Decision tree analysis for age estimation in living individuals: integrating cervical and dental radiographic evaluations within a South African population.

Age estimation in living individuals around the age of 18 years is medico-legally important in undocumented migrant cases and in countries like South Africa where many individuals are devoid of identification documents. Establishing whether an individual is younger than 18 years largely influences the legal procedure that should be followed in dealing with an undocumented individual. The aim of this study was to combine dental third molar and anterior inferior apophysis ossification data for purposes of age estimation, by applying a decision tree analysis. A sample comprising of 871 black South African individuals (n = 446 males, 425 = females) with ages ranging between 15 and 24 years was analyzed using panoramic and cephalometric radiographs. Variables related to the left upper and lower third molars and cervical vertebral ring apophysis ossification of C2, C3, and C4 vertebrae analyzed in previous studies were combined in a multifactorial approach. The data were analyzed using a pruned decision tree function for classification. Male and female groups were handled separately as a statistically significant difference was found between the sexes in the original studies. A test sample of 30 individuals was used to determine if this approach could be used with confidence in estimating age of living individuals. The outcomes obtained from the test sample indicated a close correlation between the actual ages (in years and months) and the predicted ages (in years only), demonstrating an average age difference of 0.47 years between the corresponding values. This method showed that the application of decision tree analysis using the combination of third molar and cervical vertebral development is usable and potentially valuable in this application.

Data-Driven Clinical Pharmacy Research: Utilizing Machine Learning and Medical Big Data.

To conduct clinical pharmacy research, we often face the limitations of conventional statistical methods and single-center observational study. To overcome these issues, we have conducted data-driven research using machine learning methods and medical big data. Decision tree analysis, one of the typical machine learning methods, has a flowchart-like structure that allows users to easily and quantitatively evaluate the occurrence percentage of events due to the combination of multiple factors by answering related questions with Yes or No. Using this feature, we first developed a risk prediction model for acute kidney injury caused by vancomycin, a condition we frequently encounter in clinical practice. Additionally, by replacing the prediction target from a binary variable (i.e., presence or absence of adverse drug reactions) to a continuous variable (i.e., drug dosage), we built a model to estimate the initial dose of vancomycin required to reach the optimal blood level recommended by guidelines. We found its accuracy to be better than that of conventional dose-setting algorithms. Moreover, employing Japanese medical big data such as the claims database helped us overcome the major limitations of conventional clinical pharmacy research such as institutional bias caused by single-center studies. We demonstrated that the combined use of machine learning and medical big data could generate high-quality evidence leveraging the strengths of each approach. Data-driven clinical pharmacy research using machine learning and medical big data has enabled researchers to surpass the limitations of conventional research and produce clinically valuable findings.

Flowchart for predicting achieving the target area under the concentration-time curve of vancomycin in critically ill Japanese patients: A multicenter retrospective study.

INTRODUCTION: In therapeutic drug monitoring (TDM) of vancomycin (VCM), the area under the concentration-time curve (AUC) is related to the clinical efficacy and toxicity. Therefore, herein, we examined the factors associated with achieving the target AUC at follow-up and developed a decision flowchart for achieving the target AUC in critically ill patients. METHODS: This multicenter retrospective observational study was conducted at eight hospitals. We retrospectively analyzed data from patients who had received VCM in the intensive care unit from January 2020 to December 2022. Decision-tree (DT) analysis was performed using factors with p < 0.1 in univariate analysis as the independent variables. Case data were split up to two times, and four subgroups were included. The primary endpoint was achieving the target AUC at the follow-up TDM (AUCfollow-up) and target AUCfollow-up achievement was defined as an AUC of 400-600 µg‧h/mL. The initial AUC values were calculated with the 2-point concentrations (peak and trough) using the Bayesian estimation software Practical AUC-guided TDM (PAT). RESULTS: Among 70 patients (median age [interquartile range], 66 [56, 79] years; 50 % women), the AUCfollow-up was achieved in 70 % (49/70). Three factors were selected for the decision flow chart: predicted AUCfollow-up of 400-600 µg‧h/mL, dosing at 12-h intervals, and CCr of 130 mL/min/1.73 m2 or higher; the accuracy was adequate (92 %, R2 0.52). CONCLUSION: We successfully identified the factors associated with achieving the target AUC of VCM at follow-up TDM and developed a simple-to-use DT model. However, the validity of the findings needs to be evaluated.

Risk Groups by the Needs for Help: Asian American Breast Cancer Survivors.

To supply proper and sufficient information and coaching through cancer education, it is important to decide who are risk groups among a target population. A decision tree analysis could help decide the characteristics of the risk groups. This study aimed to identify the combined characteristics of Asian American breast cancer survivors that were closely linked to high needs for help during their breast cancer survivorship process. The data on the needs for help among 185 Asian American breast cancer survivors from a parent clinical trial were included in this analysis. The instruments included the Supportive Care Needs Survey-Short Form 34 (SCNS-SF34) and multiple scales to measure the factors influencing the women's needs for help. The data were analyzed using latent profile analyses and decision tree analyses. The characteristics of the group with the highest needs for help were different depending on the types of needs. For instance, the group with the highest patient care/support needs for help score had high global symptom distress scores (cut point = 2.25) and high physical symptom distress (cut point = 1.57) and did not have regular access to health care (mean = 95.00; node 10). The findings suggest several risk groups to target in future interventions for cancer education to reduce the needs for help among this specific population. Multiple factors that could influence the needs for help among Asian American breast cancer survivors need to be considered in future intervention development for cancer education.

Diagnostic Assessment of Endoscopic Ultrasonography-Fine Needle Aspiration Cytology in the Pancreas: A Comparison between Liquid-Based Preparation and Conventional Smear.

Background and Objectives: This study aimed to elucidate the cytologic characteristics and diagnostic usefulness of endoscopic ultrasonography-fine needle aspiration cytology (EUS-FNAC) by comparing it with liquid-based preparation (LBP) and conventional smear (CS) in pancreas. Methods: The diagnostic categories (I through VII) were classified according to the World Health Organization Reporting System for Pancreaticobiliary Cytopathology. Ten cytologic features, including nuclear and additional features, were evaluated in 53 cases subjected to EUS-FNAC. Nuclear features comprised irregular nuclear contours, nuclear enlargement, hypochromatic nuclei with parachromatin clearing, and nucleoli. Additional cellular features included isolated atypical cells, mucinous cytoplasm, drunken honeycomb architecture, mitosis, necrotic background, and cellularity. A decision tree analysis was conducted to assess diagnostic efficacy. Results: The diagnostic concordance rate between LBP and CS was 49.1% (26 out of 53 cases). No significant differences in nuclear features were observed between categories III (atypical), VI (suspicious for malignancy), and VII (malignant). The decision tree analysis of LBP indicated that cases with moderate or high cellularity and mitosis could be considered diagnostic for those exhibiting nuclear atypia. Furthermore, in CS, mitosis, isolated atypical cells, and necrotic background exerted a more significant impact on the diagnosis of EUS-FNAC. Conclusions: Significant parameters for interpreting EUS-FNAC may differ between LBP and CS. While nuclear atypia did not influence the diagnosis of categories III, VI, and VII, other cytopathologic features, such as cellularity, mitosis, and necrotic background, may present challenges in diagnosing EUS-FNAC.

Machine Learning-Based Prediction of Digoxin Toxicity in Heart Failure: A Multicenter Retrospective Study.

Digoxin toxicity (plasma digoxin concentration ≥0.9 ng/mL) is associated with worsening heart failure (HF). Decision tree (DT) analysis, a machine learning method, has a flowchart-like model where users can easily predict the risk of adverse drug reactions. The present study aimed to construct a flowchart using DT analysis that can be used by medical staff to predict digoxin toxicity. We conducted a multicenter retrospective study involving 333 adult patients with HF who received oral digoxin treatment. In this study, we employed a chi-squared automatic interaction detection algorithm to construct DT models. The dependent variable was set as the plasma digoxin concentration (≥ 0.9 ng/mL) in the trough during the steady state, and factors with p < 0.2 in the univariate analysis were set as the explanatory variables. Multivariate logistic regression analysis was conducted to validate the DT model. The accuracy and misclassification rates of the model were evaluated. In the DT analysis, patients with creatinine clearance <32 mL/min, daily digoxin dose ≥1.6 µg/kg, and left ventricular ejection fraction ≥50% showed a high incidence of digoxin toxicity (91.8%; 45/49). Multivariate logistic regression analysis revealed that creatinine clearance <32 mL/min and daily digoxin dose ≥1.6 µg/kg were independent risk factors. The accuracy and misclassification rates of the DT model were 88.2 and 46.2 ± 2.7%, respectively. Although the flowchart created in this study needs further validation, it is straightforward and potentially useful for medical staff in determining the initial dose of digoxin in patients with HF.

Risk evaluation of carbapenem-induced liver injury based on machine learning analysis.

INTRODUCTION: Information regarding carbapenem-induced liver injury is limited, and the rate of liver injury caused by meropenem (MEPM) and doripenem (DRPM) remains unknown. Decision tree (DT) analysis, a machine learning method, has a flowchart-like model where users can easily predict the risk of liver injury. Thus, we aimed to compare the rate of liver injury between MEPM and DRPM and construct a flowchart that can be used to predict carbapenem-induced liver injury. METHODS: We investigated patients treated with MEPM (n = 310) or DRPM (n = 320) and confirmed liver injury as the primary outcome. We used a chi-square automatic interaction detection algorithm to construct DT models. The dependent variable was set as liver injury from a carbapenem (MEPM or DRPM), and factors including alanine aminotransferase (ALT), albumin-bilirubin (ALBI) score, and concomitant use of acetaminophen were used as explanatory variables. RESULTS: The rates of liver injury were 22.9% (71/310) and 17.5% (56/320) in the MEPM and DRPM groups, respectively; no significant differences in the rate were observed (95% confidence interval: 0.710-1.017). Although the DT model of MEPM could not be constructed, DT analysis showed that the incidence of introducing DRPM in patients with ALT >22 IU/L and ALBI scores > -1.87 might be high-risk. CONCLUSIONS: The risk of developing liver injury did not differ significantly between the MEPM and DRPM groups. Since ALT and ALBI score are evaluated in clinical settings, this DT model is convenient and potentially useful for medical staff in assessing liver injury before DRPM administration.

Chi-square automatic interaction detector decision tree analysis model: Predicting cefmetazole response in intra-abdominal infection.

BACKGROUND: Cefmetazole is used as the first-line treatment for intra-abdominal infections. However, only a few studies have investigated the risk factors for cefmetazole treatment failure. AIMS: This study aimed to develop a decision tree-based predictive model to assess the effectiveness of cefmetazole in initial intra-abdominal infection treatment to improve the clinical treatment strategies. METHODS: This retrospective cohort study included adult patients who were unexpectedly hospitalized due to intra-abdominal infections between 2003 and 2020 and initially treated with cefmetazole. The primary outcome was clinical intra-abdominal infection improvement. The chi-square automatic interaction detector decision tree analysis was used to create a predictive model for clinical improvement after cefmetazole treatment. RESULTS: Among 2,194 patients, 1,807 (82.4%) showed clinical improvement post-treatment; their mean age was 48.7 (standard deviation: 18.8) years, and 1,213 (55.3%) patients were men. The intra-abdomせinal infections were appendicitis (n = 1,186, 54.1%), diverticulitis (n = 334, 15.2%), and pancreatitis (n = 285, 13.0%). The chi-square automatic interaction detector decision tree analysis identified the intra-abdominal infection type, C-reactive protein level, heart rate, and body temperature as predictive factors by categorizing patients into seven groups. The area under the receiver operating characteristic curve was 0.71 (95% confidence interval: 0.68-0.73). CONCLUSION: This predictive model is easily understandable visually and may be applied in clinical practice.

Development of a risk prediction model for surgical site infection after lower third molar surgery.

BACKGROUND: There is little evidence regarding risk prediction for surgical site infection (SSI) after lower third molar (L3M) surgery. METHODS: We conducted a nested case-control study to develop a multivariable logistic model for predicting the risk of SSI after L3M surgery. Data were obtained from Hokkaido University Hospital from April 2013 to March 2020. Multiple imputation was applied for the missing values. We conducted decision tree (DT) analysis to evaluate the combinations of factors affecting SSI risk. RESULTS: We identified 648 patients. The final model retained the available distal space (Pell & Gregory II [p = 0.05], Pell & Gregory III [p < 0.01]), depth (Pell & Gregory B [p < 0.01], Pell & Gregory C [p < 0.01]), surgeon's experience (3-10 years [p = 0.25], <3 years [p < 0.01]), and simultaneous extraction of both L3M [p < 0.01]; the concordance-statistic was 0.72. The DT analysis demonstrated that patients with Pell and Gregory B or C and simultaneous extraction of both L3M had the highest risk of SSI. CONCLUSIONS: We developed a model for predicting SSI after L3M surgery with adequate predictive metrics in a single center. This model will make the SSI risk prediction more accessible.

Identifying Risk Profiles for Nonadherence to the 24-Hour Movement Guidelines for Children and Youth 6 Months Into the COVID-19 Pandemic.

PURPOSE: The purposes of the current study were to identify risk profiles for nonadherence among children and youth (5-17 y) at the 6-month mark of the COVID-19 pandemic and to discuss similarities and differences between risk profiles identified in the current study and those identified at the 1-month mark of the pandemic. METHODS: Data were part of a nationally representative sample of 1143 parents (Mage = 43.07 y, SD = 8.16) of children and youth (5-17 y) living in Canada. Survey data were collected in October 2020. RESULTS: Results showed that 3.8% met all movement behavior recommendations, 16.2% met the physical activity recommendation, 27% met the screen time recommendation, and 63.8% met the sleep recommendation. Characteristics associated with nonadherence to all movement behaviors included low parental perceived capability to restrict screen time and decreased overall time spent outdoors. Characteristics associated with nonadherence to the physical activity and screen time recommendations included youth (12-17 y), low parental perceived capability to restrict screen time, decreased time spent outdoors, and increased screen time. CONCLUSION: Results emphasized the importance of parental perceived capability to restrict screen time and children's and youth's outdoor time and showed that pandemic-related factors have impacted children and youth differently.

Priority analysis of factors affecting family planning practices among Ethiopians using a decision tree analysis.

This study aimed to identify the priorities of the factors affecting family planning practices in Ethiopia, with the ultimate aim of providing evidence to the Ethiopian government and international organizations for establishing family planning policies or family planning-related project plans. Multi-stage, clustered, stratified random sampling was performed on a total of 35,479 men aged above 15 years and women of childbearing age (15-49 years) in two metropolitan cities and five regions of Ethiopia. The survey was conducted by face-to-face interview using Tablet PC, and 25,972 responses, excluding censored data were included in the final analysis. The collected data were first analyzed using the Pearson chi-square test, independent sample t-test, and F-test with the Tukey HSD method as a post-hoc. Second, a decision-making tree analysis was conducted to identify priority factors affecting the decision to implement family planning The primary factor affecting the family planning practice was 'spouse or sexual partner's support for family planning (P <.001)'. 'Region (p <.001)' was the second priority factor for both the group receiving 'support for family planning by spouse or partner' and the group not receiving it. The third priority factors appeared differed by region in both groups. It is necessary to establish family planning policy and program plans targeting both men and women, and participation of religious and community leaders is considered important in the establishment process. In addition, it is considered necessary to enhance the professionalism by dividing the education and evaluation process for HEW to provide high-quality counseling, education, and services on family planning at the community level.

A decision tree analysis applied to women aged 43-45: who should be referred for ovum donation?

RESEARCH QUESTION: In women at the advanced age of 43-45 years undergoing repeated IVF cycles with autologous oocytes, who has the highest chance for birth and who should be referred early to receive donor oocytes? DESIGN: A retrospective cohort study was conducted at a university hospital reproductive centre. The computerized database of 394 women aged 43-45 years undergoing 1528 non-donor IVF or intracytoplasmic sperm injection cycles between 2010 and 2019 was analysed. A decision tree was developed, enabling a comprehensive study of a set of clinical parameters and the expected outcomes. RESULTS: The cumulative clinical pregnancy rate was 15.0% (59/394) and the cumulative live birth rate was 8.4% (33/394). The decision tree developed to predict women who should be offered egg donation included age, poor ovarian response to stimulation, the number of top-quality embryos, dominant follicles, previous pregnancy or live birth, fertilized oocytes and body mass index. The model showed that a good ovarian response in the first cycle was the best predictor for live birth (13.3% gave birth). However, among women with poor responses, 7.1% of those who were younger than 43.5 years gave birth, and none of the women who were older than 43.5 years did. CONCLUSIONS: Women over 43.5 years old with fewer than four oocytes collected in their first IVF cycle should be offered ovum donation, since their live birth rate in subsequent cycles is negligible.

Conditional inference tree models to perceive depth of invasion in T1 colorectal cancer.

BACKGROUND AND AIM: Accurate diagnosis of invasion depth for T1 colorectal cancer is of critical importance as it decides optimal resection technique. Few reports have previously covered the effects of endoscopic morphology on depth assessment. We developed and validated a novel diagnostic algorithm that accurately predicts the depth of early colorectal cancer. METHODS: We examined large pathological and endoscopic databases compiled between Jan 2015 and Dec 2018. Training and validation data cohorts were derived and real-world diagnostic performance of two conditional interference tree algorithms (Models 1 and 2) was evaluated against that of the Japan NBI-Expert Team (JNET) classification used by both expert and non-expert endoscopists. RESULTS: Model 1 had higher sensitivity in deep submucosal invasion than that of JNET alone in both training (45.1% vs. 28.6%, p < 0.01) and validation sets (52.3% vs. 40.0%, p < 0.01). Model 2 demonstrated higher sensitivity than Model 1 (66.2% vs. 52.3%, p < 0.01) in excluding deeper invasion of suspected Tis/T1a lesions. CONCLUSION: We discovered that machine-learning classifiers, including JNET and macroscopic features, provide the best non-invasive screen to exclude deeper invasion for suspected Tis/T1 lesions. Adding this algorithm improves depth diagnosis of T1 colorectal lesions for both expert and non-expert endoscopists.

Machine Learning-Based Model for Estimating Vancomycin Maintenance Dose to Target the Area under the Concentration Curve of 400-600 mg·h/L in Japanese Patients.

In therapeutic drug monitoring of vancomycin (VCM), the area under the concentration-time curve (AUC) is related to clinical efficacy and toxicity. Determining the maintenance for patient is necessary since VCM concentrations are affected by factors such as renal function. We constructed a machine learning-based model to estimate the maintenance dose to target an AUC of 400-600 mg⋅h/L in each combination of patient's factors. This retrospective observational study was conducted at two hospitals. Patients who received VCM intravenously with measured trough and another point (e.g., peak) concentrations within the November 2011 to March 2019 period were enrolled. We extracted the factors that affect VCM concentration and constructed a decision tree model using a classification and regression tree algorithm. Of the 1380 patients, 822 were included. Training data were split up to four times and included 24 subgroups. The average corrected VCM daily doses ranged 17.6-59.4 mg/kg. Estimated glomerular filtration rate, age, and body mass index were selected as predictive variables that affected the recommended daily dose. In the validation data, our model had slightly higher proportions of AUC of 400-600 mg⋅h/L than other nomograms. However, our model was based only on limited patients. Thus, further clinical studies are needed to develop a general-purpose model in the future. We successfully constructed a model that recommends VCM maintenance daily doses with AUC of 400-600 mg⋅h/L for each combination of independent variables. Our model has the potential for application as a simple decision-making tool for medical staff.

Possibility of Multiple Drug-Drug Interactions in Patients Treated with Statins: Analysis of Data from the Japanese Adverse Drug Event Report (JADER) Database and Verification by Animal Experiments.

Adverse drug events due to drug-drug interactions can be prevented by avoiding concomitant use of causative drugs; therefore, it is important to understand drug combinations that cause drug-drug interactions. Although many attempts to identify drug-drug interactions from real-world databases such as spontaneous reporting systems have been performed, little is known about drug-drug interactions caused by three or more drugs in polypharmacy, i.e., multiple drug-drug interactions. Therefore, we attempted to detect multiple drug-drug interactions using decision tree analysis using the Japanese Adverse Drug Event Report (JADER) database, a Japanese spontaneous reporting system. First, we used decision tree analysis to detect drug combinations that increase the risk of rhabdomyolysis in cases registered in the JADER database that used six statins. Next, the risk of three or more drug combinations that significantly increased the risk of rhabdomyolysis was validated with in vivo experiments in rats. The analysis identified a multiple drug-drug interaction signal only for pitavastatin. The reporting rate of rhabdomyolysis for pitavastatin in the JADER database was 0.09, and it increased to 0.16 in combination with allopurinol. Furthermore, the rate was even higher (0.40) in combination with valsartan. Additionally, necrosis of leg muscles was observed in some rats simultaneously treated with these three drugs, and their creatine kinase and myoglobin levels were elevated. The combination of pitavastatin, allopurinol, and valsartan should be treated with caution as a multiple drug-drug interaction. Since multiple drug-drug interactions were detected with decision tree analysis and the increased risk was verified in animal experiments, decision tree analysis is considered to be an effective method for detecting multiple drug-drug interactions.

Development of cerebral vasospasm following traumatic intracranial hemorrhage: incidence, risk factors, and clinical outcomes.

OBJECTIVE: Limited evidence exists characterizing the incidence, risk factors, and clinical associations of cerebral vasospasm following traumatic intracranial hemorrhage (tICH) on a large scale. Therefore, the authors sought to use data from a national inpatient registry to investigate these aspects of posttraumatic vasospasm (PTV) to further elucidate potential causes of neurological morbidity and mortality subsequent to the initial insult. METHODS: Weighted discharge data from the National (Nationwide) Inpatient Sample from 2015 to 2018 were queried to identify patients with tICH who underwent diagnostic angiography in the same admission and, subsequently, those who developed angiographically confirmed cerebral vasospasm. Multivariable logistic regression analysis was performed to identify significant associations between clinical covariates and the development of vasospasm, and a tICH vasospasm predictive model (tICH-VPM) was generated based on the effect sizes of these parameters. RESULTS: Among 5880 identified patients with tICH, 375 developed PTV corresponding to an incidence of 6.4%. Multivariable adjusted modeling determined that the following clinical covariates were independently associated with the development of PTV, among others: age (adjusted odds ratio [aOR] 0.98, 95% CI 0.97-0.99; p < 0.001), admission Glasgow Coma Scale score < 9 (aOR 1.80, 95% CI 1.12-2.90; p = 0.015), intraventricular hemorrhage (aOR 6.27, 95% CI 3.49-11.26; p < 0.001), tobacco smoking (aOR 1.36, 95% CI 1.02-1.80; p = 0.035), cocaine use (aOR 3.62, 95% CI 1.97-6.63; p < 0.001), fever (aOR 2.09, 95% CI 1.34-3.27; p = 0.001), and hypokalemia (aOR 1.62, 95% CI 1.26-2.08; p < 0.001). The tICH-VPM achieved moderately high discrimination, with an area under the curve of 0.75 (sensitivity = 0.61 and specificity = 0.81). Development of vasospasm was independently associated with a lower likelihood of routine discharge (aOR 0.60, 95% CI 0.45-0.78; p < 0.001) and an extended hospital length of stay (aOR 3.53, 95% CI 2.78-4.48; p < 0.001), but not with mortality. CONCLUSIONS: This population-based analysis of vasospasm in tICH has identified common clinical risk factors for its development, and has established an independent association between the development of vasospasm and poorer neurological outcomes.

Cerebral vasospasm following arteriovenous malformation rupture: a population-based cross-sectional study.

OBJECTIVE: Studies examining the risk factors and clinical outcomes of arterial vasospasm secondary to cerebral arteriovenous malformation (cAVM) rupture are scarce in the literature. The authors used a population-based national registry to investigate this largely unexamined clinical entity. METHODS: Admissions for adult patients with cAVM ruptures were identified in the National Inpatient Sample during the period from 2015 to 2019. Complex samples multivariable logistic regression and chi-square automatic interaction detection (CHAID) decision tree analyses were performed to identify significant associations between clinical covariates and the development of vasospasm, and a cAVM-vasospasm predictive model (cAVM-VPM) was generated based on the effect sizes of these parameters. RESULTS: Among 7215 cAVM patients identified, 935 developed vasospasm, corresponding to an incidence rate of 13.0%; 110 of these patients (11.8%) subsequently progressed to delayed cerebral ischemia (DCI). Multivariable adjusted modeling identified the following baseline clinical covariates: decreasing age by decade (adjusted odds ratio [aOR] 0.87, 95% CI 0.83-0.92; p < 0.001), female sex (aOR 1.68, 95% CI 1.45-1.95; p < 0.001), admission Glasgow Coma Scale score < 9 (aOR 1.34, 95% CI 1.01-1.79; p = 0.045), intraventricular hemorrhage (aOR 1.87, 95% CI 1.17-2.98; p = 0.009), hypertension (aOR 1.77, 95% CI 1.50-2.08; p < 0.001), obesity (aOR 0.68, 95% CI 0.55-0.84; p < 0.001), congestive heart failure (aOR 1.34, 95% CI 1.01-1.78; p = 0.043), tobacco smoking (aOR 1.48, 95% CI 1.23-1.78; p < 0.019), and hospitalization events (leukocytosis [aOR 1.64, 95% CI 1.32-2.04; p < 0.001], hyponatremia [aOR 1.66, 95% CI 1.39-1.98; p < 0.001], and acute hypotension [aOR 1.67, 95% CI 1.31-2.11; p < 0.001]) independently associated with the development of vasospasm. Intraparenchymal and subarachnoid hemorrhage were not associated with the development of vasospasm following multivariable adjustment. Among significant associations, a CHAID decision tree algorithm identified age 50-59 years (parent node), hyponatremia, and leukocytosis as important determinants of vasospasm development. The cAVM-VPM achieved an area under the curve of 0.65 (sensitivity 0.70, specificity 0.53). Progression to DCI, but not vasospasm alone, was independently associated with in-hospital mortality (aOR 2.35, 95% CI 1.29-4.31; p = 0.016) and lower likelihood of routine discharge (aOR 0.62, 95% CI 0.41-0.96; p = 0.031). CONCLUSIONS: This large-scale assessment of vasospasm in cAVM identifies common clinical risk factors and establishes progression to DCI as a predictor of poor neurological outcomes.

Telehealth Screening for Diabetic Retinopathy: Economic Modeling Reveals Cost Savings.

Introduction: The use of telehealth screening (TS) for diabetic retinopathy (DR) consists of fundus photography in a primary care setting with remote interpretation of images. TS for DR is known to increase screening utilization and reduce vision loss compared with standard in-person conventional diabetic retinal exam (CDRE). Anti-vascular endothelial growth factor intravitreal injections have become standard of care for the treatment of DR, but they are expensive. We investigated whether TS for DR is cost-effective when DR management includes intravitreal injections using national data. Materials and Methods: We compared cost and effectiveness of TS and CDRE using decision-tree analysis and probabilistic sensitivity analysis with Monte Carlo simulation. We considered the disability weight (DW) of vision impairment and 1-year direct medical costs of managing patients based on Medicare allowable rates and clinical trial data. Primary outcomes include incremental costs and incremental effectiveness. Results: The average annual direct cost of eye care was $196 per person for TS and $275 for CDRE. On average, TS saves $78 (28%) compared with CDRE and was cost saving in 88.9% of simulations. The average DW outcome was equivalent in both groups. Discussion: Although this study was limited by a 1-year time horizon, it provides support that TS for DR can reduce costs of DR management despite expensive treatment with anti-VEGF agents. TS for DR is equally effective as CDRE at preserving vision. Conclusions: Annual TS for DR is cost saving and equally effective compared with CDRE given a 1-year time horizon.

Gradually shifting clinical phenomics in migraine spectrum: a cross-sectional, multicenter study of 5438 patients.

BACKGROUND: The aim of the study was to investigate whether MwoA and MwA are different manifestations of a single disease, distinct clinical entities, or located at two poles of a spectrum. METHODS: In this cross-sectional study, 5438 patients from 10 hospitals in China were included: 4651 were diagnosed with migraine without aura (MwoA) and 787 with migraine with aura (MwA). We used a validated standardized electronic survey to collect multidimensional data on headache characteristics and evaluated the similarities and differences between migraine subtypes. To distinguish migraine subtypes, we employed correlational analysis, factor analysis of mixed data (FAMD), and decision tree analysis. RESULTS: Compared to MwA, MwoA had more severe headaches, predominantly affected females, were more easily produced by external factors, and were more likely to have accompanying symptoms and premonitory neck stiffness. Patients with MwA are heterogeneous, according to correlation analysis; FAMD divided the subjects into three clear clusters. The majority of the differences between MwoA and MwA were likewise seen when typical aura with migraine headache (AWM) and typical aura with non-migraine headache (AWNM) were compared. Furthermore, decision trees analysis revealed that the chaotic MwA data reduced the decision tree's accuracy in distinguishing MwoA from MwA, which was significantly increased by splitting MwA into AWM and AWNM. CONCLUSIONS: The clinical phenomics of headache phenotype varies gradually from MwoA to AWM and AWNM, and AWM is a mid-state between MwoA and AWNM. We tend to regard migraine as a spectrum disorder, and speculate that different migraine subtypes have different "predominant regions" that generate attacks.

A retrospective study on the combined biomarkers and ratios in serum and pleural fluid to distinguish the multiple types of pleural effusion.

PURPOSE: Pleural effusion (PE) is a common clinical manifestation, and millions of people suffer from pleural disease. Herein, this retrospective study was performed to evaluate the biomarkers and ratios in serum and pleural fluid (PF) for the differential diagnosis of the multiple types of PE and search for a new diagnostic strategy for PE. METHODS: In-patients, who developed tuberculous PE (TPE), malignant PE (MPE), complicated parapneumonic effusion (CPPE), uncomplicated PPE (UPPE), or PE caused by connective tissue diseases (CTDs) and underwent thoracentesis at Peking University People's Hospital from November 2016 to April 2019, were included in this study. Eleven biomarkers and their ratios in serum and PF were investigated and compared between pairs of the different PE groups, and a decision-tree was developed. RESULTS: Totally 112 PE cases, including 25 MPE, 33 TPE, 19 CPPE, 27 UPPE, and 8 PE caused by CTDs, were reviewed. Biomarkers and ratios showed good diagnostic performance with high area under the curve values, sensitivities, and specificities for the differential diagnosis of the multiple types of PE. According to the decision-tree analysis, the combination of adenosine deaminase (ADA), serum albumin, serum lactate dehydrogenase, total protein, PF-LDH/ADA, and PF-LDH/TP provided the best predictive capacity with an overall accuracy of 84.8%; the sensitivity and specificity for TPE diagnosis were 100% and 98.7%, respectively. CONCLUSION: The biomarkers and ratios showed good diagnostic performance, and a decision-tree with an overall accuracy of 84.8% was developed to differentiate the five types of PE in clinical settings.