract review in medical research: the application of BioBERT to exploring the 20-year use of NLP in medical research.

BACKGROUND: Abstract review is a time and labor-consuming step in the systematic and scoping literature review in medicine. Text mining methods, typically natural language processing (NLP), may efficiently replace manual abstract screening. This study applies NLP to a deliberately selected literature review problem, the trend of using NLP in medical research, to demonstrate the performance of this automated abstract review model. METHODS: Scanning PubMed, Embase, PsycINFO, and CINAHL databases, we identified 22,294 with a final selection of 12,817 English abstracts published between 2000 and 2021. We invented a manual classification of medical fields, three variables, i.e., the context of use (COU), text source (TS), and primary research field (PRF). A training dataset was developed after reviewing 485 abstracts. We used a language model called Bidirectional Encoder Representations from Transformers to classify the abstracts. To evaluate the performance of the trained models, we report a micro f1-score and accuracy. RESULTS: The trained models' micro f1-score for classifying abstracts, into three variables were 77.35% for COU, 76.24% for TS, and 85.64% for PRF. The average annual growth rate (AAGR) of the publications was 20.99% between 2000 and 2020 (72.01 articles (95% CI: 56.80-78.30) yearly increase), with 81.76% of the abstracts published between 2010 and 2020. Studies on neoplasms constituted 27.66% of the entire corpus with an AAGR of 42.41%, followed by studies on mental conditions (AAGR = 39.28%). While electronic health or medical records comprised the highest proportion of text sources (57.12%), omics databases had the highest growth among all text sources with an AAGR of 65.08%. The most common NLP application was clinical decision support (25.45%). CONCLUSIONS: BioBERT showed an acceptable performance in the abstract review. If future research shows the high performance of this language model, it can reliably replace manual abstract reviews.

Quantitative evaluation of meniscus injury using synthetic magnetic resonance imaging.

BACKGROUND: Magnetic resonance imaging (MRI) can diagnose meniscal lesions anatomically, while quantitative MRI can reflect the changes of meniscal histology and biochemical structure. Our study aims to explore the association between the measurement values obtained from synthetic magnetic resonance imaging (SyMRI) and Stoller grades. Additionally, we aim to assess the diagnostic accuracy of SyMRI in determining the extent of meniscus injury. This potential accuracy could contribute to minimizing unnecessary invasive examinations and providing guidance for clinical treatment. METHODS: Total of 60 (n=60) patients requiring knee arthroscopic surgery and 20 (n=20) healthy subjects were collected from July 2022 to November 2022. All subjects underwent conventional MRI and SyMRI. Manual measurements of the T1, T2 and proton density (PD) values were conducted for both normal menisci and the most severely affected position of injured menisci. These measurements corresponded to the Stoller grade of meniscus injuries observed in the conventional MRI. All patients and healthy subjects were divided into normal group, degeneration group and torn group according to the Stoller grade on conventional MRI. One-way analysis of variance (ANOVA) was employed to compare the T1, T2 and PD values of the meniscus among 3 groups. The accuracy of SyMRI in diagnosing meniscus injury was assessed by comparing the findings with arthroscopic observations. The diagnostic efficiency of meniscus degeneration and tear between conventional MRI and SyMRI were analyzed using McNemar test. Furthermore, a receiver operating characteristic curve (ROC curve) was constructed and the area under the curve (AUC) was utilized for evaluation. RESULTS: According to the measurements of SyMRI, there was no statistical difference of T1 value or PD value measured by SyMRI among the normal group, degeneration group and torn group, while the difference of T2 value was statistically significant among 3 groups (P=0.001). The arthroscopic findings showed that 11 patients were meniscal degeneration and 49 patients were meniscal tears. The arthroscopic findings were used as the gold standard, and the difference of T1 and PD values among the 3 groups was not statistically significant, while the difference of T2 values (32.81±2.51 of normal group, 44.85±3.98 of degeneration group and 54.42±3.82 of torn group) was statistically significant (P=0.001). When the threshold of T2 value was 51.67 (ms), the maximum Yoden index was 0.787 and the AUC value was 0.934. CONCLUSIONS: The measurement values derived from SyMRI could reflect the Stoller grade, illustrating that SyMRI has good consistency with conventional MRI. Moreover, the notable consistency observed between SyMRI and arthroscopy suggests a potential role for SyMRI in guiding clinical diagnoses.

Spurious High Platelet Count without PLT Flag(S) in a Patient with Severe Aplastic Anaemia.

BACKGROUND: Platelet (PLT) count is one of the most important parameters of automated hematology, as spurious PLT reports could affect medical judgement and bring significant risks. In most cases, spurious PLT will not be reported for review criteria, which will be triggered by abnormal PLT histograms and PLT flag(s). Here, we present a case of severe aplastic anemia after hematopoietic stem cell transplantation with spurious high platelet count with normal histogram and no PLT flag(s). METHODS: The electrical impedance channel (PLT-I) and the fluorescence channel (PLT-F) of Sysmex XN-series hematology analyzer was used to obtain PLT results. Then, the sample was retested by another hematology analyzer MINDRAY BC-7500 [NR] CRP, and incubation was performed to rule out cryoglobulin interference. Furthermore, a microscope was used to estimate the PLT count by the ratio of platelets to red blood cells and observe the morphology of cells. RESULTS: Both PLT-I and PLT-F test results were spuriously high, and microscopically assessed platelet counts were relatively reliable. The observed spiny cells and ghost cells caused by hemolysis may have contributed to the inaccuracy of instrumental counting in this case. CONCLUSIONS: For special hematologic patients, PLT-I with flags may not be sufficient for screening purposes and PLT-F is not always accurate. Multiple testing methods including manual microscopy are needed.

Emotional State Transitions in Trauma-Exposed Individuals With and Without Posttraumatic Stress Disorder.

Importance: Posttraumatic stress disorder (PTSD) is marked by the contrasting symptoms of hyperemotional reactivity and emotional numbing (ie, reduced emotional reactivity). Comprehending the mechanism that governs the transition between neutral and negative emotional states is crucial for developing targeted therapeutic strategies. Objectives: To explore whether individuals with PTSD experience a more pronounced shift between neutral and negative emotional states and how the intensity of emotional numbing symptoms impacts this shift. Design, Setting, and Participants: This cross-sectional study used hierarchical bayesian modeling to fit a 5-parameter logistic regression to analyze the valence ratings of images. The aim was to compare the curve's slope between groups and explore its association with the severity of emotional numbing symptoms. The study was conducted online, using 35 images with a valence range from highly negative to neutral. The rating of these images was used to assess the emotional responses of the participants. The study recruited trauma-exposed individuals (witnessed or experienced life-threatening incident, violent assault, or someone being killed) between January 17 and March 8, 2023. Participants completed the PTSD Checklist for the Diagnostic and Statistical Manual of Mental Disorders (Fifth Edition) (DSM-5) (PCL-5). Exposure: On the basis of DSM-5 criteria (endorsing at least 1 symptom from clusters B and C and 2 from D and E), participants were categorized as having probable PTSD (pPTSD) or as trauma-exposed controls (TECs). Main Outcomes and Measures: The main outcome was the slope parameter (b) of the logistic curve fitted to the valence rating. The slope parameter indicates the rate at which emotional response intensity changes with stimulus valence, reflecting how quickly the transition occurs between neutral and negatively valenced states. The secondary outcome was the association between emotional numbing (PCL-5 items 12-14) and the slope parameter. Results: A total of 1440 trauma-exposed individuals were included. The pPTSD group (n = 445) was younger (mean [SD] age, 36.1 [10.9] years) compared with the TEC group (mean [SD] age, 41.5 [13.3] years; P < .001). Sex distribution (427 women in the TEC group vs 230 in the pPTSD group) did not significantly differ between groups (P = .67). The pPTSD group exhibited a steeper slope (mean slope difference, -0.255; 89% highest posterior density [HPD], -0.340 to -0.171) compared with the controls. Across all individuals (n = 1440), a robust association was found between the slope and emotional numbing severity (mean [SD] additive value, 0.100 [0.031]; 89% HPD, 0.051-0.15). Additional analysis controlling for age confirmed the association between emotional numbing and transition sharpness (mean [SD] additive value, 0.108 [0.032]; 89% HPD, 0.056-0.159), without evidence of an age-related association (mean [SD] additive value, 0.031 [0.033]; 89% HPD, -0.022 to 0.083). Conclusions and Relevance: These findings support that individuals with PTSD undergo rapid transitions between neutral and negative emotional states, a phenomenon intensified by the severity of emotional numbing symptoms. Therapeutic interventions aimed at moderating these swift emotional transitions could potentially alleviate PTSD symptoms.

Deep Location Soft-Embedding-Based Network with Regional Scoring for Mammogram Classification.

Early detection and treatment of breast cancer can significantly reduce patient mortality, and mammogram is an effective method for early screening. Computer-aided diagnosis (CAD) of mammography based on deep learning can assist radiologists in making more objective and accurate judgments. However, existing methods often depend on datasets with manual segmentation annotations. In addition, due to the large image sizes and small lesion proportions, many methods that do not use region of interest (ROI) mostly rely on multi-scale and multi-feature fusion models. These shortcomings increase the labor, money, and computational overhead of applying the model. Therefore, a deep location soft-embedding-based network with regional scoring (DLSEN-RS) is proposed. DLSEN-RS is an end-to-end mammography image classification method containing only one feature extractor and relies on positional embedding (PE) and aggregation pooling (AP) modules to locate lesion areas without bounding boxes, transfer learning, or multi-stage training. In particular, the introduced PE and AP modules exhibit versatility across various CNN models and improve the model's tumor localization and diagnostic accuracy for mammography images. Experiments are conducted on published INbreast and CBIS-DDSM datasets, and compared to previous state-of-the-art mammographic image classification methods, DLSEN-RS performed satisfactorily.

Exploring the inequalities experienced by health and care workforce and their bases - A scoping review protocol.

Planning for investment in human resources for health (HRH) is critical to achieve Universal Health Coverage (UHC) and establish a sustainable health system. Informed planning warrants a better understanding of the health labour market (HLM) to tackle a variety of health and care workforce challenges: from addressing critical supply shortage, to ensuring optimal skills mix and distribution, and addressing motivation and performance challenges. Scant evidence around the overall role of socioeconomic and cultural factors like gender, race, marital status, citizenship (migrant) status, workplace hierarchy etc. in determining workforce composition, deployment, distribution, retention, un- and underemployment, sub-optimal work environments and other factors in the 'HRH crisis' warrants further exploration. This scoping review protocol aims to map and present the available evidence on inequalities experienced by health and care workforce, the socio-economic, cultural and other bases of these inequalities, and their outcomes/ consequences. PubMed, Web of Science, CINAHL and SCOPUS will be used to identify relevant literature. All types of published study designs in English language will be included if they discuss any inequality experienced by any category of health and care workers. Elaborate keyword categories for health and care workers and inequalities context have been developed, tested and reduced to the near-final search string. Eligible articles will be charted using the Joanna Briggs Institute checklist. The sample data extraction chart in JBI manual will be used as a basic skeleton with fields added to it to serve the needs of the scoping review. Descriptive analysis will be performed, depicting basic frequencies. While no further analysis has been advised in the JBI and PRISMA protocol, thematic analysis will be undertaken; following the Braun and Clarke's method with some modification and open coding as suggested by Maquire and Delahunt.

Quantitative analysis of trabecular bone tissue cryosections via a fully automated neural network-based approach.

Cryosectioning is known as a common and well-established histological method, due to its easy accessibility, speed, and cost efficiency. However, the creation of bone cryosections is especially difficult. In this study, a cryosectioning protocol for trabecular bone that offers a relatively cheap and undemanding alternative to paraffin or resin embedded sectioning was developed. Sections are stainable with common histological dying methods while maintaining sufficient quality to answer a variety of scientific questions. Furthermore, this study introduces an automated protocol for analysing such sections, enabling users to rapidly access a wide range of different stainings. Therefore, an automated 'QuPath' neural network-based image analysis protocol for histochemical analysis of trabecular bone samples was established, and compared to other automated approaches as well as manual analysis regarding scattering, quality, and reliability. This highly automated protocol can handle enormous amounts of image data with no significant differences in its results when compared with a manual method. Even though this method was applied specifically for bone tissue, it works for a wide variety of different tissues and scientific questions.

Effect of different brushing parameters on erosive tooth wear in primary bovine enamel and dentin.

This in-vitro study aimed to analyse the effect of brushing and different brushing parameters (kind of toothpaste, kind of toothbrush, brushing force) on erosive tooth wear of primary bovine enamel and dentin. Specimens were prepared from primary bovine enamel or dentin (each group n = 12) and cyclically eroded (6 × 60 s/d, citric acid, pH 2.4) and brushed with children's toothbrushes (2 × 15 s/d) over 5 days. The brushing parameters under investigation were: toothpaste (fluoridated, fluoride-free), toothbrush (manual; rotating-oscillating and sonic, each at two different activation modes) and brushing force (1 N, 2 N). Specimens that were only eroded and not brushed served as controls. Enamel and dentin wear was quantified using widefield confocal microscopy. Statistical analysis was performed using three- and one-way ANOVAs followed by Scheffe's (enamel) or Tamhane's (dentin) post-hoc tests (p < 0.05). Brushing with the fluoridated toothpaste was able to significantly reduce erosive wear in enamel (by 15 to 37%, 6 of 10 groups) and in dentin (by 58 to 72%, all groups), while brushing with the fluoride-free toothpaste was not different from the controls. Considering the kind of toothpaste and brushing force, slight differences between the toothbrushes were observed in enamel, but not in dentin. Within the same toothbrush and activation mode, almost no differences between 1 and 2 N brushing force were detected. In conclusion, erosive tooth wear on primary bovine dental hard tissue mainly depends on the kind of toothpaste, rather than on the kind of toothbrush and the brushing force.

Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes.

OBJECTIVE: Machine learning (ML) is increasingly employed to diagnose medical conditions, with algorithms trained to assign a single label using a black-box approach. We created an ML approach using deep learning that generates outcomes that are transparent and in line with clinical, diagnostic rules. We demonstrate our approach for autism spectrum disorders (ASD), a neurodevelopmental condition with increasing prevalence. METHODS: We use unstructured data from the Centers for Disease Control and Prevention (CDC) surveillance records labeled by a CDC-trained clinician with ASD A1-3 and B1-4 criterion labels per sentence and with ASD cases labels per record using Diagnostic and Statistical Manual of Mental Disorders (DSM5) rules. One rule-based and three deep ML algorithms and six ensembles were compared and evaluated using a test set with 6773 sentences (N = 35 cases) set aside in advance. Criterion and case labeling were evaluated for each ML algorithm and ensemble. Case labeling outcomes were compared also with seven traditional tests. RESULTS: Performance for criterion labeling was highest for the hybrid BiLSTM ML model. The best case labeling was achieved by an ensemble of two BiLSTM ML models using a majority vote. It achieved 100% precision (or PPV), 83% recall (or sensitivity), 100% specificity, 91% accuracy, and 0.91 F-measure. A comparison with existing diagnostic tests shows that our best ensemble was more accurate overall. CONCLUSIONS: Transparent ML is achievable even with small datasets. By focusing on intermediate steps, deep ML can provide transparent decisions. By leveraging data redundancies, ML errors at the intermediate level have a low impact on final outcomes.

SubGE-DDI: A new prediction model for drug-drug interaction established through biomedical texts and drug-pairs knowledge subgraph enhancement.

Biomedical texts provide important data for investigating drug-drug interactions (DDIs) in the field of pharmacovigilance. Although researchers have attempted to investigate DDIs from biomedical texts and predict unknown DDIs, the lack of accurate manual annotations significantly hinders the performance of machine learning algorithms. In this study, a new DDI prediction framework, Subgraph Enhance model, was developed for DDI (SubGE-DDI) to improve the performance of machine learning algorithms. This model uses drug pairs knowledge subgraph information to achieve large-scale plain text prediction without many annotations. This model treats DDI prediction as a multi-class classification problem and predicts the specific DDI type for each drug pair (e.g. Mechanism, Effect, Advise, Interact and Negative). The drug pairs knowledge subgraph was derived from a huge drug knowledge graph containing various public datasets, such as DrugBank, TwoSIDES, OffSIDES, DrugCentral, EntrezeGene, SMPDB (The Small Molecule Pathway Database), CTD (The Comparative Toxicogenomics Database) and SIDER. The SubGE-DDI was evaluated from the public dataset (SemEval-2013 Task 9 dataset) and then compared with other state-of-the-art baselines. SubGE-DDI achieves 83.91% micro F1 score and 84.75% macro F1 score in the test dataset, outperforming the other state-of-the-art baselines. These findings show that the proposed drug pairs knowledge subgraph-assisted model can effectively improve the prediction performance of DDIs from biomedical texts.

The effect of Tai Chi/Qigong on depression and anxiety symptoms in adults with Cancer: A systematic review and meta-regression.

OBJECTIVE: We expand on prior systematic reviews of Tai chi/Qigong (TCQ) practice on depression or anxiety symptoms in adults with cancer to estimate the mean effect of TCQ on depression and anxiety in randomized controlled trials. Additionally, we perform moderator analysis to examine whether effects vary based on patient features, TCQ stimuli properties, or characteristics of research design. METHODS: Guided by PRISMA guidelines, we located articles published before August 31, 2023 using a combination of electronic database search and a complementary manual search through reference lists of articles and published reviews. Two separate multilevel meta-analyses with random-effects model were employed to estimate the overall effect of TCQ on depression and anxiety respectively. Further, multilevel meta-regression analysis was utilized to examine moderating effects based on moderators derived from patient features, TCQ stimuli properties, or characteristics associated with research design. Meta-analyses were performed in R4.0.0 and certainty of evidence with GRADEpro software. RESULTS: The TCQ intervention yielded a standardized mean effect size of 0.29 (95% CI, 0.18 to 0.40) for anxiety, indicating homogeneity among the included studies. Conversely, for depression, the standardized mean effect size was 0.35 (95% CI, 0.14 to 0.55), signifying heterogeneity: reductions were larger when the trial primary outcome, predominantly function-related outcomes, changed significantly between the TCQ and control group. CONCLUSIONS: TCQ practice exhibits small-to-moderate efficacy in alleviating depression and anxiety symptoms among cancer patients and survivors. Moreover, patients with depressive symptoms for whom TCQ intervention coupled with improvements in function-related outcomes manifested greater antidepressant effect.

Rapid and multi-target genotyping of Helicobacter pylori with digital microfluidics.

Helicobacter pylori (H. pylori) infection correlates closely with gastric diseases such as gastritis, ulcers, and cancer, influencing more than half of the world's population. Establishing a rapid, precise, and automated platform for H. pylori diagnosis is an urgent clinical need and would significantly benefit therapeutic intervention. Recombinase polymerase amplification (RPA)-CRISPR recently emerged as a promising molecular diagnostic assay due to its rapid detection capability, high specificity, and mild reaction conditions. In this work, we adapted the RPA-CRISPR assay on a digital microfluidics (DMF) system for automated H. pylori detection and genotyping. The system can achieve multi-target parallel detection of H. pylori nucleotide conservative genes (ureB) and virulence genes (cagA and vacA) across different samples within 30 min, exhibiting a detection limit of 10 copies/rxn and no false positives. We further conducted tests on 80 clinical saliva samples and compared the results with those derived from real-time quantitative polymerase chain reaction, demonstrating 100% diagnostic sensitivity and specificity for the RPA-CRISPR/DMF method. By automating the assay process on a single chip, the DMF system can significantly reduce the usage of reagents and samples, minimize the cross-contamination effect, and shorten the reaction time, with the additional benefit of losing the chance of experiment failure/inconsistency due to manual operations. The DMF system together with the RPA-CRISPR assay can be used for early detection and genotyping of H. pylori with high sensitivity and specificity, and has the potential to become a universal molecular diagnostic platform.

Bayesian tensor network structure search and its application to tensor completion.

Tensor network (TN) has demonstrated remarkable efficacy in the compact representation of high-order data. In contrast to the TN methods with pre-determined structures, the recently introduced tensor network structure search (TNSS) methods automatically learn a compact TN structure from the data, gaining increasing attention. Nonetheless, TNSS requires time-consuming manual adjustments of the penalty parameters that control the model complexity to achieve better performance, especially in the presence of missing or noisy data. To provide an effective solution to this problem, in this paper, we propose a parameters tuning-free TNSS algorithm based on Bayesian modeling, aiming at conducting TNSS in a fully data-driven manner. Specifically, the uncertainty in the data corruption is well-incorporated in the prior setting of the probabilistic model. For TN structure determination, we reframe it as a rank learning problem of the fully-connected tensor network (FCTN), integrating the generalized inverse Gaussian (GIG) distribution for low-rank promotion. To eliminate the need for hyperparameter tuning, we adopt a fully Bayesian approach and propose an efficient Markov chain Monte Carlo (MCMC) algorithm for posterior distribution sampling. Compared with the previous TNSS method, experiment results demonstrate the proposed algorithm can effectively and efficiently find the latent TN structures of the data under various missing and noise conditions and achieves the best recovery results. Furthermore, our method exhibits superior performance in tensor completion with real-world data compared to other state-of-the-art tensor-decomposition-based completion methods.

Histopathology language-image representation learning for fine-grained digital pathology cross-modal retrieval.

Large-scale digital whole slide image (WSI) datasets analysis have gained significant attention in computer-aided cancer diagnosis. Content-based histopathological image retrieval (CBHIR) is a technique that searches a large database for data samples matching input objects in both details and semantics, offering relevant diagnostic information to pathologists. However, the current methods are limited by the difficulty of gigapixels, the variable size of WSIs, and the dependence on manual annotations. In this work, we propose a novel histopathology language-image representation learning framework for fine-grained digital pathology cross-modal retrieval, which utilizes paired diagnosis reports to learn fine-grained semantics from the WSI. An anchor-based WSI encoder is built to extract hierarchical region features and a prompt-based text encoder is introduced to learn fine-grained semantics from the diagnosis reports. The proposed framework is trained with a multivariate cross-modal loss function to learn semantic information from the diagnosis report at both the instance level and region level. After training, it can perform four types of retrieval tasks based on the multi-modal database to support diagnostic requirements. We conducted experiments on an in-house dataset and a public dataset to evaluate the proposed method. Extensive experiments have demonstrated the effectiveness of the proposed method and its advantages to the present histopathology retrieval methods. The code is available at https://github.com/hudingyi/FGCR.