Make Treatment Plans Research Articles

Coinfection of EBV with other pathogens: a narrative review

The Epstein-Barr viwrus (EBV) is a common herpesvirus that affects more than 90% of people worldwide. Even while EBV infections are frequently asymptomatic, they can cause autoimmune diseases and a number of cancers, especially in those with impaired immune systems. The intricate relationships between EBV and other coinfecting pathogens, including as human immunodeficiency virus (HIV), human papilloma virus (HPV), cytomegalovirus (CMV), and Plasmodium species, are examined in this study. We investigated the fundamental processes of these coinfections, their effects on the course of the disease, and their practical ramifications. The study reviewed how co-infections with EBV might modify immune responses, promote oncogenesis, and make treatment plans more challenging. In this review, we also discussed current therapeutic strategies, such as targeted molecular interventions, EBV vaccines, and adoptive T-cell therapy. The review underscores the need for more research to provide more focused and effective therapies that address the mutually reinforcing effects of numerous infections in disorders linked with EBV.

DA-Net: A classification-guided network for dental anomaly detection from dental and maxillofacial images

Dental abnormalities (DA) are frequent signs of disorders of the mouth that cause discomfort, infection, and loss of teeth. Early and reasonably priced treatment may be possible if defective teeth in the oral cavity are automatically detected. Several research works have endeavored to create a potent deep learning model capable of identifying DA from pictures. However, because of the following problems, aberrant teeth from the oral cavity are difficult to detect: 1) Normal teeth and crowded dentition frequently overlap; 2) The lesion area on the tooth surface is tiny. This paper proposes a professional dental anomaly detection network (DA-Net) to address such issues. First, a multi-scale dense connection module (MSDC) is designed to distinguish crowded teeth from normal teeth by learning multi-scale spatial information of dentition. Then, a pixel differential convolution (PDC) module is designed to perform pathological tooth recognition by extracting small lesion features. Finally, a multi-stage convolutional attention module (MSCA) is developed to integrate spatial information and channel information to obtain abnormal teeth in small areas. Experiments on benchmarks show that DA-Net performs well in dental anomaly detection and can further assist doctors in making treatment plans. Specifically, the DA-Net method performs best on multiple detection evaluation metrics: IoU, PRE, REC, and mAP. In terms of REC and mAP indicators, the proposed DA-Net method is 1.1% and 1.3% higher than the second-ranked YOLOv7 method.

Functional Near-Infrared Spectroscopy in neurodegenerative disease: a review.

In recent years, with the aggravation of aging, the incidence of neurodegenerative diseases is increasing year by year, and the prognosis of patients is poor. Functional Near-Infrared Spectroscopy (fNIRS) is a new and non-invasive neuroimaging technology, which has been gradually deepened in the application research of neurodegenerative diseases by virtue of its unique neurooxygen signal brain functional imaging characteristics in monitoring the disease condition, making treatment plans and evaluating the treatment effect. In this paper, the mechanism of action and technical characteristics of fNIRS are briefly introduced, and the application research of fNIRS in different neurodegenerative diseases is summarized in order to provide new ideas for future related research and clinical application.

Extended duration linagliptin nanoparticles: a novel, safe and effective future of diabetes treatment?

Dear Editor, Diabetes Mellitus (DM), a chronic disease characterised by hyperglycaemia caused by either underproduction of insulin or defective insulin action, has become more prevalent globally; affecting 1 in every 10 adults over the past years with type 2 diabetes being more common in the low- and middle-income countries and type 1 in high-income countries (1). Pakistan, being a lower-middle-income country, has a 26.7% prevalence of diabetes and age-adjusted comparative prevalence of 30.8% affecting 1 in approximately every 4th adult (2). The current guidelines for the management of diabetes include insulin, metformin, sulfonylureas, and sodium-glucose co-transporters type 2 (SGLT-2) inhibitors. However, hypoglycaemia, weight gain, gastrointestinal problems and contraindication of their use in patients with pre-existing renal diseases pose problems for clinicians. Poor patient compliance in following the regular antidiabetic regimen also make treatment plans ineffective. Thus, newer drugs are constantly being researched (3). Metformin has been an excellent treatment option with only a slight risk for some specific patients to develop lactic acidosis. It is the most commonly prescribed medication for DM. Another drug, Linagliptin (Lina) was approved by the FDA in 2011 as an effective dipeptidyl peptidase inhibitor for the treatment of DM. It has been used as monotherapy and in combination with dapagliflozin, an SGLT2 inhibitor, for the treatment of diabetes in patients with a history of metformin therapy. However, its use was limited due to its low bioavailability (4). Recent research suggests that the extended duration (ED) Lina via the use of poly d, l-lactic-co-glycolic acid (PLGA) polymers in nanoparticle form could be beneficial in the management of type 2 DM. It has an increased bioavailability, fewer reported side effects and a reduced need for regular dosage. Furthermore, the use of nanoparticles facilitates a targeted delivery of the drug which may omit the pain that is caused by the use of implants (5). Lina is also thought to be effective in Type 3 Diabetes which causes Alzheimer’s disease. As dementia can lead to forgetting to take medications regularly, the ED Lina, which is taken once weekly, may be a suitable option. This new formulation is being considered for its better safety profile compared to other antidiabetics and its effectiveness in controlling HbA1C both as monotherapy and in combination therapy (4,6) ---Continue

SSCFormer: Revisiting ConvNet-Transformer Hybrid Framework From Scale-Wise and Spatial-Channel-Aware Perspectives for Volumetric Medical Image Segmentation.

Accurate and robust medical image segmentation is crucial for assisting disease diagnosis, making treatment plan, and monitoring disease progression. Adaptive to different scale variations and regions of interest is essential for high accuracy in automatic segmentation methods. Existing methods based on the U-shaped architecture respectively tackling intra- and inter-scale problem with a hierarchical encoder, however, are restricted by the scope of multi-scale modeling. In addition, global attention and scaling attention in regions of interest have not been appropriately adopted, especially for the salient features. To address these two issues, we propose a ConvNet-Transformer hybrid framework named SSCFormer for accurate and versatile medical image segmentation. The intra-scale ResInception and inter-scale transformer bridge are designed to collaboratively capture the intra- and inter-scale features, facilitating the interaction of small-scale disparity information at a single stage with large-scale from multiple stages. Global attention and scaling attention are cleverly integrated from a spatial-channel-aware perspective. The proposed SSCFormer is tested on four different medical image segmentation tasks. Comprehensive experimental results show that SSCFormer outperforms the current state-of-the-art methods.

Does dynamic navigation assisted student training improve the accuracy of dental implant placement by postgraduate dental students: an in vitro study

ObjectivesTo assess the accuracy of implant placement in models and satisfaction in dynamic navigation assisted postgraduate dental students training.MethodsPostgraduate dental students who had at least one year of dental clinical practice with no experience in dental implant surgeries were included. Students were instructed to make treatment plans in the dynamic navigation system. Each student placed two maxillary right incisors, using freehand approach at first and then under dynamic navigation. The implant position was compared with treatment plan. Factors influencing the accuracy of implants placed under dynamic navigation were analyzed. Student acceptance towards the training and use of dynamic navigation was recorded using a questionnaire.ResultsA total of 21 students placed 42 implants. For freehand implant placement, the median entry point deviation, apex point deviation, and implant axis deviation was 3.79 mm, 4.32 mm, and 10.08°. For dynamic guided implant placement, the median entry point deviation, apex point deviation, and implant axis deviation was 1.29 mm, 1.25 mm, and 4.89° (p < 0.001). The accuracy of dynamic guided implant was not influenced by student gender or familiarity with computer games. All students were satisfied with the training.ConclusionsDynamic navigation system assisted students in improving the accuracy of implant placement and was well accepted by students.

Radiotherapy Planning in Synchronous Bilateral Breast Cancer Irradiation: A Dosimetric Study

Background: The large radiation field and surrounding normal structures make treatment planning and dose delivery of synchronous bilateral breast cancer (SBBC) much more difficult than it is for unilateral breast cancer. Intensity-modulated radiation therapy (IMRT) or volumetric-modulated arc therapy (VMAT) can produce acceptable normal tissue sparing while improving target dose coverage compared to 3D-CRT. With this context in mind, we carried out a study to examine the dosimetric variations of IMRT and VMAT techniques using a single isocenter for planning cases of SBBC. Patients and methods: Five patients were considered for this study. All the patients had undergone bilateral mastectomy. Dose prescribed was 50 Gy in 25 fractions. VMAT and IMRT plans were created for each patient. All the plans made were mono-isocentric. Dosimetric data of the target and organs at risk (OAR) were compared. Results: There is a trend towards better PTV coverage using VMAT compared to IMRT (V95 IMRT=94.8720, V95 VMAT=95.8740; P=0.316). VMAT plans significantly improved the dose homogeneity as V105% decreased from 2.886% to 0.312% using VMAT plans (P=0.001). IMRT plans showed trend towards higher lung Dmean and V20Gy than VMAT plans. The irradiation dose to the heart was significantly higher in the IMRT plan than VMAT plan, resulting in Dmean of 15.836 Gy vs 13.580 Gy (P=0.026), V25Gy of 16.498% vs 13.832% (P=0.046) and V30 Gy of 9.774% vs 7.022% (P= 0.043). Conclusion: The single isocentric VMAT technique can be performed conveniently in SBBC. It improves target volume coverage with optimal normal tissue sparing. It is a feasible approach while planning synchronous bilateral breast irradiation.&#x0D;

Prognostic Thresholds of Mitotic Count and Ki-67 Labeling Index for Recurrence and Survival in Lung Atypical Carcinoids

Atypical carcinoid (AC) is a rare neuroendocrine neoplasm of the lung, which exhibits a varying malignant potential. In this study, we aimed to identify the prognostic thresholds of the mitotic count and Ki-67 labeling index for recurrence and survival in AC. We retrospectively reviewed 78 patients who had been radically resected for AC and calculated said thresholds using time-dependent receiver operating characteristic curves and the Youden index. We then dichotomized the patients into groups of above or below these thresholds and estimated the cumulative incidences of the groups using the Aalen–Johansen estimator. We compared the groups using univariable and multivariable Fine–Gray subdistribution hazard models. Our findings show that more patients recurred and died from this disease if their mitotic count exceeded three and four mitoses per 2 mm2, respectively, or if their Ki-67 labeling index exceeded 14% and 11%, respectively. Both thresholds independently predicted survival (p &lt; 0.001 and p = 0.015, respectively). These thresholds may serve as a valuable tool for clinicians and researchers in making treatment plans and predicting outcomes for patients with AC.

A postpartum functional assessment tool for women based on the international classification of functioning, disability and health

BackgroundPostpartum dysfunctions and complications can occur in women. However, functional assessment should be conducted to make treatment plans before any intervention is implemented. In this context, the International Classification of Functioning, Disability and Health (ICF) may be a useful tool for women postpartum to document functional data and set rehabilitation goals. The purpose of this study was to determine the corresponding domains that should be considered in the evaluation of women’s postpartum functioning based on the International Classification of Functioning, Disability and Health (ICF) model using the Delphi method.MethodsFifteen domestic experts were invited to conduct two rounds of expert consensus survey on the ICF-based postpartum functional assessment category pool obtained through literature retrieval, clinical investigation, and reference to relevant literature. The sample was medical staff with professional knowledge of women’s health. The opinions of experts were summarized, and the positive coefficient, authority coefficient and coordination degree of experts were calculated.ResultsA total of 15 domestic experts participated in this expert consensus. Through two rounds of a questionnaire survey, 69 items were finally selected to form the ICF-based postpartum functional assessment tool for women. The items included 32 items of body function, 12 items of body structure, 17 items of activity and participation, and 8 items of environmental factors. In addition, we identified 8 items of personal factors. The expert positive coefficients of the two rounds of expert consensus were both 100%, the authority coefficient was 0.789, and the coefficient of variation was between 0.09 to 0.31.ConclusionA postpartum functional assessment tool for women based on the ICF model was constructed based on the Delphi method, which can provide more comprehensive health management and life intervention for postpartum women.Trial registrationThe Registration number of the Chinese Clinical Trial Registry is ChiCTR2200066163, 25/11/2022.

Breast Cancer Prediction: A Fusion of Genetic Algorithm, Chemical Reaction Optimization, and Machine Learning Techniques

Breast cancer is currently one of the most prevalent cancers affecting women globally. Uncontrolled growth and division of breast cells lead to the formation of tumors, marking the onset of breast cancer. Predicting breast cancer is essential for early detection, making treatment plans, and implementing preventive measures, ultimately improving patient outcomes and reducing mortality rates. In recent years, numerous studies have been published to predict breast cancer where researchers use a variety of methods. Most investigations have been conducted using narrow and specific datasets, often resulting in a lack of accuracy. Such methods may not be suitable for clinical use. The study aims to address the limitations of existing models in terms of robustness and generalization across diverse datasets. In our study, we employed two metaheuristic algorithms, namely, genetic algorithm (GA) and chemical reaction optimization (CRO) with machine learning techniques, including support vector machine (SVM), decision tree, random forest, and XGBoost. GA and CRO are used to optimize the feature selection process. It enables machine learning algorithms to predict more accurately. Experiments were conducted on three datasets, namely, Wisconsin Breast Cancer (WBC), Breast Cancer‐the University of California, Irvine (BC‐UCI), and Breast Cancer Coimbra (BCC) datasets. The datasets contain 569, 286, and 116 instances, respectively. The classifiers with optimized features consistently outperformed the classifiers without feature optimization in terms of accuracy, precision, recall, specificity, and F1 score. Among the compared methods published recently, our method attained the highest accuracies of 99.64% in the WBC dataset and 98% in the BCC dataset, as well as the second highest accuracy of 99.12% in the BC‐UCI dataset. Comparative analysis demonstrated the superiority of our approach over existing methods.

A Conceptual Study on Rajyakshma through Ayurveda

One of the Asthamahagadas described by Acharya Charaka and known as the "king of the disease" is Rajyakshma. Due to its multisystem involvement and syndromic expression, it has traditionally been difficult to identify and treat. Therefore, it is crucial to fully comprehend Nidana and Samprapti prior to making treatment plans. Rajayakshma has been linked to numerous immunodeficiency syndromes. However, a closer look at the symptoms reveals that it more closely resembles a multisystem respiratory disease. As well as being classified as an Aupsargika Vyadhi, the ailment also had a number of predisposing elements or Chaturvidha Nidana. Tridoshas and Sapta Dhatu are induced as a result of Nidana indulgence. In the present period, pulmonary tuberculosis can be linked to Rajyakshma, which affects the Pranavaha Srotasa. Although the pathophysiology of Rajayakshma and pulmonary tuberculosis differ, their clinical profiles are remarkably similar. Western medicine focuses primarily on infectious diseases, how they spread, various diagnostic techniques, and WHO-recommended antibiotics. The paper's main goals are to fully convey the fundamental ideas of Rajayakshma's Hetu and Samprapti and how they affect the Pranavaha Srotasa in relation to pulmonary tuberculosis. Rajayakshma is considered the king of all diseases. It is formed with two words: Raja (king) and Yakshma (decay), which means fraying condition of huge magnitude. The symptoms of Rajayakshma include Sahasa (extreme tension and strain), Vegasandharana (restraining natural impulses), Kshaya (decreasing Dhathu), and Vishamashana (resisting natural urges). It is a Shosha that Madhyama Rogamarga Vyadhi has manifested. The Tridosha and the Sapta Dhatu are impacted by the emergence of Ekadasha Roopa. The Nidana and the Samprapti are given a lot of attention in the classics of Ayurveda, since they are crucial to comprehending Chikitsa. Chikitsa is Nidana Parivarjana and Samprapti Vighatana; it is nothing. Rajayakshma's knowledge was compiled by exhaustively searching the primary Ayurvedic literature. Rajayakshma is a rare illness, and the disease hierarchy is as described by Sahasajanaya Rajayakshma and Vega Sandarana. Janya Rajayakshma, Kshaya Janya Rajayakshma, and Vishamashana Janya Rajayakshma is one of the four categories involved in Nidana. In modern medicine, Rajyakshma may correlate with pulmonary tuberculosis. Though there is a difference in the pathogenesis of tuberculosis and Rajyakshma, the clinical picture of both is quite similar.

Using a CT-based scale to evaluate disease extension and the resectability of locally advanced thyroid cancer.

To establish a computed tomography (CT)-based scale to evaluate the resectability of locally advanced thyroid cancer. This twin-centre retrospective study included 95 locally advanced thyroid cancer patients from the 1st centre as the training cohort and 31 patients from the 2nd centre as the testing cohort, who were categorised into the resectable and unresectable groups. Three radiologists scored the CT scans of each patient by evaluating the extension to the recurrent laryngeal nerve (RLN), trachea, oesophagus, artery, vein, soft tissue, and larynx. A 14-score scale (including all comprised structures) and a 12-score scale (excluding larynx) were developed. Receiver-operating characteristic (ROC) analysis was used to evaluate the performance of the scales. Stratified fivefold cross-validation and external verification were used to validate the scale. In the training cohort, compromised RLN (p < 0.001), trachea (p = 0.001), oesophagus (p = 0.002), artery (p < 0.001), vein (p = 0.005), and soft tissue (p < 0.001) were predictors for unresectability, while compromised larynx (p = 0.283) was not. The 12-score scale (AUC = 0.882, 95%CI: 0.812-0.952) was not inferior to the 14-score scale (AUC = 0.891, 95%CI: 0.823-0.960). In subgroup analysis, the AUCs of the 12-score scale were 0.826 for treatment-naïve patients and 0.976 for patients with prior surgery. The 12-score scale was further validated with a fivefold cross-validation analysis, with an overall accuracy of 78.9-89.4%. Finally, external validation using the testing cohort showed an AUC of 0.875. The researchers built a CT-based 12-score scale to evaluate the resectability of locally advanced thyroid cancer. Validation with a larger sample size is required to confirm the efficacy of the scale. This 12-score CT scale would help clinicians evaluate the resectability of locally advanced thyroid cancer. • The researchers built a 12-score CT scale (including recurrent laryngeal nerve, trachea, oesophagus, artery, vein, and soft tissue) to evaluate the resectability of locally advanced thyroid cancer. • This scale has the potential to help clinicians make treatment plans for locally advanced thyroid cancer.

Application value of ultrasound TIC curve in the evaluation of ablation effect of liver tumors

ObjectiveTo evaluate the efficacy of ablation of hepatocellular carcinoma (HCC) and the diagnostic value of new intrahepatic nodules after ablation by studying the time-intensity curve (TIC) of contrast-enhanced ultrasound (CEUS), Maximize the survival time and quality of life of patients.so as to make treatment plans as early as possible and extend the survival time and quality of life of patients to the greatest extent. MethodsA total of 59 nodules were selected from 42 clinically confirmed HCC patients who planned to undergo ultrasound-guided microwave ablation in our hospital from October 2021 to October 2022. Among them, 31 were males and 11 were females, aged 38–72 years, with an average age of 56.7 ± 9.6 years. For all lesions included in the study, CEUS examination was performed before ablation and TIC was fitted. The patients were examined by routine B-ultrasound, CEUS alone, CEUS combined with TIC at 1 month, 3 months and 6 months after ablation. At the same time, CEUS alone and CEUS combined with TIC were performed for all new nodules found in the liver under conventional B-ultrasonography. The diagnostic efficacy of CEUS alone and CEUS combined with TIC on ablation and new nodules in the liver were compared and analyzed. At least two enhanced imaging tests (CEUS, enhanced CT, or enhanced MRI) plus relevant laboratory tests were used as the gold standard. Meanwhile, the quantitative parameters of recurrent lesions and TIC nodules in liver were compared with the surrounding normal tissues before and after surgery. Results(1) When evaluating the efficacy of ultrasound-guided microwave ablation, the specificity, accuracy and positive prediction rate of CEUS combined with TIC diagnosis group were lower than those of CEUS alone, and the difference was statistically significant; (2) The sensitivity, accuracy and negative predictive rate of CEUS combined with TIC in the diagnosis of new intrahepatic nodules after intrahepatic ablation were higher than those of CEUS alone, but the difference was not statistically significant; (3)The TIC peak time of primary hepatocellular carcinoma (HCC), local recurrence of HCC after microwave ablation and intrahepatic recurrence of HCC after ablation was shorter than the surrounding normal liver parenchyma, and the difference was statistically significant, while the slope of curve rise was larger than the surrounding normal liver parenchyma, and the difference was statistically significant.) ConclusionTIC is not suitable for evaluating the efficacy of ultrasound-guided microwave ablation for primary hepatocellular carcinoma, as TIC can significantly increase the false positive rate.For the diagnosis of new nodules in liver after microwave therapy of hepatocellular carcinoma, CEUS combined with TIC method is suitable, which can improve the diagnostic efficiency of the disease. At the same time, it was found in our study that the peak time of primary hepatocellular carcinoma, local recurrent liver cancer foci after microwave ablation, and intrahepatic recurrent liver cancer after ablation was less than that of surrounding normal liver parenchyma, and the upward slope of the curve was greater than that of surrounding normal liver parenchyma. Therefore, in the CEUS diagnosis of intrahepatic space-occupying lesions, the method of quantitative parameters can be adopted to quantitatively evaluate the nature of the lesions in order to obtain more accurate results.

Evaluation of grouped capsule network for intracranial hemorrhage segmentation in CT scans

Intracranial hemorrhage is a cerebral vascular disease with high mortality. Automotive diagnosing and segmentation of intracranial hemorrhage in Computed Tomography (CT) could assist the neurosurgeon in making treatment plans, which improves the survival rate. In this paper, we design a grouped capsule network named GroupCapsNet to segment the hemorrhage region from a Non-contract CT scan. In grouped capsule network, we constrain the prediction capsules for output capsules produced from different groups of input capsules with various types in each layer. This method can reduce the number of intermediate prediction capsules and accelerate the capsule network. In addition, we modify the squashing function to further accelerate the forward procedure without sacrificing its performance. We evaluate our proposed method with a collected dataset containing 210 intracranial hemorrhage CT scan slices. In experiments, our proposed method achieves competitive results in intracranial hemorrhage area segmentation compared to the existing methods.

Analysis of Depression and Working Memory Effectiveness of &amp;apos;Active Health Mini Program&amp;apos;

Parents of special children will encounter many difficulties and pressures in the process of raising special children, which will cause discomfort in mental health, such as depression. Depression is usually accompanied by cognitive decline, and its working memory will be damaged. The existing tools are cumbersome for the test of depression and working memory capacity. For general hospitals, rapid and convenient diagnosis of patients ' depression and working memory is of great practical significance for doctors to make treatment plans. Therefore, this experiment first tested the applicability of Zung self rating depression scale (SDS) in parents of special children, and simplified the SDS on this basis. Secondly, the effectiveness of depression and working memory tasks in active health mini-programs will be investigated. In this experiment, 125 parents were recruited. (1) The internal consistency coefficient of SDS was 0.83; (2) Split-half reliability, Spearman-Brown correction coefficient was 0.72; (3) Factor analysis, According to the Ksiser method, five factors were obtained by the criterion of eigenvalue ≥ 1, the characteristic roots were 5.38, 3.07, 1.72, 1.12 and 1.01, respectively, which explained 22.59%, 15.82%, 8.05%, 7.83% and 7.18% of the variation values, and the cumulative contribution rate was 61.47%, Four factors were obtained by reclassifying the factors with too few variables; (4) There was a significant positive correlation between the small program depression score and the SDS, r = 0.42, P < 0.001; (5) There was a significant positive correlation between small program working memory name and memory color, r = 0.25, P < 0.05; (6) There was a significant positive correlation between the correct number of small program memory items and the position 1 of Bcak corsi knock task (BCT), r = 0.49, P < 0.01; (7) There was a significant negative correlation between the correct number of small program memory items and the position 2 of BCT, r = -0.56, P < 0.01; (8) There was a significant positive correlation between the two memory positions of BCT, r = -0.81, P < 0.01. The results showed that although it did not fully reflect the patient's overall depression or working memory status, the self-assessment of depression and working memory in the small program can reflect the patient's depression and cognitive impairment. It is an effective and simple tool.

Development of Prediction Model Using Machine-Learning Algorithms for Nonsteroidal Anti-inflammatory Drug-Induced Gastric Ulcer in Osteoarthritis Patients: Retrospective Cohort Study of a Nationwide South Korean Cohort.

Nonsteroidal anti-inflammatory drugs (NSAID) are currently among the most prescribed medications worldwide to relieve pain and reduce inflammation, especially in patients suffering osteoarthritis (OA). However, NSAIDs are known to have adverse effects on the gastrointestinal system. If a gastric ulcer occurs, planned OA treatment needs to be changed, incurring additional treatment costs and causing discomfort for both patients and clinicians. Therefore, it is necessary to create a gastric ulcer prediction model that can reflect the detailed health status of each individual and to use it when making treatment plans. Using sample cohort data from 2008 to 2013 from the National Health Insurance Service in South Korea, we developed a prediction model for NSAID-induced gastric ulcers using machine-learning algorithms and investigated new risk factors associated with medication and comorbidities. The population of the study consisted of 30,808 patients with OA who were treated with NSAIDs between 2008 and 2013. After a 2-year follow-up, these patients were divided into two groups: without gastric ulcer (n=29,579) and with gastric ulcer (n=1,229). Five machine-learning algorithms were used to develop the prediction model, and a gradient boosting machine (GBM) was selected as the model with the best performance (area under the curve, 0.896; 95% confidence interval, 0.883-0.909). The GBM identified 5 medications (loxoprofen, aceclofenac, talniflumate, meloxicam, and dexibuprofen) and 2 comorbidities (acute upper respiratory tract infection [AURI] and gastroesophageal reflux disease) as important features. AURI did not have a dose-response relationship, so it could not be interpreted as a significant risk factor even though it was initially detected as an important feature and improved the prediction performance. We obtained a prediction model for NSAID-induced gastric ulcers using the GBM method. Since personal prescription period and the severity of comorbidities were considered numerically, individual patients' risk could be well reflected. The prediction model showed high performance and interpretability, so it is meaningful to both clinicians and NSAID users.

737. Oral Antibiotic Stepdown Therapy for Uncomplicated Streptococcal

Abstract Background Streptococcus species are known pathogens in bloodstream infections (BSIs). Traditionally, BSIs are managed with intravenous (IV) antibiotics, however there is growing literature supporting oral (PO) antibiotics in BSIs as well as other invasive infections. Advantages to PO therapies include shortened hospital stay, reduced treatment costs, and avoidance of line-related complications. Currently, there is a paucity of data supporting the use of PO antibiotics in streptococcal BSIs. Methods This retrospective cohort study evaluated patients with streptococcal bacteremia between September 2019 to September 2021. Patients 18 and older were included if they had at least one positive blood culture for any Streptococcus species and excluded if BSI was polymicrobial, or treatment was for complicated BSI, identified by receipt of targeted therapy for ≥ 16 days, or source being endocarditis, osteomyelitis, or meningitis. Clinical outcomes were compared between patients who completed treatment with IV antibiotics verses those who completed with an PO stepdown regimen. The primary endpoint was clinical failure, which was a composite endpoint defined as BSI recurrence with the same pathogen and infection-related readmission within 30 days from completion of antibiotics. Results A total of 158 patients were included, with 77 (49%) receiving a full course of IV antibiotics and 81 (51%) receiving an PO antibiotic stepdown regimen. Clinical failure was not different between the IV antibiotics group versus the PO stepdown group, respectively (16% vs. 15%, odds ratio [OR] = 0.94; 95% confidence interval [CI], 0.40 to 2.25). No differences were observed in 30-day all-cause mortality. Patients that received PO antibiotic stepdown therapy had a significantly shorter hospital length of stay by 6 days (6 versus 12 days, p&amp;lt; 0.01). Conclusion Our results suggest that clinical cure with an PO stepdown regimen for uncomplicated streptococcal BSIs is comparable to IV antibiotics. The benefit of comparable efficacy in the setting of reduced length of stay and avoidance of central line placement for outpatient IV antibiotics should be considered when making treatment plans for patients with uncomplicated streptococcal BSIs. Disclosures All Authors: No reported disclosures.

National survey of amblyopia treatment in Japan: comparison with amblyopia treatment study results of the pediatric eye disease investigator group.

To investigate the treatment policy for amblyopia in Japan as of 2017 through a survey of multiple facilities and to compare the findings with those obtained by the Amblyopia Treatment Study (ATS) of the Pediatric Eye Disease Investigator Group. Questionnaire survey study. A questionnaire was sent to 181 facilities where patients with amblyopia are being treated. The outcomes of the present survey were compared with the results of the ATS study, and the coincidence rates were evaluated. The questionnaire response rate was 68.0%. The treatment plan that showed the highest agreement between the outcomes of the ATS study and the present study was whether or not treatment was to be given to patients aged 10-15years who had received no previous treatment; 90% of the facilities answered that they would provide treatment to such patients as well. The next highest agreement was the future treatment of amblyopia with stable visual acuity in the affected eye; 82.6% of the facilities responded that they would reduce the occlusion time. On the other hand, the lowest agreement rate was the follow-up period of the refractive correction for moderate anisometropic amblyopia. The ATS showed "4 months," whereas most of the facilities in the present survey replied "3 months." The agreement rate was 10.8%. The amblyopia treatment in Japan survey did not always agree with the research results of the ATS. Japanese ophthalmologists tend to make treatment plans for amblyopia according to their clinical experience.

Three‐dimensional dental image segmentation and classification using deep learning with tunicate swarm algorithm

AbstractDentistry frequently makes use of intraoral scanning technologies to digitally acquire the three‐dimensional (3D) geometry of teeth. In recent times, dental clinics over the globe utilize used computer aided diagnosis (CAD) models to make treatment plans, for example, orthodontics. Orthodontic CAD system acts as a vital part of the advanced dentistry field. A 3D dental model, computed by patient impression, as input and aids dentist in the extraction, moving, deletion, and rearranging of teeth to simulate treatment output. Tooth segmentation and labelling is the basic and foremost element of the CAD model which needs to be addressed. Automated segmentation and classification of 3D dental images using advanced machine learning and deep learning (DL) models become essential. This article introduces a new 3D dental image segmentation and classification using DL with tunicate swarm algorithm (3DDISC‐DLTSA) model. The major intention of the 3DDISC‐DLTSA system is to segment the tooth model and identify seven distinct tooth types. To accomplish this, the presented 3DDISC‐DLTSA model performs image pre‐processing in two stages namely image filtering and U‐Net segmentation. In addition, the 3DDISC‐DLTSA model derives DenseNet‐169 model for feature extraction purposes. For the recognition and classification of tooth type, the TSA based hyperparameter tuning process is carried out which helps to accomplish maximum classification performance. A wide range of experimental analyses is performed and the outcomes are inspected under many aspects. On dataset‐1, 3DDISC‐DLTSA model accuracy rose by 96.67%. On dataset‐3, 3DDISC‐DLTSA model accuracy rose by 97.48% and algorithm accuracy by 97.35%. The 3DDISC‐DLTSA model outperformed more modern models, according to the comparative investigation.

STANDARD-DEVIATION BASED CONFORMITY INDEX FOR EVALUATING TREATMENT PLAN OF INTENSITY MODULATED RADIOTHERAPY IN LUNG CANCER.

This paper attempts to find a new conformity index (CI) calculation method with slice and angle information for evaluating lung cancer radiation treatment plan. A total of 20 lung cancer patients in 2016-2019 were selected. Treatment plans were made for each patient. Parameters used in the process of making treatment plans were set the same. The CI and the standard-deviation based CI (SDCI) that contains angle and slice information were calculated. Comparison of results calculated with SDCI and CI were made. The results of the two methods for the patients showed the same trend. Different shapes of simulated dose distribution line shows SDCI can provide more detail information about the target area. Special shapes of simulated dose distribution line for SDCI showed inaccuracy in angle information. The parameter SDCI has more advantage towards the traditional CI for it can provide angle and slice information. However, more angles need to be calculated.