Predicting early mortality and severe intraventricular hemorrhage in very-low birth weight preterm infants: a nationwide, multicenter study using machine learning.

Our aim was to develop a machine learning-based predictor for early mortality and severe intraventricular hemorrhage (IVH) in very-low birth weight (VLBW) preterm infants in Taiwan. We collected retrospective data from VLBW infants, dividing them into two cohorts: one for model development and internal validation (Cohort 1, 2016-2021), and another for external validation (Cohort 2, 2022). Primary outcomes included early mortality, severe IVH, and early poor outcomes (a combination of both). Data preprocessing involved 23 variables, with the top four predictors identified as gestational age, birth body weight, 5-min Apgar score, and endotracheal tube ventilation. Six machine learning algorithms were employed. Among 7471 infants analyzed, the selected predictors consistently performed well across all outcomes. Logistic regression and neural network models showed the highest predictive performance (AUC 0.81-0.90 in both internal and external validation) and were well-calibrated, confirmed by calibration plots and the lowest two mean Brier scores (0.0685 and 0.0691). We developed a robust machine learning-based outcome predictor using only four accessible variables, offering valuable prognostic information for parents and aiding healthcare providers in decision-making.

Unmasking air quality: A novel image-based approach to align public perception with pollution levels.

In the quest to reconcile public perception of air pollution with scientific measurements, our study introduced a pioneering method involving a gradient boost-regression tree model integrating PM2.5 concentration, visibility, and image-based data. Traditional stationary monitoring often falls short of accurately capturing public air quality perceptions, prompting the need for alternative strategies. Leveraging an extensive dataset of over 20,000 public visibility perception evaluations and over 8,000 stationary images, our models effectively quantify diverse air quality perceptions. The predictive prowess of our models was validated by strong performance metrics for perceived visibility (R = 0.98, RMSE = 0.19), all-day PM2.5 concentrations (R: 0.77-0.78, RMSE: 8.31-9.40), and Central Weather Bureau visibility records (R = 0.82, RMSE = 9.00). Interestingly, image contrast and light intensity hold greater importance than scenery clarity in the visibility perception model. However, clarity is prioritized in PM2.5 and Central Weather Bureau models. Our research also unveiled spatial limitations in stationary monitoring and outlined the variations in predictive image features between near and far stations. Crucially, all models benefit from the characterization of atmospheric light sources through defogging techniques. The image-based insights highlight the disparity between public perception of air pollution and current policy implementation. In other words, policymakers should shift from solely emphasizing the reduction of PM2.5 levels to also incorporating the public's perception of visibility into their strategies. Our findings have broad implications for air quality evaluation, image mining in specific areas, and formulating air quality management strategies that account for public perception.

Small blood stem cells for enhancing early osseointegration formation on dental implants: a human phase I safety study.

BACKGROUND: Small blood stem cells (SB cells), isolated from human peripheral blood, demonstrated the ability to benefit bone regeneration and osseointegration. The primary goal of our study is to examine the safety and tolerability of SB cells in dental implantation for human patients with severe bone defects. METHODS: Nine patients were enrolled and divided into three groups with SB cell treatment doses of 1 × 105, 1 × 106, and 1 × 107 SB cells, and then evaluated by computed tomography (CT) scans to assess bone mineral density (BMD) by Hounsfield units (HU) scoring. Testing was conducted before treatment and on weeks 4, 6, 8, and 12 post dental implantation. Blood and comprehensive chemistry panel testing were also performed. RESULTS: No severe adverse effects were observed for up to 6-month trial. Grade 1 leukocytosis, anemia, and elevated liver function were observed, but related with the patient's condition or the implant treatment itself and not the transplantation of SB cells. The levels of cytokines and chemokines were detected by a multiplex immunological assay. Elevated levels of eotaxin, FGF2, MCP-1, MDC, and IL17a were found among patients who received SB cell treatment. This observation suggested SB cells triggered cytokines and chemokines for local tissue repair. To ensure the efficacy of SB cells in dental implantation, the BMD and maximum stresses via stress analysis model were measured through CT scanning. All patients who suffered from severe bone defect showed improvement from D3 level to D1 or D2 level. The HU score acceleration can be observed by week 2 after guided bone regeneration (GBR) and prior to dental implantation. CONCLUSIONS: This phase I study shows that treatment of SB cells for dental implantation is well tolerated with no major adverse effects. The use of SB cells for accelerating the osseointegration in high-risk dental implant patients warrants further phase II studies. TRIAL REGISTRATION: Taiwan Clinical Trial Registry ( SB-GBR001 ) and clinical trial registry of the United States ( NCT04451486 ).

Evaluation of the implant stability and the marginal bone level changes during the first three months of dental implant healing process: A prospective clinical study.

Achievement of adequate implant stability is one of the determinants for long-term successful osseointegration. Resonance frequency analysis was developed to monitor implant stability and is now a well-recognized, non-invasive tool for determining the appropriate time for functional loading. However, there have been few studies with continuous evaluation and comparison of implant stability and marginal bone level changes between two different macro designs and clinical situations during the implant healing process. Thus, the purpose of this clinical trial is to evaluate the implant stability and marginal bone level changes of straight and conical implants during the implant healing process. In this prospective clinical trial, 25 participants were randomized to either straight or conical implants. A total of 32 titanium dental implants with a length of 9 mm or 11 mm were installed in the maxilla and the mandible according to the manufacturer's instructions. A resonance frequency analyzer was used to measure the implant stability quotient (ISQ) at the time of implant placement and after 2 weeks, 4 weeks, 6 weeks, 8 weeks, 10 weeks, and 12 weeks of healing. The changes in the peri-implant marginal bone level were evaluated from digital radiographic films taken at the time of implant placement and after 4 weeks, 8 weeks, and 12 weeks of healing. The preliminary results of this study revealed higher ISQ values and better healing tendency for conical implants in comparison with straight implants in the maxilla. Similar ISQ values and healing tendency were observed for straight and conical implants in the mandible. No significant differences in marginal bone loss were found between the straight and conical implants. However, in the mandible, slightly more marginal bone loss was found with the conical implants than straight implants after 12 weeks of healing. In conclusion, ISQ healing tendency and marginal bone loss are influenced by implant macro-design and jaw regions. Straight implants revealed similar ISQ healing tendency and marginal bone loss in both the mandible and maxilla. Conical implants were confirmed more beneficial for maintenance of implant stability and marginal bone level in the maxilla.