Machine Learning From Quantitative Coronary Computed Tomography Angiography Predicts Fractional Flow Reserve-Defined Ischemia and Impaired Myocardial Blood Flow.

BACKGROUND: A pathophysiological interplay exists between plaque morphology and coronary physiology. Machine learning (ML) is increasingly being applied to coronary computed tomography angiography (CCTA) for cardiovascular risk stratification. We sought to assess the performance of a ML score integrating CCTA-based quantitative plaque features for predicting vessel-specific ischemia by invasive fractional flow reserve (FFR) and impaired myocardial blood flow (MBF) by positron emission tomography (PET). METHODS: This post-hoc analysis of the PACIFIC trial (Prospective Comparison of Cardiac Positron Emission Tomography/Computed Tomography [CT]' Single Photon Emission Computed Tomography/CT Perfusion Imaging and CT Coronary Angiography with Invasive Coronary Angiography) included 208 patients with suspected coronary artery disease who prospectively underwent CCTA' [15O]H2O PET, and invasive FFR. Plaque quantification from CCTA was performed using semiautomated software. An ML algorithm trained on the prospective NXT trial (484 vessels) was used to develop a ML score for the prediction of ischemia (FFR≤0.80), which was then evaluated in 581 vessels from the PACIFIC trial. Thereafter, the ML score was applied for predicting impaired hyperemic MBF (≤2.30 mL/min per g) from corresponding PET scans. The performance of the ML score was compared with CCTA reads and noninvasive FFR derived from CCTA (FFRCT). RESULTS: One hundred thirty-nine (23.9%) vessels had FFR-defined ischemia, and 195 (33.6%) vessels had impaired hyperemic MBF. For the prediction of FFR-defined ischemia, the ML score yielded an area under the receiver-operating characteristic curve of 0.92, which was significantly higher than that of visual stenosis grade (0.84; P<0.001) and comparable with that of FFRCT (0.93; P=0.34). Quantitative percent diameter stenosis and low-density noncalcified plaque volume had the greatest ML feature importance for predicting FFR-defined ischemia. When applied for impaired MBF prediction, the ML score exhibited an area under the receiver-operating characteristic curve of 0.80; significantly higher than visual stenosis grade (area under the receiver-operating characteristic curve 0.74; P=0.02) and comparable with FFRCT (area under the receiver-operating characteristic curve 0.77; P=0.16). CONCLUSIONS: An externally validated ML score integrating CCTA-based quantitative plaque features accurately predicts FFR-defined ischemia and impaired MBF by PET, performing superiorly to standard CCTA stenosis evaluation and comparably to FFRCT.

Handling missing values in machine learning to predict patient-specific risk of adverse cardiac events: Insights from REFINE SPECT registry.

BACKGROUND: Machine learning (ML) models can improve prediction of major adverse cardiovascular events (MACE), but in clinical practice some values may be missing. We evaluated the influence of missing values in ML models for patient-specific prediction of MACE risk. METHODS: We included 20,179 patients from the multicenter REFINE SPECT registry with MACE follow-up data. We evaluated seven methods for handling missing values: 1) removal of variables with missing values (ML-Remove), 2) imputation with median and unique category for continuous and categorical variables, respectively (ML-Traditional), 3) unique category for missing variables (ML-Unique), 4) cluster-based imputation (ML-Cluster), 5) regression-based imputation (ML-Regression), 6) missRanger imputation (ML-MR), and 7) multiple imputation (ML-MICE). We trained ML models with full data and simulated missing values in testing patients. Prediction performance was evaluated using area under the receiver-operating characteristic curve (AUC) and compared with a model without missing values (ML-All), expert visual diagnosis and total perfusion deficit (TPD). RESULTS: During mean follow-up of 4.7 ± 1.5 years, 3,541 patients experienced at least one MACE (3.7% annualized risk). ML-All (reference model-no missing values) had AUC 0.799 for MACE risk prediction. All seven models with missing values had lower AUC (ML-Remove: 0.778, ML-MICE: 0.774, ML-Cluster: 0.771, ML-Traditional: 0.771, ML-Regression: 0.770, ML-MR: 0.766, and ML-Unique: 0.766; p < 0.01 for ML-Remove vs remaining methods). Stress TPD (AUC 0.698) and visual diagnosis (0.681) had the lowest AUCs. CONCLUSION: Missing values reduce the accuracy of ML models when predicting MACE risk. Removing variables with missing values and retraining the model may yield superior patient-level prediction performance.

Determining a minimum set of variables for machine learning cardiovascular event prediction: results from REFINE SPECT registry.

AIMS: Optimal risk stratification with machine learning (ML) from myocardial perfusion imaging (MPI) includes both clinical and imaging data. While most imaging variables can be derived automatically, clinical variables require manual collection, which is time-consuming and prone to error. We determined the fewest manually input and imaging variables required to maintain the prognostic accuracy for major adverse cardiac events (MACE) in patients undergoing a single-photon emission computed tomography (SPECT) MPI. METHODS AND RESULTS: This study included 20 414 patients from the multicentre REFINE SPECT registry and 2984 from the University of Calgary for training and external testing of the ML models, respectively. ML models were trained using all variables (ML-All) and all image-derived variables (including age and sex, ML-Image). Next, ML models were sequentially trained by incrementally adding manually input and imaging variables to baseline ML models based on their importance ranking. The fewest variables were determined as the ML models (ML-Reduced, ML-Minimum, and ML-Image-Reduced) that achieved comparable prognostic performance to ML-All and ML-Image. Prognostic accuracy of the ML models was compared with visual diagnosis, stress total perfusion deficit (TPD), and traditional multivariable models using area under the receiver-operating characteristic curve (AUC). ML-Minimum (AUC 0.798) obtained comparable prognostic accuracy to ML-All (AUC 0.799, P = 0.19) by including 12 of 40 manually input variables and 11 of 58 imaging variables. ML-Reduced achieved comparable accuracy (AUC 0.796) with a reduced set of manually input variables and all imaging variables. In external validation, the ML models also obtained comparable or higher prognostic accuracy than traditional multivariable models. CONCLUSION: Reduced ML models, including a minimum set of manually collected or imaging variables, achieved slightly lower accuracy compared to a full ML model but outperformed standard interpretation methods and risk models. ML models with fewer collected variables may be more practical for clinical implementation.

Diagnostic safety of a machine learning-based automatic patient selection algorithm for stress-only myocardial perfusion SPECT.

BACKGROUND: Stress-only myocardial perfusion imaging (MPI) markedly reduces radiation dose, scanning time, and cost. We developed an automated clinical algorithm to safely cancel unnecessary rest imaging with high sensitivity for obstructive coronary artery disease (CAD). METHODS AND RESULTS: Patients without known CAD undergoing both MPI and invasive coronary angiography from REFINE SPECT were studied. A machine learning score (MLS) for prediction of obstructive CAD was generated using stress-only MPI and pre-test clinical variables. An MLS threshold with a pre-defined sensitivity of 95% was applied to the automated patient selection algorithm. Obstructive CAD was present in 1309/2079 (63%) patients. MLS had higher area under the receiver operator characteristic curve (AUC) for prediction of CAD than reader diagnosis and TPD (0.84 vs 0.70 vs 0.78, P < .01). An MLS threshold of 0.29 had superior sensitivity than reader diagnosis and TPD for obstructive CAD (95% vs 87% vs 87%, P < .01) and high-risk CAD, defined as stenosis of the left main, proximal left anterior descending, or triple-vessel CAD (sensitivity 96% vs 89% vs 90%, P < .01). CONCLUSIONS: The MLS is highly sensitive for prediction of both obstructive and high-risk CAD from stress-only MPI and can be applied to a stress-first protocol for automatic cancellation of unnecessary rest imaging.

Comparación del ángulo de la guía condílea sagital obtenida del registro radiográfico y clínico en pacientes dentados / Comparison of sagittal condylar guidance obtained from radiographic and and clinical records in dentate patients

Objetivo: Comparar el ángulo de la guía condílea sagital obtenida del registro radiográfico y clínico en pacientes dentados. Materiales y métodos: La muestra estuvo conformada por un grupo único de estudio de 32 pacientes, en el que se evaluó la radiografía lateral estricta y los registros posicionales: en relación céntrica, registro protrusivo a 5 mm en lateralidad derecha y registro protrusivo a 5 mm en lateralidad izquierda. Con el registro posicional del arco facial se articuló el modelo superior, con el registro posicional en relación céntrica se articuló el modelo inferior, con los registros laterales protrusivos de los lados derecho e izquierdo se obtuvo la medida del ángulo de la guía condílea sagital para la programación del articulador semiajustable. El plan estadístico en la presente investigación utilizó el programa SPSS versión 24, la normalidad fue evaluada usando el test de Shapiro-Wilk, también se realizaron las pruebas de T de Student y correlación de Pearson. Resultados: Se determinó estadísticamente que el género y la edad influyen en la medida del ángulo de la guía condílea sagital. El método radiográfico presentó un ángulo de guía condílea de 35,69 ±5,18 y con el método clínico fue 35,69 ± 5,16 (p > 0,05). La prueba de correlación de Pearson sí mostró una correlación importante entre ambos métodos r = 0,948, p < 0,001. Conclusiones: Existe alta correlación en las medidas obtenidas del ángulo de la guía condílea sagital con los registros radiográficos y clínicos; esta concordancia permitiría reemplazar un método por el otro. (AU)

Objective: To compare the angle of the sagittal condylar guidance obtained from the radiographic and clinical records of dentate patients. Materials and Methods: The sample consisted of 32 patients in whom strict lateral radiography and positional records were performed: in centric relation, protrusive recording 5 mm in right laterality and protrusive recording 5 mm in left laterality. With the positional registration of the facebow, the upper model was articulated, while the lower model was articulated with the positional registration in centric relation, and with the protrusive lateral registrations on the right and left side the condylar guidance was obtained for programming the semi-adjustable articulator. Statistics were performed with the SPSS program version 24 in Spanish. Normality was evaluated using the Shapiro-Wilk test, for data with normal distribution, and the Student's T test and Pearson's correlation were performed in descriptive statistics. Results: The statistical analyses showed that gender and age influence the angle measurement of the sagittal condylar guide. The radiographic method presented a condylar guide angle of 35.69 ± 5.18, being 35.69 ± 5.16 with the clinical method (p> 0.05). Pearson's correlation test showed an important correlation between the two methods (r = 0.948, p <0.001). Conclusions: There is a high correlation in the measurements obtained from the angle of the sagittal condylar guide and the radiographic and clinical records, indicating that both methods are effective. (AU)

Prognostically safe stress-only single-photon emission computed tomography myocardial perfusion imaging guided by machine learning: report from REFINE SPECT.

AIMS: Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) stress-only protocols reduce radiation exposure and cost but require clinicians to make immediate decisions regarding rest scan cancellation. We developed a machine learning (ML) approach for automatic rest scan cancellation and evaluated its prognostic safety. METHODS AND RESULTS: In total, 20 414 patients from a solid-state SPECT MPI international multicentre registry with clinical data and follow-up for major adverse cardiac events (MACE) were used to train ML for MACE prediction as a continuous probability (ML score), using 10-fold repeated hold-out testing to separate test from training data. Three ML score thresholds (ML1, ML2, and ML3) were derived by matching the cancellation rates achieved by physician interpretation and two clinical selection rules. Annual MACE rates were compared in patients selected for rest scan cancellation between approaches. Patients selected for rest scan cancellation with ML had lower annualized MACE rates than those selected by physician interpretation or clinical selection rules (ML1 vs. physician interpretation: 1.4 ± 0.1% vs. 2.1 ± 0.1%; ML2 vs. clinical selection: 1.5 ± 0.1% vs. 2.0 ± 0.1%; ML3 vs. stringent clinical selection: 0.6 ± 0.1% vs. 1.7 ± 0.1%, all P < 0.0001) at matched cancellation rates (60 ± 0.7, 64 ± 0.7, and 30 ± 0.6%). Annualized all-cause mortality rates in populations recommended for rest cancellation by physician interpretation, clinical selection approaches were higher (1.3%, 1.2%, and 1.0%, respectively) compared with corresponding ML thresholds (0.6%, 0.6%, and 0.2%). CONCLUSION: ML, using clinical and stress imaging data, can be used to automatically recommend cancellation of rest SPECT MPI scans, while ensuring higher prognostic safety than current clinical approaches.

Machine Learning Adds to Clinical and CAC Assessments in Predicting 10-Year CHD and CVD Deaths.

OBJECTIVES: The aim of this study was to evaluate whether machine learning (ML) of noncontrast computed tomographic (CT) and clinical variables improves the prediction of atherosclerotic cardiovascular disease (ASCVD) and coronary heart disease (CHD) deaths compared with coronary artery calcium (CAC) Agatston scoring and clinical data. BACKGROUND: The CAC score provides a measure of the global burden of coronary atherosclerosis, and its long-term prognostic utility has been consistently shown to have incremental value over clinical risk assessment. However, current approaches fail to integrate all available CT and clinical variables for comprehensive risk assessment. METHODS: The study included data from 66,636 asymptomatic subjects (mean age 54 ± 11 years, 67% men) without established ASCVD undergoing CAC scanning and followed for cardiovascular disease (CVD) and CHD deaths at 10 years. Clinical risk assessment incorporated the ASCVD risk score. For ML, an ensemble boosting approach was used to fit a predictive classifier for outcomes, followed by automated feature selection using information gain ratio. The model-building process incorporated all available clinical and CT data, including the CAC score; the number, volume, and density of CAC plaques; and extracoronary scores; comprising a total of 77 variables. The overall proposed model (ML all) was evaluated using a 10-fold cross-validation framework on the population data and area under the curve (AUC) as metrics. The prediction performance was also compared with 2 traditional scores (ASCVD risk and CAC score) and 2 additional models that were trained using all the clinical data (ML clinical) and CT variables (ML CT). RESULTS: The AUC by ML all (0.845) for predicting CVD death was superior compared with those obtained by ASCVD risk alone (0.821), CAC score alone (0.781), and ML CT alone (0.804) (p < 0.001 for all). Similarly, for predicting CHD death, AUC by ML all (0.860) was superior to the other analyses (0.835 for ASCVD risk, 0.816 for CAC, and 0.827 for ML CT; p < 0.001). CONCLUSIONS: The comprehensive ML model was superior to ASCVD risk, CAC score, and an ML model fitted using CT variables alone in the prediction of both CVD and CHD death.

[Comparison of sagittal condylar guidance obtained from radiographic and clinical records in dentate patients]. / Comparación del ángulo de la guía condílea sagital obtenida del registro radiográfico y clínico en pacientes dentados.

Objective: To compare the angle of the sagittal condylar guidance obtained from the radiographic and clinical records of dentate patients. Materials and Methods: The sample consisted of 32 patients in whom strict lateral radiography and positional records were performed: in centric relation, protrusive recording 5 mm in right laterality and protrusive recording 5 mm in left laterality. With the positional registration of the facebow, the upper model was articulated, while the lower model was articulated with the positional registration in centric relation, and with the protrusive lateral registrations on the right and left side the condylar guidance was obtained for programming the semi-adjustable articulator. Statistics were performed with the SPSS program version 24 in Spanish. Normality was evaluated using the Shapiro-Wilk test, for data with normal distribution, and the Student's T test and Pearson's correlation were performed in descriptive statistics. Results: The statistical analyses showed that gender and age influence the angle measurement of the sagittal condylar guide. The radiographic method presented a condylar guide angle of 35.69 ± 5.18, being 35.69 ± 5.16 with the clinical method (p> 0.05). Pearson's correlation test showed an important correlation between the two methods (r = 0.948, p <0.001). Conclusions: There is a high correlation in the measurements obtained from the angle of the sagittal condylar guide and the radiographic and clinical records, indicating that both methods are effective.

Population model of bladder motion and deformation based on dominant eigenmodes and mixed-effects models in prostate cancer radiotherapy.

In radiotherapy for prostate cancer irradiation of neighboring organs at risk may lead to undesirable side-effects. Given this setting, the bladder presents the largest inter-fraction shape variations hampering the computation of the actual delivered dose vs. planned dose. This paper proposes a population model, based on longitudinal data, able to estimate the probability of bladder presence during treatment, using only the planning computed tomography (CT) scan as input information. As in previously-proposed principal component analysis (PCA) population-based models, we have used the data to obtain the dominant eigenmodes that describe bladder geometric variations between fractions. However, we have used a longitudinal analysis along each mode in order to properly characterize patient's variance from the total population variance. We have proposed is a mixed-effects (ME) model in order to separate intra- and inter-patient variability, in an effort to control confounding cohort effects. Other than using PCA, bladder shapes are represented by using spherical harmonics (SPHARM) that additionally enables data compression without information lost. Based on training data from repeated CT scans, the ME model was thus implemented following dimensionality reduction by means of SPHARM and PCA. We have evaluated the model in a leave-one-out cross validation framework on the training data but also using independent data. Probability maps (PMs) were thus generated with several draws from the learnt model as predicted regions where the bladder will likely move and deform. These PMs were compared with the actual regions using metrics based on mutual information distance and misestimated voxels. The prediction was also compared with two previous population PCA-based models. The proposed model was able to reduce the uncertainties in the estimation of the probable region of bladder motion and deformation. This model can thus be used for tailoring radiotherapy treatments.

A tensor-based population value decomposition to explain rectal toxicity after prostate cancer radiotherapy.

In prostate cancer radiotherapy the association between the dose distribution and the occurrence of undesirable side-effects is yet to be revealed. In this work a method to perform population analysis by comparing the dose distributions is proposed. The method is a tensor-based approach that generalises an existing method for 2D images and allows for the highlighting of over irradiated zones correlated with rectal bleeding after prostate cancer radiotherapy. Thus, the aim is to contribute to the elucidation of the dose patterns correlated with rectal toxicity. The method was applied to a cohort of 63 patients and it was able to build up a dose pattern characterizing the difference between patients presenting rectal bleeding after prostate cancer radiotherapy and those who did not.

A multistate outbreak of Escherichia coli O157:H7 infection linked to consumption of beef tacos at a fast-food restaurant chain.

We investigated a multistate outbreak of Escherichia coli O157:H7 infections. Isolates from 13 case patients from California, Nevada, and Arizona were matched by pulsed-field gel electrophoresis subtyping. Five case patients (38%) were hospitalized, and 3 (23%) developed hemolytic uremic syndrome; none died. The median age was 12 years (range, 2-75 years), and 10 (77%) were female. Case-control studies found an association between illness and eating beef tacos at a national Mexican-style fast-food restaurant chain (88% of cases versus 38% of controls; matched OR, undefined; 95% confidence interval, 1.49 to infinity; P=.009). A trace-back investigation implicated an upstream supplier of beef, but a farm investigation was not possible. This outbreak illustrates the value of employing hospital laboratory-based surveillance to detect local clusters of infections and the effectiveness of using molecular subtyping to identify geographically dispersed outbreaks. The outbreak investigation also highlights the need for a more efficient tracking system for food products.

An outbreak of food-borne illness associated with methomyl-contaminated salt.

CONTEXT: On January 5, 1999, the California Department of Health Services was notified of the repeated occurrence (December 21, 1998, and January 2, 1999) of gastrointestinal tract illness among patrons at a Thai restaurant in central California. OBJECTIVE: To identify the source of the outbreak. DESIGN: Case-control study; microbiological and toxicological laboratory testing of samples of food, stool, and vomitus. SETTING: Thai food restaurant in central California. PARTICIPANTS: Patrons of the restaurant. A case (n = 107) was defined as dizziness, nausea, or vomiting occurring in a person who ate at the restaurant between December 20, 1998, and January 2, 1999, with onset of symptoms within 2 hours of eating. A control (n = 169) was a person who ate at the restaurant during the same period but reported no symptoms. MAIN OUTCOME MEASURES: Odds ratios (ORs) of illness associated with food exposures; ORs of shifts during which illness occurred associated with certain cooks; laboratory results. RESULTS: The median latency period was 40 minutes from beginning eating to first symptom and was 2 hours to onset of diarrhea. The median duration of symptoms was 6 hours. Twenty-six persons (24%) visited the emergency department or were treated by a physician; no person required hospitalization. Patients reported nausea (95%), dizziness (72%), abdominal cramps (58%), headache (52%), vomiting (51%), chills (48%), and diarrhea (46%). Fifty-one cases (48%) included dizziness, lightheadedness, or a feeling of disequilibrium as the initial symptom. Illness was statistically associated with several foods and ingredients, but no single dish or ingredient explained a substantial number of cases. The analysis of food exposures included salt added by cooks, as estimated by using the amount of salt in the recipe for each dish and the amount of each dish eaten by respondents. This association was stronger with increasing levels of salt: ORs for illness among persons who consumed more than 0.42 to 0.84, more than 0.84 to 1.25, and more than 1.25 tsp of salt added to foods in the kitchen were 1.9 (95% confidence interval [CI], 0.6-5.7), 3.0 (95% CI, 1.0-8.8), and 4.0 (95% CI, 1.3-13.5) compared with persons who consumed less than 0.42 tsp (P value for trend =.004). Methomyl, a highly toxic carbamate pesticide, was identified in a sample of vomitus (20 ppm) and in salt taken from containers in the storeroom (mean, 5600 ppm) and the stovetop (mean, 1425 ppm). The oral toxic dose causing illness in 50% of those exposed to methomyl was estimated to be 0.15 mg/kg of body weight (estimated range, 0.09-0.31 mg/kg of body weight). The presence of cook A was associated with shifts during which cases of illness occurred (OR, 10.4; 95% CI, 1.2-157.4). CONCLUSION: This outbreak of gastrointestinal illness was associated with the consumption of food seasoned with methomyl-contaminated salt. To allow rapid assessment for further investigational and control measures by health officials, physicians should report suspected outbreaks of illness to public health departments, however trivial the symptoms or cause may seem.

Immunogenicity and reactogenicity of combined versus separately administered DTPw-HBV and Hib vaccines given to healthy infants at 2, 4 and 6 months of age, with a booster at 18 months.

OBJECTIVES: To determine the immunogenicity and reactogenicity of a combined DTPw-HBV/Hib vaccine, in comparison with DTPw-HBV and Hib vaccines given as separate concomitant injections. METHODS: In an open, randomized study, healthy infants were injected with either DTPw-HBV/Hib vaccine or separate DTPw-HBV and Hib vaccines at 2, 4 and 6 months of age, with a booster at 18 months. RESULTS: Both vaccination regimens were immunogenic, with seropositivity rates of 100% after the booster vaccination for all vaccine components. Even as early as 2 months after the second dose of the primary vaccination, most patients had seroprotective antibody titers, the proportion of seropositive subjects approaching 100% for tetanus, hepatitis B, and Hib. Post-primary and post-booster geometric mean titers (GMTs) were well above seroprotective thresholds for each vaccine antigen in both groups, with no clinically relevant differences in the groups. The separate and combined administrations showed comparable reactogenicity profiles, and neither showed a significant increase in reactogenicity with successive doses. CONCLUSIONS: The results of this study support the combination of Hib and DTPw-HBV vaccination in routine infant immunization at 2, 4 and 6 months of age with a booster at 18 months. Maximum benefit is obtained from compliance with the full course, but substantial benefit is likely to be achieved even in partially compliant patients, provided they receive at least two doses. Furthermore, these results demonstrate the tolerability of a fourth (booster) administration, where the addition of the Hib vaccine to DTPw-HBV did not lead to an increase in the overall reactogenicity.

Infectoepidemiologic and immunologic implications of Campylobacter coli enteritis in one newborn monozygotic twin pair

Como as características clínicas da infecçäo humana por campylobacter em pacientes recém-nascidos näo estäo ainda bem documentadas, considerou-se interessante comunicar a ocorrência de dois casos simultâneos de enterite por C. coli em gêmeos monozigotos. Discute-se a história clínica, os aspectos epidemiológicos e microbiológicos, o desenvolvimento de imunidade bem cocmo a síntese de Ig totais, tendo em consideraçäo as estreitas relaçöes genético-ecológicas destes dois casos

Infecciones sistémicas por haemophilus influenzae resistentes a ampicilina y cloramfenicol: comunicación de cinco casos / Systemic infections by haemophilus influenzae resistant to ampicillin and chloramphenicol: communication of 5 cases

Se comunican cinco casos detectados en los últimos 3 añosde infecciones sistémicas producidas por H.Influenzae resistentes a ampicilina ycloramfenicol, en el Servicio de Pediatría del Hospital Reginal de Valdivia