RESUMO
Purpose: This study aims to investigate the prevalence of artifacts in optical coherence tomography (OCT) images with acceptable signal strength and evaluate the performance of supervised deep learning models in improving OCT image quality assessment. Methods: We conducted a retrospective study on 4555 OCT images from 546 patients, with each image having an acceptable signal strength (≥6). A comprehensive analysis of prevalent OCT artifacts was performed, and five pretrained convolutional neural network models were trained and tested to infer images based on quality. Results: Our results showed a high prevalence of artifacts in OCT images with acceptable signal strength. Approximately 21% of images were labeled as nonacceptable quality. The EfficientNetV2 model demonstrated superior performance in classifying OCT image quality, achieving an area under the receiver operating characteristic curve of 0.950 ± 0.007 and an area under the precision recall curve of 0.985 ± 0.002. Conclusions: The findings highlight the limitations of relying solely on signal strength for OCT image quality assessment and the potential of deep learning models in accurately classifying image quality. Translational Relevance: Application of the deep learning-based OCT image quality assessment models may improve the OCT image data quality for both clinical applications and research.
Assuntos
Artefatos , Aprendizado Profundo , Tomografia de Coerência Óptica , Tomografia de Coerência Óptica/métodos , Humanos , Estudos Retrospectivos , Masculino , Feminino , Pessoa de Meia-Idade , Curva ROC , Prevalência , Redes Neurais de Computação , Idoso , AdultoRESUMO
PURPOSE: To evaluate the effects of two base types and three restoration designs on the resin consumption and trueness of the 3D-printed dental casts. Additionally, the study explored the dimensional stability of these 3D-printed dental casts after 1 year of storage. MATERIALS AND METHODS: Various types of reference dental casts were specifically designed to represent three types of dental restoration fabrications, including full-arch (FA), long-span (LS), and single-unit (SU) prostheses. The reference casts were digitized with a dental laboratory scanner and used to create flat and hollow base designs (N = 18) for the 3D-printed study casts. The 3D-printed study casts were digitized and evaluated against their corresponding references immediately after 3D printing and again after 1 year of storage, with the trueness quantified using the root mean square error (RMSE) at both time points. Volumes of resin used were recorded to measure resin consumption, and the weights of the 3D-printed study casts were also measured. The data were analyzed using two-way ANOVA and a Tukey post hoc test, α = 0.05. RESULTS: Volumetric analysis showed the flat-base design had significantly higher resin consumption with weights for the FA group at 42.51 ± 0.16 g, the LS group at 31.64 ± 0.07 g, and the SU group at 27.67 ± 0.31 g, as opposed to 26.22 ± 1.01 g, 22.86 ± 0.93 g, and 20.10 ± 0.19 g for the hollow designs respectively (p < 0.001). Trueness, assessed through two-way ANOVA, revealed that the flat-base design had lower RMSE values indicating better trueness in the LS (54 ± 6 µm) and SU (59 ± 7 µm) groups compared to the hollow-base design (LS: 73 ± 5, SU: 99 ± 11 µm, both p < 0.001), with no significant difference in the FA group (flat-base: 50 ± 3, hollow: 47 ± 5 µm, p = 0.398). After 1 year, the flat-base design demonstrated superior dimensional stability in the LS (flat base: 56 ± 6 µm, hollow base: 149 ±45 µm, p < 0.001) and SU groups (flat base: 95 ± 8 µm, hollow base: 183 ±27 µm, p < 0.001), with the FA group showing no significant difference in the base design (flat base: 47 ± 9, hollow base: 62 ± 12 µm, p = 0.428). CONCLUSIONS: The hollow-base design group showed lower resin consumption than the flat-base design group. However, the flat-base designs exhibited superior trueness and less distortion after 1 year of storage. These findings indicate that despite the higher material usage, flat-base designs provide better initial accuracy and maintain their dimensional stability over time for most groups.
RESUMO
In recent years, organic-inorganic hybrid perovskite materials have become one of the most promising materials in the new generation of solar cells. These perovskites can provide excellent photoelectric properties after a simple fabrication process. Although perovskite solar cells have achieved high power conversion efficiency, instability concerns regarding material exposure to heat, moisture, air, and UV light present hindrances to commercialization. In this study, three kinds of perovskites (MAPbI3, MAPbI3-xBrx, and MAPbI3-xClx) were used to investigate the crystal stability upon exposure to heat and UV light. SEM, XRD, and FTIR were used to observe the surface morphology, crystal structure, and functional groups of the perovskite thin films. XPS was used to examine the surface composition and chemical state of the perovskite thin films under different conditions. Among these three types of perovskites, it was found that the MAPbI3-xBrx crystal demonstrated the best stability. ToF-SIMS was used to confirm the molecular distribution of the MAPbI3-xBrx films upon exposure to heat and UV light at different depths. ToF-SIMS revealed that [Pb]+ and [PbI]+ aggregated at the interface between the perovskite and ITO substrate after 14 days of thermal treatment. On the other hand, [Pb]+ and [PbI]+ were distributed uniformly after 3 days of UV exposure. This study systematically analyzed and revealed the thermal- and UV-induced degradation process of three perovskite films by using surface analysis techniques. It was concluded that bromine-doped perovskite films had better stability, and UV light caused more severe damage than heat.
RESUMO
BACKGROUND: Children with dental caries are treated with stainless steel metal crowns (SSC), but the aesthetics and precision still need to be improved. Currently, both 3D-printed resin crowns (PRC) and computer-aided design/computer-aided manufacture (CAD/CAM) resin crowns (CRC) meet the clinical requirements for crown applications in terms of strength, production time, cost, and aesthetics. AIM: This study replaced SSC with customized resin crowns by 3D printing and CAD/CAM. DESIGN: In this study, PRC, CRC, and SSC were used for incisor and molar restorations, and 60 crowns were made with 10 for each group. The fabrication efficiency, surface characteristics, marginal fit, and stability of the two different crowns were evaluated. RESULTS: PRC and CRC show superior color and surface characteristics, though production times are longer (5.3-12.4 times and 3.3-9.1 times, respectively) than for SSC (p < .05). They, however, can be completed within 80 min. Edge gaps for PRC and CRC are significantly lower (13.0-19.2 times and 13.0-13.7 times) than for SSC (p < .05). All materials exhibit good stability. CONCLUSION: The 3D-PRCs and CAD/CAM resin crowns may replace SSCs as a potential choice for clinical child caries.
RESUMO
The skin is subjected to various external factors that contribute to aging including oxidative stress from hydrogen peroxide (H2O2). This study investigated the distribution of aquaporin-8 (AQP8), a protein that transports H2O2 across biological membranes, in skin cells, and its effects in mitigating H2O2-induced oxidative damage. Human dermal fibroblasts were treated with increasing concentrations of H2O2 to evaluate oxidative damage. Cell viability, reactive oxygen species (ROS) generation, and the expression of specific genes associated with skin aging (IL-10, FPR2, COL1A1, KRT19, and Aggrecan) were evaluated and AQP8 expression was assessed via quantitative polymerase chain reaction and western blotting. Small-interfering RNA was used to silence the AQP8 gene and evaluate its significance. The results show that H2O2 treatment reduces cell viability and increases ROS generation, leading to oxidative damage that affects the expression of target molecules. Interestingly, H2O2-treated cells exhibit high levels of AQP8 expression and gene silencing of AQP8 reverses high levels of ROS and low levels of COL1A1, KRT19, and Aggrecan expression in stressed cells, indicating that AQP8 plays a vital role in preventing oxidative damage and consequent aging. In conclusion, AQP8 is upregulated in human dermal fibroblasts during H2O2-induced oxidative stress and may help prevent oxidative damage and aging. These findings suggest that AQP8 could be a potential therapeutic target for skin aging. Further research is necessary to explore the feasibility of using AQP8 as a preventive or therapeutic strategy for maintaining skin health.
RESUMO
Lidocaine, a local anesthetic widely used in dentistry, is esteemed for its efficacy and safety. Recent research reveals its additional role in modulating the immune system, and particularly in reducing inflammation crucial for protecting tooth-supporting tissues. Notably, monocytes and macrophages, essential cellular components overseeing various physiological and pathological processes, stand as potential mediators of lidocaine's effects. Therefore, this study aimed to investigate how lidocaine influences cell behavior using RNA sequencing. To investigate the effect of lidocaine on THP-1 cells' behavior, we performed an MTT assay and RNA-Seq along with qPCR analyses to evaluate the transcriptomic and proteomic changes in THP-1 cells. Our results showed that a high dose of lidocaine (>1 mM) had a significant cytotoxic effect on THP-1 cells. However, a lidocaine dose lower than 0.5 mM induced a mixed anti-inflammatory profile by significantly upregulating tissue remodeling (GDF15, FGF7, HGF, COL4A3, COL8A2, LAMB2, LAMC2, PDGFRA, and VEGFA) and through the resolution of inflammation (Cpeb4, Socs1, Socs2, Socs3, Dusp1, Tnfaip3, and Gata3) gene cassettes. This study explores the effect of lidocaine on the THP-1 in the M2-like healing phenotype and provides potential applications of lidocaine's therapeutic effectiveness in dental tissue repair.
RESUMO
Background/purpose: Current 3D-printing technology has been widely used for creating dental resin restorations. This study aimed to evaluate the effect of light intensity, time, and energy post-curing on the surface color of 3D-printed resin crowns. However, the influences of post-curing parameters on the restoration after printing still need to be explored. Therefore, this project investigates the effect of post-cure conditions on resin color. Materials and methods: Specimens from single-crown (SC) and pontic (PO) specimens underwent post-curing at various light intensities (105, 210, 420, 630, and 860 mW/cm2) for 5, 10, and 15 min. Specimens were observed at three predetermined points and measured using a commercial spectrophotometer that utilizes the CIE Lab∗ color space. Subsequently, samples were analyzed for color differences (ΔE). Results: ΔE color differences in evaluated samples were influenced by the light intensity, time, and energy post-curing. SC samples showed a significant color difference (P < 0.05), with the lowest value at 5 min of 16 (860 mW/cm2), while 10 and 15 min had a difference of 4 (210 mW/cm2). PO samples exhibited a significant decrease in the color difference (P < 0.05) at 5 and 10 min of 16 (860 mW/cm2), and at 15 min of 12 (630 mW/cm2). Conclusion: The results of this study indicate that exposing a resin crown to a high light intensity results in color stability and allows shorter post-curing times.
RESUMO
Background/purpose: Producing tooth crowns through dental technology is a basic function of dentistry. The morphology of tooth crowns is the most important parameter for evaluating its acceptability. The procedures were divided into four steps: tooth collection, scanning skills, use of mathematical methods and software, and machine learning calculation. Materials and methods: Dental plaster rods were prepared. The effective data collected were to classify 121 teeth (15th tooth position), 342 teeth (16th tooth position), 69 teeth (21st tooth position), and 89 teeth (43rd tooth position), for a total of 621 teeth. The procedures are divided into four steps: tooth collection, scanning skills, use of mathematical methods and software, and machine learning calculation. Results: The area under the curve (AUC) value was 0, 0.5, and 0.72 in this study. The precision rate and recall rate of micro-averaging/macro-averaging were 0.75/0.73 and 0.75/0.72. If we took a newly carved tooth picture into the program, the current effectiveness of machine learning was about 70%-75% to evaluate the quality of tooth morphology. Through the calculation and analysis of the two different concepts of micro-average/macro-average and AUC, similar values could be obtained. Conclusion: This study established a set of procedures that can judge the quality of hand-carved plaster sticks and teeth, and the accuracy rate is about 70%-75%. It is expected that this process can be used to assist dental technicians in judging the pros and cons of hand-carved plaster sticks and teeth, so as to help dental technicians to learn the tooth morphology more effectively.
RESUMO
PURPOSE: To assess the survival impact of pre-concurrent chemoradiotherapy (CCRT) staging with positron emission tomography-CT (PET-CT) in patients with unresectable epidermal growth factor receptor (EGFR) mutation-positive adenocarcinoma. METHODS: Patients with unresectable stage IIIA-IIIC EGFR mutation-positive adenocarcinoma undergoing definitive CCRT were divided into two groups: those who received PET-CT staging prior to CCRT and those with other staging methods. Survival outcomes were compared after propensity score matching. RESULTS: Analysis of 11 856 patients (5928 in each group) showed that PET-CT staging was associated with improved survival (adjusted HR of all-cause mortality: 0.74, 95% CI 0.71 to 0.79). Other prognostic factors included male sex, age group, clinical stage, adjuvant treatment, smoking status, Charlson Comorbidity Index score and treatment setting. CONCLUSION: Pre-CCRT staging with PET-CT in patients with unresectable EGFR mutation-positive adenocarcinoma of clinical stage IIIA-IIIC was associated with enhanced survival. Independent prognostic factors were also identified.
RESUMO
OBJECTIVE: The unique structure of human teeth limits dental repair to custom-made solutions. The production process requires a lot of time and manpower. At present, artificial intelligence (AI) has begun to be used in the medical field and improve efficiency. This study attempted to design a variety of dental restorations using AI and evaluate their clinical applicability. METHODS: Using inlay and crown restoration types commonly used in dental standard models, we compared differences in artificial wax-up carving (wax-up), artificial digital designs (digital) and AI designs (AI). The AI system was designed using computer calculations, and the other two methods were designed by humans. Restorations were made by 3D printing resin material. Image evaluations were compared with cone beam computed tomography (CBCT) by calculating the root mean squared error. RESULTS: Surface truth results showed that AI (68.4 µm) and digital-designed crowns (51.0 µm) had better reproducibility. Using AI for the crown reduced the time spent by 400% (compared to digital) and 900% (compared to wax-up). Optical microscopic and CBCT images showed that AI and digital designs had close margin gaps (p < 0.05). The margin gap of the crown showed that the wax-up group was 4.1 and 4.3 times greater than those of the AI and digital crowns, respectively. Therefore, the utilization of artificial intelligence can assist in the production of dental restorations, thereby enhancing both production efficiency and accuracy. SIGNIFICANCE: It is expected that the development of AI can contribute to the reproducibility, efficiency, and goodness of fit of dental restorations.
Assuntos
Desenho Assistido por Computador , Coroas , Humanos , Inteligência Artificial , Reprodutibilidade dos Testes , Planejamento de Prótese Dentária/métodosRESUMO
OBJECTIVE: Surgical outcome prediction is challenging but necessary for postoperative management. Current machine learning models utilize pre- and post-op data, excluding intraoperative information in surgical notes. Current models also usually predict binary outcomes even when surgeries have multiple outcomes that require different postoperative management. This study addresses these gaps by incorporating intraoperative information into multimodal models for multiclass glaucoma surgery outcome prediction. MATERIALS AND METHODS: We developed and evaluated multimodal deep learning models for multiclass glaucoma trabeculectomy surgery outcomes using both structured EHR data and free-text operative notes. We compare those to baseline models that use structured EHR data exclusively, or neural network models that leverage only operative notes. RESULTS: The multimodal neural network had the highest performance with a macro AUROC of 0.750 and F1 score of 0.583. It outperformed the baseline machine learning model with structured EHR data alone (macro AUROC of 0.712 and F1 score of 0.486). Additionally, the multimodal model achieved the highest recall (0.692) for hypotony surgical failure, while the surgical success group had the highest precision (0.884) and F1 score (0.775). DISCUSSION: This study shows that operative notes are an important source of predictive information. The multimodal predictive model combining perioperative notes and structured pre- and post-op EHR data outperformed other models. Multiclass surgical outcome prediction can provide valuable insights for clinical decision-making. CONCLUSIONS: Our results show the potential of deep learning models to enhance clinical decision-making for postoperative management. They can be applied to other specialties to improve surgical outcome predictions.
Assuntos
Aprendizado Profundo , Glaucoma , Humanos , Glaucoma/cirurgia , Aprendizado de Máquina , Redes Neurais de Computação , Resultado do TratamentoRESUMO
Purpose: Retinopathy of prematurity (ROP) is one of the leading causes of blindness in children. Although the role of oxygen in the pathophysiology of ROP is well established, a precise understanding of the dynamic relationship between oxygen exposure ROP incidence and severity is lacking. The purpose of this study was to evaluate the correlation between time-dependent oxygen variables and the onset of ROP. Design: Retrospective cohort study. Participants: Two hundred thirty infants who were born at a single academic center and met the inclusion criteria were included. Infants are mainly born between January 2011 and October 2022. Methods: Patient data were extracted from electronic health records (EHRs), with sufficient time-dependent oxygen data. Clinical outcomes for ROP were recorded as none/mild or moderate/severe (defined as type II or worse). Mixed-effects linear models were used to compare the 2 groups in terms of dynamic oxygen variables, such as daily average and the coefficient of variation (COV) fraction of inspired oxygen (FiO2). Support vector machine (SVM) and long-short-term memory (LSTM)-based multimodal models were trained with fivefold cross-validation to predict which infants would develop moderate/severe ROP. Gestational age (GA), birth weight, and time-dependent oxygen variables were used to develop predictive models. Main Outcome Measures: Model cross-validation performance was evaluated by computing the mean area under the receiver operating characteristic (AUROC) curve, precision, recall, and F1 score. Results: We found that both daily average and COV of FiO2 were associated with more severe ROP (adjusted P < 0.001). With fivefold cross-validation, the multimodal LSTM models had higher performance than the best static models (SVM using GA and 3 average FiO2 features) and SVM models trained on GA alone (mean AUROC = 0.89 ± 0.04 vs. 0.86 ± 0.05 vs. 0.83 ± 0.04). Conclusions: The development of severe ROP might not only be influenced by oxygen exposure but also by its fluctuation, which provides direction for future study of pathophysiological factors associated with severe ROP development. Additionally, we demonstrated that multimodal neural networks can be a method to extract useful information from time-series data, which may be a valuable methodology for the investigation of other diseases using EHR data. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
RESUMO
Abstract: Background/purpose: Overlay restorations can be used clinically as a treatment option to preserve natural dentine. However, whether the residual enamel thickness and overlay thickness affect the adhesion between the restoration and tooth is still unknown. This study was to investigate effects of the overlay thickness and residual enamel thickness on bonding strength. Materials and methods: Overlays of different thicknesses were prepared with natural teeth which had 2, 4, and 6 mm of occlusal reduction (n = 10). Specimens were subjected to 10,000 cycles in water at 5-55 °C, and finally compressive strength tests were used to evaluate the bonding strength. Results: All groups showed good bond strength (P > 0.05). The overlay restorations of different thicknesses reduced the preparation amount by 30.3%-7.2% and significantly preserved more of the tooth structure (P < 0.005). Compared to the control group, the overlay restoration increased the marginal fitness by about 0.67-0.88 times. The thermal cycling indicated that the decrease in the maximum bearing stress was due to the aging of the ceramic itself. Therefore, the thickness of the overlay had a greater influence on the compressive strength than the bond strength. Conclusion: Based on the above this study recommends an overlay thickness of at least 2 mm in clinical practice. The aging test confirmed that adhesion between the overlay and teeth was quite firm and stable. This shows that a stable adhesive effect of the overlay can be used as a treatment option for preserving a greater amount of a tooth's structure.
RESUMO
Mixed-cation hybrid perovskite nanocrystal (HPNC) with high crystallinity, color purity, and tunable optical bandgap offers a practical pathway toward next-generation displays. Herein, a two-step modified hot-injection combined with cation compositional engineering and surface treatment to synthesize high-purity cesium/formamidinium lead bromide HPNCs(Cs1-x FAx PbBr3 ) is presented. The optimized Cs0.5 FA0.5 PbBr3 light-emitting devices (LEDs) exhibit uniform luminescence of 3500 cd m-2 and a prominent current efficiency of 21.5 cd A-1 . As a proof of concept, a self-healing polymer (SHP) integrated with white LED backlight and laser prototypes exhibited 4 h autonomous self-healing through the synergistic effect of weak reversible imine bonds and stronger H-bonds. First, the SHP-HPNCs-initial and SHP-HPNCs-cut possess high long-term stability and dramatically suppressed lead leakage as low as 0.6 ppm along with a low leakage rate of 1.11 × 10-5 cm2 and 3.36 × 10-5 cm2 even over 6 months in water. Second, the Cs0.5 FA0.5 PbBr3 HPNCs and SHP-induced shattered-repaired perovskite glass substrate show the lowest lasing threshold values of 1.24 and 8.58 µJ cm-2 , respectively. This work provides an integrative and in-depth approach to exploiting SHP with intrinsic and entropic self-healing capabilities combined with HPNCs to develop robust and reliable soft-electronic backlight and laser applications.
RESUMO
The current digital dentistry workflow has streamlined dental restoration production, but the effectiveness of digital virtual design and 3D printing for restorations still needs evaluation. This study explores the impact of model-free digital design and 3D-printing placement angles on restorations, including single crowns and long bridges produced with and without casts. The restorations are 3D printed using resin at placement angles of 0°, 60°, and 90°. Each group of samples was replicated ten times, resulting in a total of 120 restorations. The Root Mean Square Error (RMSE) value was used to evaluate the surface integrity of the restoration. In addition, the contact space, edge gap, and occlusal space of restorations produced by different processes were recorded. The results indicate that there was no significant difference in the RMSE value of the crown group (p > 0.05). Changing the bridge restoration angle from 0° to 90° resulted in RMSE values increasing by 2.02 times (without casts) and 2.39 times (with casts). Furthermore, the marginal gaps in the crown group were all less than 60 µm, indicating good adaptation. In contrast, the bridge group showed a significant increase in marginal gaps at higher placement angles (p > 0.05). Based on the findings, virtual fabrication without casts does not compromise the accuracy of dental restorations. When the position of the long bridge exceeds 60 degrees, the error will increase. Therefore, designs without casts and parallel placement result in higher accuracy for dental restorations.
RESUMO
Purpose: To describe the methods involved in processing and characteristics of an open dataset of annotated clinical notes from the electronic health record (EHR) annotated for glaucoma medications. Methods: In this study, 480 clinical notes from office visits, medical record numbers (MRNs), visit identification numbers, provider names, and billing codes were extracted for 480 patients seen for glaucoma by a comprehensive or glaucoma ophthalmologist from January 1, 2019, to August 31, 2020. MRNs and all visit data were de-identified using a hash function with salt from the deidentifyr package. All progress notes were annotated for glaucoma medication name, route, frequency, dosage, and drug use using an open-source annotation tool, Doccano. Annotations were saved separately. All protected health information (PHI) in progress notes and annotated files were de-identified using the published de-identifying algorithm Philter. All progress notes and annotations were manually validated by two ophthalmologists to ensure complete de-identification. Results: The final dataset contained 5520 annotated sentences, including those with and without medications, for 480 clinical notes. Manual validation revealed 10 instances of remaining PHI which were manually corrected. Conclusions: Annotated free-text clinical notes can be de-identified for upload as an open dataset. As data availability increases with the adoption of EHRs, free-text open datasets will become increasingly valuable for "big data" research and artificial intelligence development. This dataset is published online and publicly available at https://github.com/jche253/Glaucoma_Med_Dataset. Translational Relevance: This open access medication dataset may be a source of raw data for future research involving big data and artificial intelligence research using free-text.
Assuntos
Registros Eletrônicos de Saúde , Glaucoma , Humanos , Inteligência Artificial , Glaucoma/tratamento farmacológico , Glaucoma/epidemiologia , Big Data , RegistrosRESUMO
Esophageal cancer (EC) remains a leading cause of death worldwide and in Taiwan. The prognosis of advanced-stage EC is notably poor, and the treatment options are limited. Chinese herbal medicine (CHM) has been widely used as a complementary treatment for cancer, yet the long-term effect of CHM in stage IV EC remains unclear. The multi-institutional cohort obtained from the Chang Gung research database (CGRD) was used to study the long-term outcome of CHM use among incident stage IV EC patients from 1 January 2002, to 31 December 2018. All patients were followed up to 5 years or the occurrence of death. The overall survival (OS) and disease-specific survival rates were conducted using Kaplan-Meier estimation. Overlap weighing and landmark analysis were used to eliminate confounding and immortal time biases. Furthermore, we demonstrated the core CHMs for stage IV EC by using the Chinese herbal medicine network (CMN) analysis on prescriptions. Nine hundred eighty-five stage IV EC patients were analyzed, including 74 CHM users and 911 non-CHM users. We found the use of CHM was associated with a higher 5-year overall survival rate than CHM nonusers (the cumulative probability: 19.52% versus 6.04%, log-rank test: p < 0.001, and the p < 0.001 with overlap weighting). In addition, the overall median survival time was about 7 months longer among CHM users. Moreover, the lower 1-, 3-, 5-year disease-specific survival rates were higher among CHM users. Additionally, the risk of all-cause mortality was lower among CHM users when considering accessible demographic covariates (adjusted hazard ratio: 0.59, 95%CI: 0.39, 0.89, p = 0.011). Furthermore, the CMN analysis revealed that CHMs improved health while relieving tumor burden. For example, Hedyotis diffusa Willd . was the core CHM with an anti-cancer effect, while Fritillaria thunbergii Miq and Sevilla maindronide Rochebrune were used together to relieve cancer-related gastrointestinal discomfort. The use of CHM seems safe and possibly beneficial among stage IV EC patients with a higher 5-year OS. Further clinical trials on CHM were guaranteed to explore the role of CHM in managing stage IV EC patients.
RESUMO
For patients with inoperable huge hepatocellular carcinoma (H-HCC, tumor size ≥10 cm), treatment options are limited. This study aimed to evaluate the characteristics and outcomes of patients with H-HCC who use Chinese herbal medicine (CHM). Multi-institutional cohort data were obtained from the Chang Gung Research Database (CGRD) between 1 January 2002 and 31 December 2018. All patients were followed up for 3 years or until the occurrence of death. Characteristics of CHM users and risk of all-cause mortality were assessed, and core CHMs with potential pharmacologic pathways were explored. Among 1618 patients, clinical features of CHM users (88) and nonusers (1530) were similar except for lower serum α-fetoprotein (AFP) and higher serum albumin levels in CHM users. CHM users had significantly higher 3 year overall survival rates (15.0% vs. 9.7%) and 3 year liver-specific survival rates (13.4% vs. 10.7%), about 3 months longer median survival time, and lower risk of all-cause mortality. Core CHMs were discovered from the prescriptions, including Hedyotis diffusa Willd combined with Scutellaria barbata D.Don, Salvia miltiorrhiza Bunge., Curcuma longa L., Rheum palmatum L., and Astragalus mongholicus Bunge. CHM use appears safe and is possibly beneficial for inoperable H-HCC patients; however, further clinical trials are still required.
Assuntos
Carcinoma Hepatocelular , Medicamentos de Ervas Chinesas , Neoplasias Hepáticas , Carcinoma Hepatocelular/tratamento farmacológico , Carcinoma Hepatocelular/epidemiologia , Estudos de Coortes , Medicamentos de Ervas Chinesas/uso terapêutico , Humanos , Neoplasias Hepáticas/tratamento farmacológico , Neoplasias Hepáticas/epidemiologia , Medicina Tradicional Chinesa , Estudos Retrospectivos , Albumina Sérica , alfa-FetoproteínasRESUMO
Objective: The authors performed several tree-based algorithms and an association rules mining as data mining tools to find useful determinants for neurological outcomes in out-of-hospital cardiac arrest (OHCA) patients as well as to assess the effect of the first-aid and basic characteristics in the EMS system. Patients and Methods: This was a retrospective cohort study. The outcome was Cerebral Performance Categories grading on OHCA patients at hospital discharge. Decision tree-based models inclusive of C4.5 algorithm, classification and regression tree and random forest were built to determine an OHCA patient's prognosis. Association rules mining was another data mining method which we used to find the combination of prognostic factors linked to the outcome. Results: The total of 3520 patients were included in the final analysis. The mean age was 67.53 (±18.4) year-old and 63.4% were men. To overcome the imbalance outcome issue in machine learning, the random forest has a better predictive ability for OHCA patients in overall accuracy (91.19%), weighted precision (88.76%), weighted recall (91.20%) and F1 score (0.9) by oversampling adjustment. Under association rules mining, patients who had any witness on the spot when encountering OHCA or who had ever ROSC during first-aid would be highly correlated with good CPC prognosis. Conclusion: The random forest has a better predictive ability for OHCA patients. This paper provides a role model applying several machine learning algorithms to the first-aid clinical assessment that will be promising combining with Artificial Intelligence for applying to emergency medical services.