[Economic evaluation of Annao Pills combined with antihypertensive drugs in treatment of primary hypertension: a study based on decision tree model].

The purpose of this study was to evaluate the economics of Annao Pills combined with antihypertensive drugs in the treatment of primary hypertension in the Chinese medical setting. TreeAge pro 2018 was used for cost-effect analysis and sensitivity analysis of the two treatment regimens. The intervention time of the simulation model was 2 weeks. The cost parameters were derived from Yaozhi.com, and the effect parameters were based on Meta-analysis of randomized controlled trial(RCT) involving Annao Pills. The experimental group was treated with Annao Pills combined with anti-hypertensive drugs(nifedipine controlled-release tablets + losartan potassium tablets), and the control group was treated with anti-hypertensive drugs(nifedipine controlled-release tablets + losartan potassium tablets). The basic analysis showed that the incremental cost-effect ratio(ICER) of the two groups was 2 678.67 yuan, which was less than 7.26% of the per capita disposable income in 2022. That is, compared with anti-hypertensive drugs alone, Annao Pills combined with antihypertensive drugs cost 2 678.67 yuan more for each additional patient with primary hypertension. The results of sensitivity analysis verified the robustness of the basic analysis results. The probability sensitivity results showed that when the patient's personal willingness to pay the price was higher than 2 650 yuan, the probability of the regimen in the experimental group was higher, which was consistent with the results of the basic analysis. In conclusion, when the price was higher than 2 650 yuan, Annao Pills combined with anti-hypertensive drugs was more economical than anti-hypertensive drugs alone in terms of improving the response rate of the patients with primary hypertension.

Classified diagnosis and treatment scheme of oral cosmetic restoration based on aesthetic analysis (part â ): basic concept, decision tree and clinical pathway.

At present, the commonly used clinical protocols of oral comestic restoration are mostly based on the aesthetic indicators proposed by Western developed countries (referred to as Western aesthetics). Mechanically copying the Western aesthetic scheme, ignoring the difference between it and the Chinese oral aesthetic indicators (referred to as Chinese aesthetics), is unable to effectively support personalized cosmetic restoration diagnosis and treatment. In addition, new technologies and new solutions for cosmetic restoration, which are developing rapidly in recent years, are emerging one after another, but many popular concepts are confusing and lack of proper hierarchical diagnosis and treatment norms, and there is indeed an urgent need for discussion and clarity. From the perspective of serving clinical application, this paper discusses the deficiencies of the Chinese translation of the word "aesthetics", the diffe-rence and connection between aesthetics and cosmetology, and the relationship between cosmetic restoration and fixed restoration. It also discusses the difference between anterior teeth, esthetic zone and exposed zone, the diagnostic and therapeutic value of oral aesthetic analysis, as well as the application methods of desensitization, suggestion, and other therapies in difficult oral cosmetic restoration cases. We further introduce the decision tree and the clinical pathway for restoration and reconstruction of teeth in exposed zone guided by aesthetic analysis, and introduce the clinical process of aesthetic analysis and evaluation, the clinical triclassification of oral cosmetic restoration, and the corresponding clinical classification diagnosis and treatment points.

Reducing abnormal expenses in national health insurance based on a control chart and decision tree-driven define, measure, analyze, improve and control process.

This study examined the cost of medical insurance for "sepsis" treatment in Taiwan. We applied statistical tests, cost control charts, and C5.0 decision trees using the define, measure, analyze, improve and control (DMAIC) process to mine data on Diagnosis-Related Groups (DRGs) and clinics that reported expense anomalies and disposal costs. Analyzing 353 valid samples (application fees) from four DRGs, 70 clinics, and 15 input variables, abnormalities in application fees for adults (age ≧18 years old) with comorbidities or complications was significant (95% confidence interval) in one DRG and nine clinics. Four input variables (ward charge, treatment fee, laboratory fee, and pharmaceutical service charge) had a significant impact. Improvements or controls should be prioritized for three clinics (Nos. 49, 44, and 14) and two input variables (treatment and laboratory fees). This model can be replicated to ascertain excess medical expenditures and improve the efficiency of medical resource use.

Postoperative thyroglobulin as a yard-stick for radioiodine therapy: decision tree analysis in a European multicenter series of 1317 patients with differentiated thyroid cancer.

PURPOSE: An accurate postoperative assessment is pivotal to inform postoperative 131I treatment in patients with differentiated thyroid cancer (DTC). We developed a predictive model for post-treatment whole-body scintigraphy (PT-WBS) results (as a proxy for persistent disease) by adopting a decision tree model. METHODS: Age, sex, histology, T stage, N stage, risk classes, remnant estimation, TSH, and Tg were identified as potential predictors and were put into regression algorithm (conditional inference tree, ctree) to develop a risk stratification model for predicting the presence of metastases in PT-WBS. RESULTS: The lymph node (N) stage identified a partition of the population into two subgroups (N-positive vs N-negative). Among N-positive patients, a Tg value > 23.3 ng/mL conferred a 83% probability to have metastatic disease compared to those with lower Tg values. Additionally, N-negative patients were further substratified in three subgroups with different risk rates according to their Tg values. The model remained stable and reproducible in the iterative process of cross validation. CONCLUSIONS: We developed a simple and robust decision tree model able to provide reliable informations on the probability of persistent/metastatic DTC after surgery. These information may guide post-surgery 131I administration and select patients requiring curative rather than adjuvant 131I therapy schedules.

Variations in Radioiodine Therapy in Europe: Decision-Making after Total Thyroidectomy.

The role of radioiodine therapy (RIT) (used as ablation therapy or adjuvant therapy) following total thyroidectomy for differentiated thyroid cancer (DTC) changed. Major revisions of the American Thyroid Association (ATA) Guidelines in 2015 resulted in significant differences in treatment recommendations in comparison to the European Association of Nuclear Medicine (EANM) 2008 guidelines. Recently, we presented the effects on daily practice for RIT among Swiss Nuclear Medicine centres. We now performed a study at the European level and hypothesized that there is also considerable variability among European experts. We performed a decision-tree-based analysis of management strategies from all members of the EANM thyroid committee to map current practice among experts. We collected data on whether or not RIT is administered, on which criteria these decisions are based and collected details on treatment activities and patient preparation. Our study shows discrepancies for low-risk DTC, where "follow-up only" is recommended by some experts, while RIT with significant doses is used by other experts. E.g., for pT1b tumours without evidence of metastases, the level of agreement for the use of RIT is as low as 50%. If RIT is administered, activities of I-131 range from 1.1 GBq to 3.0 GBq. In other constellations (e.g., pT1a), experts diverge from current clinical guidelines as up to 75% administer RIT in certain cases. For intermediate and high-risk patients, RIT is generally recommended. However, dosing and treatment preparation (rhTSH vs. thyroid hormone withdrawal) vary distinctly. In comparison to the Swiss study, the general level of agreement is higher among the European experts. The recently proposed approach on the use of RIT, based on integrated post-surgery assessment (Martinique article) and results of ongoing prospective randomized studies are likely to reduce uncertainty in approaching RIT treatment. In certain constellations, consensus identified among European experts might be helpful in formulating future guidelines.

The RIFM approach to evaluating Natural Complex Substances (NCS).

The Research Institute for Fragrance Materials, Inc. (RIFM) has evaluated safety data for fragrance materials for 55 years. The safety assessment of Natural Complex Substances (NCS) is similar to that of discrete fragrance materials; all of the same endpoints are evaluated. A series of decision trees, reflecting advances in risk assessment approaches of mixtures and toxicological methodologies, follows a tiered approach for each endpoint using a 4-step process with testing only as a last resort: 1) evaluate available data on NCS; 2) verify whether the Threshold of Toxicological Concern (TTC) can be applied; 3) verify whether the NCS risk assessment can be achieved on a component basis; and 4) determine whether data must be generated. Using in silico tools, RIFM examined NCS similarities based on the plant part, processing, and composition of materials across 81 plant families to address data gaps. Data generated from the Creme RIFM Aggregate Exposure Model for over 900 fragrance NCS demonstrate that dermal exposure is the primary route of human exposure for NCS fragrance uses. Over a third of materials are below the most conservative TTC limits. This process aims to provide a comprehensive Safety Assessment of NCS used as a fragrance ingredient.

Approach to Obesity in the Older Population.

Until recently, weight loss in older obese people was feared because of ensuing muscle loss and frailty. Facing overall increasing longevity, high rates of obesity in older individuals (age ≥ 65 years) and a growing recognition of the health and functional cost of the number of obesity years, abetted by evidence that intentional weight loss in older obese people is safe, this approach is gradually, but not unanimously, being replaced by more active principles. Lifestyle interventions that include reduced but sufficient energy intake, age-adequate protein and micronutrient intake, coupled with aerobic and resistance exercise tailored to personal limitations, can induce weight loss with improvement in frailty indices. Sustained weight loss at this age can prevent or ameliorate diabetes. More active steps are controversial. The use of weight loss medications, particularly glucagon-like peptide-1 analogs (liraglutide as the first example), provides an additional treatment tier. Its safety and cardiovascular health benefits have been convincingly shown in older obese patients with type 2 diabetes mellitus. In our opinion, this option should not be denied to obese individuals with prediabetes or other obesity-related comorbidities based on age. Finally, many reports now provide evidence that bariatric surgery can be safely performed in older people as the last treatment tier. Risk-benefit issues should be considered with extreme care and disclosed to candidates. The selection process requires good presurgical functional status, individualized consideration of the sequels of obesity, and reliance on centers that are highly experienced in the surgical procedure as well as short-term and long-term subsequent comprehensive care and support.

Improving the ability of antimicrobial susceptibility tests to predict clinical outcome accurately: Adding metabolic evasion to the equation.

Antimicrobial susceptibility tests (AST) are based on the minimal inhibitory concentration (MIC), the method used worldwide to guide antimicrobial therapy. Despite its relevance in correctly predicting clinical outcome for most acute infections, this approach is misleading for multiple clinical cases in which pathogens do not grow rapidly, uniformly or with physical protection. This behaviour, named 'metabolic evasion' (ME), enables bacteria to survive antimicrobials. ME can result from different, and sometimes combined, bacterial mechanisms such as biofilms, intracellular growth, persisters or dormancy. We discuss how ME can influence the MIC-based probability of target attainment. We identify clinical cases in which this approach is undermined by ME and propose a new approach that takes ME into account in order to improve patient management and the evaluation of innovative drugs.

Cost-effectiveness of Atezolizumab Plus Bevacizumab vs Sorafenib as First-Line Treatment of Unresectable Hepatocellular Carcinoma.

Importance: Treatment with atezolizumab plus bevacizumab may prolong overall survival among patients with unresectable hepatocellular carcinoma. However, to our knowledge, the cost-effectiveness of using this high-priced therapy for this indication is currently unknown. Objective: To evaluate the cost-effectiveness of atezolizumab plus bevacizumab to treat unresectable hepatocellular carcinoma from the US payer perspective. Design, Setting, and Participants: This economic evaluation used a partitioned survival model consisting of 3 discrete health states to assess the cost-effectiveness of treatment of hepatocellular carcinoma with atezolizumab plus bevacizumab vs sorafenib. The characteristics of patients in the model were similar to patients in a phase 3, open-label randomized clinical trial (IMbrave150) who had unresectable hepatocellular carcinoma and had not previously received systemic treatment. Key clinical data were generated from the IMbrave150 trial conducted between March 15, 2018, and January 30, 2019, and cost and health preference data were collected from the literature. Main Outcomes and Measures: Costs, quality-adjusted life-years (QALYs), incremental cost-utility ratios, incremental net health benefits, and incremental net monetary benefits were calculated for the 2 treatment strategies. Subgroup, 1-way sensitivity, and probabilistic sensitivity analyses were performed. Results: Treatment of hepatocellular carcinoma with atezolizumab plus bevacizumab added 0.530 QALYs and resulted in an incremental cost of $89 807 compared with sorafenib therapy, which had an incremental cost-utility ratio of $169 223 per QALY gained. The incremental net health benefit was -0.068 QALYs, and the incremental net monetary benefit was -$10 202 at a willingness-to-pay threshold of $150 000/QALY. The probabilistic sensitivity analysis indicated that treatment with atezolizumab plus bevacizumab achieved a 35% probability of cost-effectiveness at a threshold of $150 000/QALY. One-way sensitivity analysis revealed that the results were most sensitive to the hazard ratio of overall survival. The subgroup analysis found that treatment with atezolizumab plus bevacizumab was associated with preferred incremental net health benefits in several subgroups, including patients with hepatitis B and C. Conclusions and Relevance: Atezolizumab plus bevacizumab treatment is unlikely to be a cost-effective option compared with sorafenib for patients with unresectable hepatocellular carcinoma. Reducing the prices of atezolizumab and bevacizumab may improve cost-effectiveness. The economic outcomes also may be improved by tailoring treatments based on individual patient factors.

Modeling of diagnosis for metabolic syndrome by integrating symptoms into physiochemical indexes.

BACKGROUND: Metabolic syndrome (MS) is a major global health concern comprising a cluster of co-occurring conditions that increase the risk of heart disease, stroke and type 2 diabetes. MS is usually diagnosed using a combination of physiochemical indexes (such as BMI, abdominal circumference and blood pressure) but largely ignores clinical symptoms when investigating prevention and treatment of the disease. Exploring predictors of MS using multiple diagnostic indicators may improve early diagnosis and treatment of MS. Traditional Chinese medicine (TCM) attaches importance to the etiology of disease symptoms and indications using four diagnostic methods, which have long been used to treat metabolic disease. Therefore, in this study, we aimed to develop predictive indicators for MS using both physiochemical indexes and TCM methods. METHODS: Clinical information (including both physiochemical and TCM indexes) was obtained from a cohort of 586 individuals across 4 hospitals in China, comprising 136 healthy controls and 450 MS cases. Using this cohort, we compared three classic machine learning methods: decision tree (DT), support vector machine (SVM) and random forest (RF) towards MS diagnosis using physiochemical and TCM indexes, with the best model selected by comparing the accuracy, specificity and sensitivity of the three models. In parallel, the best proportional partition of the training data to the test data was confirmed by observing the changes in evaluation indexes using each model. Next, three subsets containing different categories of variables (including both TCM and physicochemical indexes combined - termed the "fused indexes", only physicochemical indexes, and TCM indexes only) were compared and analyzed using the best performing model and optimum training to test data proportion. Next, the best subset was selected through comprehensive comparative analysis, and then the important prediction variables were selected according to their weight. RESULTS: When comparing the three models, we found that the RF model had the highest average accuracy (average 0.942, 95%CI [0.925, 0.958]) and sensitivity (average 0.993, 95%CI [0.990, 0.996]). Besides, when the training set accounted for 80% of the cohort data, the specificity got the best value and the accuracy and sensitivity were also very high in RF model. In view of the performance of the three different subsets, the prediction accuracy and sensitivity of models analyzing the fused indexes and only physicochemical indexes remained at a high level. Further, the mean value of specificity of the model using fused indexes was 0.916, which was significantly higher than the model with only physicochemical indexes (average 0.822) and the model with only TCM indexes (average 0.403). Based on the RF model and data allocation ratio (8:2), we further extracted the top 20 most significant variables from the fused indexes, which included 14 physicochemical indexes and 6 TCM indexes including wiry pulse, chest tightness, spontaneous perspiration, greasy tongue coating etc. CONCLUSION: Compared with SVM and DT models, the RF model showed the best performance, especially when the ratio of the training set to test set is 8:2. Compared with single predictive indexes, the model constructed by combining physiochemical indexes with TCM indexes (i.e. the fused indexes) exhibited better predictive ability. In addition to common physicochemical indexes, some TCM indexes, such as wiry pulse, chest tightness, spontaneous perspiration, greasy tongue coating, can also improve diagnosis of MS.

Trends in imaging utilization for small cell lung cancer: a decision tree analysis of the NCCN guidelines.

PURPOSE: To investigate the differences in small cell lung cancer (SCLC) diagnostic imaging utilization relative to National Comprehensive Cancer Network (NCCN) guidelines. METHODS: We retrospectively reviewed SCLC records at our institution between January 1, 2003 and August 1, 2019 (n = 529). Patients were grouped by extensive-stage versus limited-stage and diagnosis date. Clinical, CT, MRI, and nuclear imaging data was collected. Imaging utilization was compared using Student's t-test or Kruskal-Wallis-test/Wilcoxon-Rank-Sums test. Survival was compared using Log-rank-test and Kaplan-Meier-curves. RESULTS: SCLC patients had a median survival of 290 days. Extensive-stage patients with SCLC demonstrated an increase in emergency imaging utilization when diagnosed in 2011-2019 compared to 2003-2010 (CT abdomen/pelvis p < 0.001, CTA chest for pulmonary embolism p < 0.01, CT head p < 0.003). Limited-stage patients with SCLC demonstrated an increase in inpatient imaging utilization (CT abdomen/pelvis p < 0.04) and decreased total/outpatient imaging utilization (CT chest-abdomen-pelvis p < 0.05, CT head p < 0.003) when diagnosed in 2011-2019 compared to 2003-2010. All patients with SCLC had decreased average number of bone-scan studies when diagnosed in 2011-2019 compared to 2003-2010 (Extensive-stage p < 0.006, Limited-stage p < 0.0006). CONCLUSION: Imaging utilization trends in the management of patients with SCLC at our institution differed between 2003 and 2010 and 2011-2019 reflecting the changes in the NCCN guidelines.

Cost-effectiveness of Surgical Treatment Pathways for Prolapse.

OBJECTIVE: To evaluate the cost-effectiveness of surgical treatment pathways for apical prolapse. STUDY DESIGN: We constructed a stochastic Markov model to assess the cost-effectiveness of vaginal apical suspension, laparoscopic sacrocolpopexy, and robotic sacrocolpopexy. We modeled over 5 and 10 years, with 9 pathways accounting for up to 2 separate surgical repairs, recurrence of symptomatic apical prolapse, reoperation, and complications, including mesh excision. We calculated costs from the health care system's perspective. RESULTS: Over 5 years, compared with expectant management, all surgical treatment pathways cost less than the willingness-to-pay threshold of US $50,000 per quality adjusted life-years. However, among surgical treatments, all but 2 pathways were dominated. Of the remaining 2, laparoscopic sacrocolpopexy followed by vaginal repair for apical recurrence was not cost-effective compared with the vaginal-only approach (incremental cost-effectiveness ratio [ICER], >$500,000). Over 10 years, all but the same 2 pathways were dominated. However, starting with the laparoscopic approach in this case was more cost-effective with an ICER of US $6,176. If the laparoscopic approach was not available, starting with the robotic approach similarly became more cost-effective at 10 years (ICER, US $35,479). CONCLUSIONS: All minimally invasive surgical approaches for apical prolapse repair are cost-effective when compared with expectant management. Among surgical treatments, the vaginal-only approach is the only cost-effective option over 5 years. However, over a longer period, starting with a laparoscopic (or robotic) approach becomes cost-effective. These results help inform discussions regarding the surgical approach for prolapse.

May the best-sighted win? The relationship between visual function and performance in Para judo.

This study aimed to establish the optimal cut-off point(s) between classes in a new, evidence-based classification system for VI judo. We collected results from international VI judo competitions held between 2012 and 2018. Data on visual acuity (VA) and visual field (VF) measured during classification were obtained. Performance was determined by calculating a win ratio for each athlete. VA was significantly associated with judo performance (r = -.33, p <.001), VF was not (r =.30, p =.15). Decision tree analysis suggested to split the data into two groups with a VA cut-off of 2.5 logMAR units. Stability assessment using bootstrap sampling suggested a split into two groups, but showed considerable variability in the cut-off point between 2.0 and 3.5 logMAR. We conclude that to minimise the impact of impairment on the outcome of competition, VI judo should be split into two sport classes to separate partially sighted from functionally blind athletes. To establish an exact cut-off point and to decide if other measures of visual function need to be included, we argue for continued research efforts together with careful evaluation of research results from a multidisciplinary perspective.

Single amino acid utilization for bacterial categorization.

Despite great advancement in genetic typing, phenotyping is still an indispensable tool for categorization of bacteria. Certain amino acids may be essential for bacterial survival, growth, pathogenicity or toxin production, which prompts the idea that the intrinsic ability to utilize single amino acid under live-or-die situation could be a basis for differentiation of bacteria species. In this study, we determined the single amino acid consumption profiles of 7 bacterial species, and demonstrated that most bacteria have species-specific pattern of amino acid consumption. We also discovered that bacterial strains from different hosts, toxigenicity, and antibiotic-resistance presented distinct preference for certain amino acids. Taken altogether, the amino acid consumption profiles showed potential to be a novel tool complementary to study not only bacterial categorization but also biochemical characteristics of the bacteria such that its phenotyping can be used to uncover strategies for nutritional, pharmaceutical, taxonomic, and evolutionary aspects of bacterial researches.

Economic evaluation of a dedicated cardiac resynchronisation therapy preassessment clinic.

INTRODUCTION: Patient evaluation before cardiac resynchronisation therapy (CRT) remains heterogeneous across centres and it is suspected a proportion of patients with unfavourable characteristics proceed to implantation. We developed a unique CRT preassessment clinic (CRT PAC) to act as a final review for patients already considered for CRT. We hypothesised that this clinic would identify some patients unsuitable for CRT through updated investigations and review. The purpose of this analysis was to determine whether the CRT PAC led to savings for the National Health Service (NHS). METHODS: A decision tree model was made to evaluate two clinical pathways; (1) standard of care where all patients initially seen in an outpatient cardiology clinic proceeded directly to CRT and (2) management of patients in CRT PAC. RESULTS: 244 patients were reviewed in the CRT PAC; 184 patients were eligible to proceed directly for implantation and 48 patients did not meet consensus guidelines for CRT so were not implanted. Following CRT, 82.4% of patients had improvement in their clinical composite score and 57.7% had reduction in left ventricular end-systolic volume ≥15%. Using the decision tree model, by reviewing patients in the CRT PAC, the total savings for the NHS was £966 880. Taking into consideration the additional cost of the clinic and by applying this model structure throughout the NHS, the potential savings could be as much as £39 million. CONCLUSIONS: CRT PAC appropriately selects patients and leads to substantial savings for the NHS. Adopting this clinic across the NHS has the potential to save £39 million.

Influences of Daily Life Habits on Risk Factors of Stroke Based on Decision Tree and Correlation Matrix.

PURPOSE: To explore the influences of smoking, alcohol consumption, drinking tea, diet, sleep, and exercise on the risk of stroke and relationships among the factors, present corresponding knowledge-based rules, and provide a scientific basis for assessment and intervention of risk factors of stroke. METHODS: The decision tree C4.5 algorithm was optimized and utilized to establish a model for stroke risk assessment; then, the main risk factors of stroke (including hypertension, dyslipidemia, diabetes, atrial fibrillation, body mass index (BMI), history of stroke, family history of stroke, and transient ischemic attack (TIA)) and daily habits (e.g., smoking, alcohol consumption, drinking tea, diet, sleep, and exercise) were analyzed; corresponding knowledge-based rules were finally presented. Establish a correlation matrix of stroke risk factors and analyze the relationship between stroke risk factors. RESULTS: The accuracy of the established model for stroke risk assessment was 87.53%, and the kappa coefficient was 0.8344, which was superior to that of the random forest and Logistic algorithm. Additionally, 37 knowledge-based rules that can be used for prevention of risk factors of stroke were derived and verified. According to in-depth analysis of risk factors of stroke, the values of smoking, exercise, sleep, drinking tea, alcohol consumption, and diet were 6.00, 7.00, 8.67, 9.33, 10.00, 10.60, and 10.75, respectively, indicating that their influence on risk factors of stroke was reduced in turn; on the one hand, smoking and exercise were strongly associated with other risk factors of stroke; on the other hand, sleep, drinking tea, alcohol consumption, and diet were not firmly associated with other risk factors of stroke, and they were relatively tightly associated with smoking and exercise. CONCLUSIONS: Establishment of a model for stroke risk assessment, analysis of factors influencing risk factors of stroke, analysis of relationships among those factors, and derivation of knowledge-based rules are helpful for prevention and treatment of stroke.

[What to do in the event of a suspicion of analytical interference during an immunoassay?] / Conduite à tenir devant une suspicion d'interférence analytique lors d'un immunodosage.

Identifying analytical interference is a challenge for the medical biologist in providing advice to the prescriber. Indeed, these analytical interferences often have deleterious consequences on the care of patients. Understanding their mechanisms and mastering corrective procedures is essential to limit these management errors. Faced with the many questions from clinicians in current practice, we propose an algorithm for managing a sample when interference is suspected.

A Decision Tree Using Patient Characteristics to Predict Resistance to Commonly Used Broad-Spectrum Antibiotics in Children With Gram-Negative Bloodstream Infections.

BACKGROUND: As rates of multidrug-resistant gram-negative infections rise, it is critical to recognize children at high risk of bloodstream infections with organisms resistant to commonly used empiric broad-spectrum antibiotics. The objective of the current study was to develop a user-friendly clinical decision aid to predict the risk of resistance to commonly prescribed broad-spectrum empiric antibiotics for children with gram-negative bloodstream infections. METHODS: This was a longitudinal retrospective cohort study of children with gram-negative bacteria cared for at a tertiary care pediatric hospital from June 2009 to June 2015. The primary outcome was a bloodstream infection due to bacteria resistant to broad-spectrum antibiotics (ie, cefepime, piperacillin-tazobactam, meropenem, or imipenem-cilastatin). Recursive partitioning was used to develop the decision tree. RESULTS: Of 689 episodes of gram-negative bloodstream infections included, 31% were resistant to broad-spectrum antibiotics. The decision tree stratified patients into high- or low-risk groups based on prior carbapenem treatment, a previous culture with a broad-spectrum antibiotic resistant gram-negative organism in the preceding 6 months, intestinal transplantation, age ≥3 years, and ≥7 prior episodes of gram-negative bloodstream infections. The sensitivity for classifying high-risk patients was 46%, and the specificity was 91%. CONCLUSION: A decision tree offers a novel approach to individualize patients' risk of gram-negative bloodstream infections resistant to broad-spectrum antibiotics, distinguishing children who may warrant even broader antibiotic therapy (eg, combination therapy, newer ß-lactam agents) from those for whom standard empiric antibiotic therapy is appropriate. The constructed tree needs to be validated more widely before incorporation into clinical practice.

MR-Forest: A Deep Decision Framework for False Positive Reduction in Pulmonary Nodule Detection.

With the development of deep learning methods such as convolutional neural network (CNN), the accuracy of automated pulmonary nodule detection has been greatly improved. However, the high computational and storage costs of the large-scale network have been a potential concern for the future widespread clinical application. In this paper, an alternative Multi-ringed (MR)-Forest framework, against the resource-consuming neural networks (NN)-based architectures, has been proposed for false positive reduction in pulmonary nodule detection, which consists of three steps. First, a novel multi-ringed scanning method is used to extract the order ring facets (ORFs) from the surface voxels of the volumetric nodule models; Second, Mesh-LBP and mapping deformation are employed to estimate the texture and shape features. By sliding and resampling the multi-ringed ORFs, feature volumes with different lengths are generated. Finally, the outputs of multi-level are cascaded to predict the candidate class. On 1034 scans merging the dataset from the Affiliated Hospital of Liaoning University of Traditional Chinese Medicine (AH-LUTCM) and the LUNA16 Challenge dataset, our framework performs enough competitiveness than state-of-the-art in false positive reduction task (CPM score of 0.865). Experimental results demonstrate that MR-Forest is a successful solution to satisfy both resource-consuming and effectiveness for automated pulmonary nodule detection. The proposed MR-forest is a general architecture for 3D target detection, it can be easily extended in many other medical imaging analysis tasks, where the growth trend of the targeting object is approximated as a spheroidal expansion.