Classification And Regression Tree Analysis Research Articles

Risk factor structure of heart failure in patients with cancer after treatment with anticancer agents’ assessment by big data from a Japanese electronic health record

As the prognosis of cancer patients has been improved, comorbidity of heart failure (HF) in cancer survivors is a serious concern, especially in the aged population. This study aimed to examine the risk factors of HF development after treatment by anticancer agents, using a machine learning-based analysis of a massive dataset obtained from the electronic health record (EHR) in Japan. This retrospective, cohort study, using a dataset from 2008 to 2017 in the Diagnosis Procedure Combination (DPC) database in Japan, enrolled 140,327 patients. The structure of risk factors was determined using multivariable analysis and classification and regression tree (CART) algorithm for time-to-event data. The mean follow-up period was 1.55 years. The prevalence of HF after anticancer agent administration were 4.0%. HF was more prevalent in the older than the younger. As the presence of cardiovascular diseases and various risk factors predicted HF, CART analysis of the risk factors revealed that the risk factor structures complicatedly differed among different age groups. The highest risk combination was hypertension, diabetes mellitus, and atrial fibrillation in the group aged ≤ 64 years, and the presence of ischemic heart disease was a key in both groups aged 65–74 years and 75 ≤ years. The machine learning-based approach was able to develop complicated HF risk structures in cancer patients after anticancer agents in different age population, of which knowledge would be essential for realizing precision medicine to improve the prognosis of cancer patients.

Interactive Combinations Between Gait Speed and Physical Function at Acute Phase Can Predict the Physical Activity at 2 Years After Total Knee Arthroplasty Using Classification and Regression Tree Analysis

ObjectiveTo clarify the interactive combinations of various clinical factors associated with physical activity (PA) at 2 years after total knee arthroplasty (TKA) using classification and regression tree (CART) analysis. DesignA retrospective cohort study. SettingA single university hospital. Participants286 patients who underwent TKA (N=286). Main Outcome MeasuresPA was assessed preoperatively, 3 weeks, and 2 years after TKA. Physical functions, namely, 10 m walking test (10MWT), timed Up and Go test, 1-leg standing time, isometric knee extension and flexion strength, knee joint stability, knee pain, femora-tibial angle, and the passive knee extension and flexion angle, were measured before surgery as a baseline and 3 weeks after TKA as acute phase. CART analysis was conducted to clarify the interactive combinations that accurately predict the PA at 2 years after TKA. ResultsThe results of CART analysis indicated that gait speed (≥1.05 m/s) at the acute phase after TKA was the primal predictor for the postoperative PA at 2 years. The highest postoperative PA at 2 years was determined by gait speed (≥1.05 m/s) and PA (>74.5) at the acute phase. The PA at baseline and at acute phase, as well as the body mass index were also selected as predictors of postoperative PA at 2 years. ConclusionThe present study suggested that acquiring gait speed (≥1.05 m/s) and PA (>74.5) in the postoperative acute phase is the predictive of a high PA at 2 years after TKA.

The Prognostic Value of Preoperative Serum Markers and Risk Classification in Patients with Hepatocellular Carcinoma.

Complex hepatocellular carcinoma (HCC) prognostic biomarkers have been reported in various studies. We aimed to establish biomarkers that could predict prognosis, and formulate a simple classification using non-invasive preoperative blood test data. We retrospectively identified 305 patients for a discovery cohort who had undergone HCC-related hepatectomy at four Japanese university hospitals between January 1, 2011 and December 31, 2013. Preoperative blood test parameter optimal cut-off values were determined using receiver operating characteristic curve analysis. Cox uni- and multivariate analyses were used to determine independent prognostic factors. Risk classifications were established using classification and regression tree (CART) analysis. Validation was performed with 267 patients from three other hospitals. In multivariate analysis, α-fetoprotein (AFP, p < 0.001), protein induced by vitamin K absence or antagonist-II (PIVKA-II, p = 0.006), and C-reactive protein (CRP, p < 0.001) were independent prognostic factors for overall survival (OS). AFP (p = 0.007), total bilirubin (p = 0.001), and CRP (p = 0.003) were independent recurrent risk factors for recurrence-free survival (RFS). CART analysis results formed OS (CRP, AFP, and albumin) and RFS (PIVKA-II, CRP, and total bilirubin) decision trees, based on machine learning using preoperative serum markers, with three risk classifications. Five-year OS (low risk, 80.0%; moderate risk, 56.3%; high risk, 25.2%; p < 0.001) and RFS (low risk, 43.4%; moderate risk, 30.8%; high risk, 16.6%; p < 0.001) risks differed significantly. These classifications also stratified OS and RFS risk in the validation cohort. Three simple risk classifications using preoperative non-invasive prognostic factors could predict prognosis.

Diagnosis of comorbid migraine without aura in patients with idiopathic/genetic epilepsy based on the gray zone approach to the International Classification of Headache Disorders 3 criteria.

Migraine without aura (MwoA) is a very frequent and remarkable comorbidity in patients with idiopathic/genetic epilepsy (I/GE). Frequently in clinical practice, diagnosis of MwoA may be challenging despite the guidance of current diagnostic criteria of the International Classification of Headache Disorders 3 (ICHD-3). In this study, we aimed to disclose the diagnostic gaps in the diagnosis of comorbid MwoA, using a zone concept, in patients with I/GEs with headaches who were diagnosed by an experienced headache expert. In this multicenter study including 809 consecutive patients with a diagnosis of I/GE with or without headache, 163 patients who were diagnosed by an experienced headache expert as having a comorbid MwoA were reevaluated. Eligible patients were divided into three subgroups, namely, full diagnosis, zone I, and zone II according to their status of fulfilling the ICHD-3 criteria. A Classification and Regression Tree (CART) analysis was performed to bring out the meaningful predictors when evaluating patients with I/GEs for MwoA comorbidity, using the variables that were significant in the univariate analysis. Longer headache duration (<4 h) followed by throbbing pain, higher visual analog scale (VAS) scores, increase of pain by physical activity, nausea/vomiting, and photophobia and/or phonophobia are the main distinguishing clinical characteristics of comorbid MwoA in patients with I/GE, for being classified in the full diagnosis group. Despite being not a part of the main ICHD-3 criteria, the presence of associated symptoms mainly osmophobia and also vertigo/dizziness had the distinguishing capability of being classified into zone subgroups. The most common epilepsy syndromes fulfilling full diagnosis criteria (n = 62) in the CART analysis were 48.39% Juvenile myoclonic epilepsy followed by 25.81% epilepsy with generalized tonic-clonic seizures alone. Longer headache duration, throbbing pain, increase of pain by physical activity, photophobia and/or phonophobia, presence of vertigo/dizziness, osmophobia, and higher VAS scores are the main supportive associated factors when applying the ICHD-3 criteria for the comorbid MwoA diagnosis in patients with I/GEs. Evaluating these characteristics could be helpful to close the diagnostic gaps in everyday clinical practice and fasten the diagnostic process of comorbid MwoA in patients with I/GEs.

Preoperative prognostic nutritional index predicts short-term complications after radical resection of distal cholangiocarcinoma.

The occurrence of postoperative complications of distal cholangiocarcinoma (dCCA) is an indicator of poor patient prognosis. This study aimed to determine the immune-nutritional indexes (INIs) that can predict short-term postoperative complications. A retrospective analysis of 148 patients with dCCA who were operated radical pancreaticoduodenectomy at the First Hospital of Lanzhou University from December 2015 to March 2022 was conducted to assess the predictive value of preoperative INIs and preoperative laboratory tests for short-term postoperative complications, and a decision tree model was developed using classification and regression tree (CART) analysis to identify subgroups at risk for overall complications. In this study, 83 patients (56.08%) experienced overall complications. Clavien-Dindo grade III-V complications occurred in 20 patients (13.51%), and 2 patients died. The areas under curves (AUCs) of the preoperative prognostic nutritional index (PNI), controlling nutritional status (CONUT) score, and neutrophil-to-lymphocyte ratio (NLR) were compared; the PNI provided the maximum discrimination for complications (AUC = 0.685, 95% CI = 0.600-0.770), with an optimal cutoff value of 46.9, and the PNI ≤ 46.9 group had higher incidences of overall complications (70.67% vs. 40.00%, P < 0.001) and infectious complications (28.77% vs. 13.33%, P = 0.035). Multivariate logistic regression analysis identified PNI (OR = 0.87, 95% CI: 0.80-0.94) and total bilirubin (OR = 1.01, 95% CI: 1.00-1.01) were independent risk factors for overall complications (P < 0.05). According to CART analysis, PNI was the most important parameter, followed by the total bilirubin (TBIL) level. Patients with a PNI lower than the critical value and TBIL higher than the critical value had the highest overall complication rate (90.24%); the risk prediction model had an AUC of 0.714 (95% CI, 0.640-0.789) and could be used to stratify the risk of overall complications and predict grade I-II complications (P < 0.05). The preoperative PNI is a good predictor for short-term complications after the radical resection of dCCA. The decision tree model makes PNI and TBIL easier to use in clinical practice.

Predicting the body weight of indigenous goat breeds from morphological measurements using the classification and regression tree (CART) data mining algorithm

Classification and regression tree (CART) is a tree-based data mining algorithm that develops a model to predict an outcome. This study purposed to create a model to predict the body weight (BWT) of Red Sokoto (RS), Sahel (SH), and West African Dwarf (WAD) goats using morphological measurements (such as body length, BL; head girth, HG; head width, HDW; face length, FAL; height at wither, HTW; rump length, RL; shoulder width, SW; rump width, RW; and rump height, RH). In total, 600 goats were used for this study (200 each of RS, SH, and WAD goats). Pearson?s Moment Correlation was used to evaluate the degree of association between BWT and each morphological measurement. Concomitantly, CART analysis was performed to estimate which independent variable (morphological measurements) played a considerable role in the BWT (dependent variable) prediction. In RS and WAD goats, a positive and statistically significant (p &lt; 0.0001) correlation was observed between BWT and each morphological measurement. However, in SH goats, both positive and negative statistically significant correlations were observed between BWT and morphological measurements. The CART analysis indicated that in RS and WAD goats, HG played a considerable role in BWT prediction, while, in SH goats, BL was considered the most critical independent variable in BWT prediction. Therefore, this study suggests that HG can be used as a prognostic index for BWT estimation in Red Sokoto and West African Dwarf, while BL can be used for Sahel goats. The SAS codes used are available via a GitHub repository (https://github.com/Soullevram/CART).

Clinicoradiologic Characteristics of Intradural Extramedullary Conventional Spinal Ependymoma.

Distinguishing intradural extramedullary (IDEM) spinal ependymoma from myxopapillary ependymoma is challenging due to the location of IDEM spinal ependymoma. This study aimed to investigate the utility of clinical and MR imaging features for differentiating between IDEM spinal and myxopapillary ependymomas. We compared tumor size, longitudinal/axial location, enhancement degree/pattern, tumor margin, signal intensity (SI) of the tumor on T2-weighted images and T1-weighted image (T1WI), increased cerebrospinal fluid (CSF) SI caudal to the tumor on T1WI, and CSF dissemination of pathologically confirmed 12 IDEM spinal and 10 myxopapillary ependymomas. Furthermore, classification and regression tree (CART) was performed to identify the clinical and MR features for differentiating between IDEM spinal and myxopapillary ependymomas. Patients with IDEM spinal ependymomas were older than those with myxopapillary ependymomas (48 years vs. 29.5 years, p < 0.05). A high SI of the tumor on T1W1 was more frequently observed in IDEM spinal ependymomas than in myxopapillary ependymomas (p = 0.02). Conversely, myxopapillary ependymomas show CSF dissemination. Increased CSF SI caudal to the tumor on T1WI was observed more frequently in myxopapillary ependymomas than in IDEM spinal ependymomas (p < 0.05). Dissemination to the CSF space and increased CSF SI caudal to the tumor on T1WI were the most important variables in CART analysis. Clinical and radiological variables may help differentiate between IDEM spinal and myxopapillary ependymomas.

Use of machine learning as a tool for determining fire management units in the brazilian atlantic forest

Geoprocessing techniques are generally applied in natural disaster risk management due to their ability to integrate and visualize different sets of geographic data. The objective of this study was to evaluate the capacity of classification and regression tree (CART) to assess fire risk. MCD45A1 product of the burnt area, relative to a 16-year period (2000-2015) was used to obtain a fire occurrence map, from center points of the raster, using a kernel density approach. The resulting map was then used as a response variable for CART analysis with fire influence variables used as predictors. A total of 12 predictors were determined from several databases, including environmental, physical, and socioeconomic aspects. Rules generated by the regression process allowed to of define different risk levels, expressed in 35 management units, and used to produce a fire prediction map. Results of the regression process (r = 0.94 and r² = 0.88) demonstrate the capability of the CART algorithm in highlighting hierarchical relationships among predictors, while the model's easy interpretability provides a solid basis for decision making. This methodology can be expanded in other environmental risk analysis studies and applied to any area of the globe on a regional scale.

The Clinical Significance of Maximum Tumor Diameter on MRI in Men Undergoing Radical Prostatectomy or Definitive Radiotherapy for Locoregional Prostate Cancer.

Maximum tumor diameter (MTD) on pretreatment magnetic resonance imaging (MRI) has the potential to further risk stratify for men with prostate cancer (PCa) prior to definitive local therapy. We aim to evaluate the prognostic impact of radiographic maximum tumor diameter (MTD) in men with localized prostate cancer. From a single-center retrospective cohort of men receiving definitive treatment for PCa (radical prostatectomy [RP] or radiotherapy [RT]) with available pretreatment MRI, we conducted univariable and multivariable Cox proportional-hazards models for progression using clinical variables including age, NCCN risk group, radiographic extracapsular extension (ECE), radiographic seminal vesical invasion (SVI), and MTD. RP and RT cohorts were analyzed separately. Covariates were used in a classification and regression tree (CART) analysis and progression-free survival was estimated with the Kaplan-Meier method and groups were compared using log-rank tests. The cohort included 631 patients (n=428 RP, n=203 RT). CART analysis identified 4 prognostic groups for patients treated with RP and 2 prognostic groups in those treated with RT. In the RP cohort, NCCN low/intermediate risk group patients with MTD>=15 mm had significantly worse PFS than those with MTD <= 14 mm, and NCCN high-risk patients with radiographic ECE had significantly worse PFS than those without ECE. In the RT cohort, PFS was significantly worse in the cohort with MTD >= 23 mm than those <= 22 mm. Radiographic MTD may be a useful prognostic factor for patients with locoregional prostate cancer. This is the first study to illustrate that the importance of pretreatment tumor size may vary based on treatment modality.

Evaluation of some factors on birth and weaning weights in Awassi sheep by using GLM and CART analysis.

Birth weight (BW), which is the first physiological record of the postnatal period, is an important indicator that affects growth and development, reproduction, and some yields of living things in the future. The present study was carried out using the birth records of 5417 heads of Awassi lambs from 2013 to 2018 in MeMuTa dairy sheep farm in Zengen town of Ereğli district of Konya city in Türkiye. In this study, the effects of some environmental and genetic factors on birth and weaning weight in Awassi lambs were evaluated using both general linear model (GLM) and classification and regression tree (CART) analysis. As a result of the GLM analysis, the least squares' means of birth and weaning weights (BW and WW) were determined as 4.15 ± 0.05kg and 16.39 ± 0.13kg, respectively. Fixed genetic factors such as birth type and sex, and environmental factors such as season and year were found to be significant on birth weight (P < 0.01). As for weaning weight, other factors except birth type were found to be similarly important like birth weight (P < 0.01). Also, linear regression of birth weight on weaning weight was found to be significant (P < 0.01). In GLM and CART analyses, the determination coefficient (R2) was determined to be 23.80% and 11.70% for BW, and 24.11% and 13.18% for WW, respectively. The findings of the analysis results showed that the factors in the model have a similar tendency both in terms of their relative ratios in the total variation in the GLM analysis and in their relative importance in the CART algorithm. It was seen that CART data mining algorithm in the prediction of some genetic and environmental factors on birth and weaning weights using some factors in Awassi lambs produced successful results in predictive performance. Briefly, it was determined that there is a similar tendency to GLM analysis according to CART algorithm analysis in the current study.

Preoperative Serum Markers and Risk Classification in Intrahepatic Cholangiocarcinoma: A Multicenter Retrospective Study.

Accurate risk stratification selects patients who are expected to benefit most from surgery. This retrospective study enrolled 225 Japanese patients with intrahepatic cholangiocellular carcinoma (ICC) who underwent hepatectomy between January 2009 and December 2020 and identified preoperative blood test biomarkers to formulate a classification system that predicted prognosis. The optimal cut-off values of blood test parameters were determined by ROC curve analysis, with Cox univariate and multivariate analyses identifying prognostic factors. Risk classifications were established using classification and regression tree (CART) analysis. CART analysis revealed decision trees for recurrence-free survival (RFS) and overall survival (OS) and created three risk classifications based on machine learning of preoperative serum markers. Five-year rates differed significantly (p < 0.001) between groups: 60.4% (low-risk), 22.8% (moderate-risk), and 4.1% (high-risk) for RFS and 69.2% (low-risk), 32.3% (moderate-risk), and 9.2% (high-risk) for OS. No difference in OS was observed between patients in the low-risk group with or without postoperative adjuvant chemotherapy, although OS improved in the moderate group and was prolonged significantly in the high-risk group receiving chemotherapy. Stratification of patients with ICC who underwent hepatectomy into three risk groups for RFS and OS identified preoperative prognostic factors that predicted prognosis and were easy to understand and apply clinically.

The “grey” digital divide in older adults during COVID-19 in Germany: Who is most at risk?

Abstract Background During the COVID-19 pandemic, physical distancing was a recommended public health measure. For some older adults, distancing has not only been physical but also social due to a lack of access to the internet - either due to consciously opting out or lack of resources. This study aims to assess who is most at risk of not having access to the internet and the associated negative mental and physical health outcomes. Methods Participants were drawn from the 2020 German Ageing Survey (DEAS) in June and July 2020, and include community-dwelling adults above 45 years old (N = 4,823; 56.5% response rate). Two complementary analytic approaches were used to identify lack of access: logistic regression (LR) and Classification and Regression Tree (CART) analysis, using social indicators as predictors. LR provides information about main effects of the predictors; CART, through an exploratory, non-parametric procedure, illustrates the mathematical relationship of the variables. Results CART analysis revealed that the strongest discriminating factor for internet access was being over or under 75 years old (n = 3,131 Pr = 0.075 vs n = 1,545 Pr = 0.385). Moreover, for older individuals high education was a protective factor (n = 739 Pr = 0.260 vs n = 805 Pr = 0.499), while for younger individuals a monthly income of 2,000€ set the internet access cut-off point (n = 2520 Pr = 0.0504 vs n = 611 Pr = 0.177). Logistic regression revealed that gender (OR = 1.50; pv &amp;lt; 0.001), education (OR = 0.36; pv &amp;lt; 0.001), monthly income (0.93; pv &amp;lt; 0.001) and region in Germany (West-East) (OR = 2.42; pv &amp;lt; 0.001) explain 29.40% of internet access’ variance. Results are preliminary. Conclusions In times of forced physical distancing, the “grey” digital divide increases the vulnerability of disadvantaged groups. CART analysis helped identify groups at higher risk of not having access to the internet and yields the ground for tailored public health interventions. Key messages

An area under the concentration–time curve threshold as a predictor of efficacy and nephrotoxicity for individualizing polymyxin B dosing in patients with carbapenem-resistant gram-negative bacteria

BackgroundEvidence supports therapeutic drug monitoring of polymyxin B, but clinical data for establishing an area under the concentration–time curve across 24 h at steady state (AUCss,24 h) threshold are still limited. This study aimed to examine exposure–response/toxicity relationship for polymyxin B to establish an AUCss,24 h threshold in a real-world cohort of patients.MethodsUsing a validated Bayesian approach to estimate AUCss,24 h from two samples, AUCss,24 h threshold that impacted the risk of polymyxin B-related nephrotoxicity and clinical response were derived by classification and regression tree (CART) analysis and validated by Cox regression analysis and logical regression analysis.ResultsA total of 393 patients were included; acute kidney injury (AKI) was 29.0%, clinical response was 63.4%, and 30-day all-cause mortality was 35.4%. AUCss,24 h thresholds for AKI of > 99.4 mg h/L and clinical response of > 45.7 mg h/L were derived by CART analysis. Cox and logical regression analyses showed that AUCss,24 h of > 100 mg h/L was a significant predictor of AKI (HR 16.29, 95% CI 8.16–30.25, P < 0.001) and AUCss,24 h of ≥ 50 mg h/L (OR 4.39, 95% CI 2.56–7.47, P < 0.001) was independently associated with clinical response. However, these exposures were not associated with mortality. In addition, the correlation between trough concentration (1.2–2.8 mg/L) with outcomes was similar to AUCss,24 h.ConclusionsFor critically ill patients, AUCss,24 h threshold of 50–100 mg h/L was associated with decreased nephrotoxicity while assuring clinical efficacy. Therapeutic drug monitoring is recommended for individualizing polymyxin B dosing.

Narratives of the worst experiences associated with peritraumatic distress during the COVID-19 pandemic: a mixed method study in the USA and Italy

ABSTRACT Background: Although symptoms of posttraumatic stress disorder (PTSD) have been associated with the COVID-19 pandemic experiences, no study has explored yet the association of specific COVID-19 narratives with peritraumatic distress, the precursor of PTSD. Objective: To explore the worst experiences associated with peritraumatic distress during the first wave of the COVID-19 pandemic. Method: Adult residents (N = 1098), from the US (n = 741) and Italy (n = 357), completed an online survey including socio-demographic data, COVID-19-related experiences, the Peritraumatic Distress Inventory and an open question on their worst experiences during the first period of the COVID-19 pandemic (April–May 2020). A thematic content analysis (TCA) was conducted on the answers to the open question and a classification and regression tree (CART) analysis was used to identify the themes that best predicted the clinical levels of peritraumatic distress. Results: The main TCA themes related to participants’ worst COVID-19 experiences were anxiety, threat, loss, anger, stress and constriction. Threat was the most prevalent theme and correlated with experiences such as being quarantined, being infected and a loved one receiving the diagnosis. US participants’ descriptions of their worst experiences related more to life-threat and loss, while Italians reported more threat to the world, stress, social isolation, and feeling trapped. In the CART analysis, the main predictor (79.9%) was perceiving negative effects from the COVID-19 crisis. Among them, a COVID-related threat to self-experience was the most robust predictor. In its absence, being deprived of resources or experiencing high levels of anxiety were other robust predictors. Conclusions: The study provided evidence of the utility of a mixed-method approach in conceptualizing experiences associated with the COVID-19 pandemic and the risk of traumatic symptoms. Its findings may inform healthcare interventions and policies for tackling the new challenges posed by the COVID-19 pandemic. HIGHLIGHTS Clinically significant levels of peritraumatic distress symptoms were prevalent during the COVID-19 pandemic. Clinically significant levels of peritraumatic distress during the COVID-19 pandemic were related to experiences of life-threat, resource deprivation, and anxiety, cross-cutting the themes articulated by the thematic content analysis of anxiety, threat, loss, anger, stress and constriction. The US and Italian participants’ descriptions of their worst experiences differed in subtle but important ways, with Americans reporting more life-threat and losses compared to Italians reporting more threat to the world, stress, social isolation, and feelings of being trapped.

Prediction of anorectal malformations with bladder-neck/urethral-prostatic fistula using classification and regression tree analysis.

The anorectal malformations (ARMs) with bladder-neck/urethral-prostatic fistula in males are the most complex groups in ARMs. It is essential to diagnose them effectively before the primary operation for both surgical modalities and future functional prognosis can be quite different from other types. Our study aimed to develop a classification and regression tree (CART) model for the prediction of ARMs with bladder-neck/urethral-prostatic fistula. A total of 132 newborns with ARMs were included retrospectively and randomly assigned to the training sample and test sample in a 3:1 ratio. The pouch-perineum distance of ultrasound (PPDU), the pouch-perineum distance of invertogram (PPDI), and the rectum gas above the coccyx (RGAC) on the invertogram were hypothesized can serve as individual predictors. The CART analysis was used to determine the best combination of candidate predictors. The model's performance was assessed by the area under the receiver operating characteristic curve (AUC) and validated in the test sample. All three individual predictors were included in the CART model to predict the ARMs with bladder-neck/urethral-prostatic fistula in the derivation cohort with the following test characteristics (95% CI): sensitivity 75.6% (60.1 to 86.6); specificity 88.9% (76.7 to 95.4); AUC 0.909 (0.854 to 0.965). The model's predicted accuracy was validated in the test cohort (AUC=0.883). In all 132 subjects, the AUC of the tree model was significantly superior to that of the best individual index: PPDU (0.901 vs. 0.819; p=0.005). A predictive model that consists of PPDU, PPDI, and RGAC may be useful in predicting ARMs with bladder-neck/urethral-prostatic fistula.

Why Do Some Patients Have Severe Sacroiliac Disease But No Syndesmophytes in Ankylosing Spondylitis? Data From a Nested Case-Control Study.

Sacroiliac (SI) joint and spinal inflammation are characteristic of ankylosing spondylitis (AS), but some patients with AS have been identified who have discordant radiographic disease. We studied an AS subgroup with long-standing disease and fused SI joints. We identified factors associated with discrepant degrees of radiographic damage between the SI joints and spine. From the Prospective Study of Outcomes in AS (PSOAS) cohort, patients with a disease duration ≥ 20 years and fused SI joints were included in a nested case-control design. Patients with and without syndesmophytes were used as cases and controls for analysis. We used classification and regression tree (CART) analysis to determine risk factors for syndesmophytes presence and reexamined the validity of the risk factors using univariable logistic regression models. There were 354 patients in the subgroup, 23 of whom lacked syndesmophytes. CART analysis showed females were less likely to have syndesmophytes. The next important predictor was age of symptom onset in males, with age of onset ≤ 16 years being less likely to have syndesmophytes. Univariable analysis confirmed females were less likely to have syndesmophytes (odds ratio [OR] 0.17, 95% CI 0.07-0.41). Syndesmophyte presence was associated with HLA-B27 positivity (P = 0.03) and age of symptom onset > 16 years old (OR 2.72, 95% CI 1.15-6.45). All 23 patients who lacked syndesmophytes were HLA-B27 positive. Using CART analysis and univariable modeling, women were less likely to have syndesmophytes despite advanced disease duration and SI joint disease. Patients with younger age of symptom onset were less likely to have syndesmophytes. All patients without syndesmophytes were HLA-B27 positive, indicating HLA-B27 positivity may be more associated with SI disease than spinal disease.

Clinical Variables Associated with Pre-Fontan Aortopulmonary Collateral Burden.

Aortopulmonary collaterals (APCs) develop universally, but to varying degrees, in patients with single ventricle congenital heart disease (CHD). Despite their ubiquitous presence, APCs remain poorly understood. We sought to evaluate the association between APC burden and common non-invasive clinical variables. We conducted a single center, retrospective study of patients with single ventricle CHD and previous Glenn palliation who underwent pre-Fontan cardiac magnetic resonance (CMR) imaging from 3/2018 to 3/2021. CMR was used to quantify APC flow, which was normalized to aortic (APC/QAo) and pulmonary vein (APC/QPV) blood flow. Univariate, multivariable, and classification and regression tree (CART) analyses were done to investigate the potential relationship between CMR-quantified APC burden and clinical variables. A total of 29 patients were included, all of whom had increased APC flow (APC/QAo: 26.9, [22.0, 39.1]%; APC/QPV: 39.4 [33.3, 46.9]%), but to varying degrees (APC/QAo: range 11.9-44.4%; APC/QPV: range 17.7-60.0%). Pulmonary artery size (Nakata index, at pre-Fontan CMR) was the only variable associated with APC flow on multivariable analysis (APC/QAo: p = 0.020, R2 = 0.19; APC/QPV: p = 0.0006, R2 = 0.36) and was the most important variable associated with APC burden identified by CART analysis (size inversely related to APC flow). APC flow is universally increased but highly variable in patients with single ventricle CHD and Glenn circulation. Small branch pulmonary artery size is a key factor associated with increased APC burden; however, the pathogenesis of APCs is likely multifactorial. Further research is needed to better understand APC pathogenesis, including predisposing and mitigating factors.

A Practical Risk Classification of Early Recurrence in Hepatocellular Carcinoma Patients with Microvascular invasion after Hepatectomy: A Decision Tree Analysis.

This study was designed to establish risk classifications for early recurrence in hepatocellular carcinoma (HCC) patients with microvascular invasion (MVI) after hepatectomy. The data of 563 HCC patients with MVI after hepatectomy from two hospitals were retrospectively reviewed. Kaplan-Meier curves and Cox proportional hazards regression models were used to analyse early recurrence. The risk classification for early recurrence was established by using classification and regression tree (CART) analysis and validated by using two independent validation cohorts from two hospitals. Multivariate analysis revealed that four indices, namely, infection of chronic viral hepatitis, MVI classification, tumour size, and serum alpha-fetoprotein (AFP), were independent prognostic factors for early recurrence in HCC patients with MVI. By CART analysis, MVI classification and serum AFP became the nodes of a decision tree and 3-stratification classifications that satisfactorily determined the risk of early recurrence were established. The area under the time-dependent receiver operating characteristic curve (AUC) values of the classification for early recurrence at 0.5, 1.0, and 2.0 years were 0.75, 0.73, and 0.71, respectively, which were all significantly higher than three common classic HCC stages (BCLC stage, Chinese stage, and TNM stage). The calibration curves showed good agreement between predictions by classification for early recurrence and actual survival outcomes. These prediction results also were confirmed in the independent internal and external validation cohorts. The 3 stratification classifications enabled satisfactory risk evaluation of early recurrence in HCC patients with MVI after hepatectomy.

Chronic Care for All? The Intersecting Roles of Race and Immigration in Shaping Multimorbidity, Primary Care Coordination, and Unmet Health Care Needs Among Older Canadians.

Despite the predominance of chronic disease clustering, primary care delivery for multimorbid patients tends to be less effective and often uncoordinated. This study aims to quantify racial-nativity inequalities in multimorbidity prevalence ≥3 chronic conditions), access to primary care, and relations to past-year subjective unmet health care needs (SUN) among older Canadians. Population-based data were drawn from the Canadian Community Health Survey (2015-2018). Multivariable logistic regression was performed to estimate the likelihood of multimorbidity, sites of usual source of primary care (USOC), primary care coordination, and multidimensional aspects of SUN. The Classification and Regression Tree (CART) was applied to identify intersecting determinants of SUN. The overall sample (n = 19,020) were predominantly (69.4%) Canadian-born (CB) Whites (1% CB non-Whites, 18.1% White immigrants, and 11.5% racialized immigrants). Compared with CB Whites, racialized immigrants were more likely to have multimorbidity (adjusted odds ratio [AOR] = 1.35, 99% confidence interval [CI]: 1.13-1.61), lack a USOC (AOR = 1.41, 99% CI: 1.07-1.84), and report higher SUN (AOR = 1.47, 99% CI: 1.02-2.11). Racialized immigrants' greater SUN was driven by heightened affordability barriers (AOR = 4.31, 99% CI: 2.02-9.16), acceptability barriers (AOR = 3.11, 99% CI: 1.90-5.10), and unmet needs for chronic care (AOR = 2.71, 99% CI: 1.53-4.80) than CB Whites. The CART analysis found that the racial-nativity gap in SUN perception was still evident even among those who had access to nonpoorly coordinated care. To achieve an equitable chronic care system, efforts need to tackle affordability barriers, improve service acceptability, minimize service fragmentation, and reallocate treatment resources to underserved older racialized immigrants in Canada.

An application of CART algorithms for detection of an association between VDR polymorphisms and reduced bone density in individuals with type 2 diabetes: a population-based cross-sectional study

Introduction: An important part of preventing major common diseases is identifying genetic factors that contribute to their occurrence. For the first time in our knowledge, we investigated the association between five polymorphisms of vitamin D receptor (VDR) gene (ApaI, BsmI, FokI, EcoRV, and TaqI) and low bone density/osteopenia/osteoporosis in individuals with type 2 diabetes using classification and regression tree (CART) algorithms. Methods: Data from 158 participants with T2D were used to develop the CART analysis. The binary output variable was "bone state" with low or normal values. Age and BMI (continuous variables), vitamin D deficiency (yes/no), and gender (binary variables), as well as the studied polymorphism of the VDR gene (categorical variables) all played a role in the explanatory model. A 5-fold cross-validation process was used for model validation. Results: Participants were divided into three groups: men, women, and both sexes. In all groups, age was the major factor predicting the low state in the final obtained tree model. The second most significant predictor in each model was BMI in both sexes (accuracy:75.30% ± 2.80%, AUC: 0.740 ± 0.064), EcoRV polymorphism in women (accuracy: 80.79% ± 6.58%, AUC:0.785 ± 0.063), and TaqI polymorphism in men (accuracy: 76.36% ± 3.05%, AUC:0.706 ± 0.125). Conclusion: Model validation of the final tree models demonstrated that the use of CART algorithms could be an acceptable technique for risk factors of osteoporosis among individuals with T2D. Our recommendation is to conduct more population-based studies. We hope this study will serve as a basis for future research.