Machine learning and LACE index for predicting 30-day readmissions after heart failure hospitalization in elderly patients.

Machine learning (ML) techniques may improve readmission prediction performance in heart failure (HF) patients. This study aimed to assess the ability of ML algorithms to predict unplanned all-cause 30-day readmissions in HF elderly patients, and to compare them with conventional LACE (Length of hospitalization, Acuity, Comorbidities, Emergency department visits) index. All patients aged ≥ 65 years discharged alive between 2010 and 2019 after a hospitalization for acute HF were included in this retrospective cohort study. We applied MICE (Multivariate Imputation via Chained Equations) method to obtain a balanced, fully valued dataset and LASSO (Least Absolute Shrinkage and Selection Operator) algorithm to get the most significant features. Training (80% of records) and test (20%) cohorts were randomly selected. Study population: 3079 patients, 394 (12.8%) presented at least one readmission within 30 days, and 2685 (87.2%) did not. In the test cohort AUCs (IC95%) of XGBoost, Ada Boost Classifier, Random forest, and Gradient Boosting, and LACE Index were: 0.803 (0.734-0.872), 0.782 (0.711-0.854), 0.776 (0.703-0.848), 0.786 (0.715-0.857), and 0.504 (0.414-0.594), respectively, for predicting readmissions. A SHAP analysis was performed to offer a breakdown of the ML variables associated with readmission. Positive and negative predicting values estimates of the different ML models and LACE index were also provided, for several values of readmission rate prevalence. Among elderly patients, the rate of all-cause unplanned 30-day readmissions after hospitalization due to an acute HF was high. ML models performed better than the conventional LACE index for predicting readmissions. ML models can be proposed as promising tools for the identification of subjects at high risk of hospitalization in this clinical setting, enabling care teams to target interventions for improving overall clinical outcomes.

Acute pulmonary embolism in patients presenting pulmonary deterioration after hospitalisation for non-critical COVID-19.

BACKGROUND: Emerging evidence suggests an association between COVID-19 and acute pulmonary embolism (APE). AIMS: To assess the prevalence of APE in patients hospitalised for non-critical COVID-19 who presented clinical deterioration, and to investigate the association of clinical and biochemical variables with a confirmed diagnosis of APE in these subjects. METHODS: All consecutive patients admitted to the internal medicine department of a general hospital with a diagnosis of non-critical COVID-19, who performed a computer tomography pulmonary angiography (CTPA) for respiratory deterioration in April 2020, were included in this retrospective cohort study. RESULTS: Study populations: 41 subjects, median (interquartile range) age: 71.7 (63-76) years, CPTA confirmed APE = 8 (19.51%, 95% confidence interval (CI): 8.82-34.87%). Among patients with and without APE, no significant differences were found with regards symptoms, comorbidities, treatment, Wells score and outcomes. The optimal cut-off value of d-dimer for predicting APE was 2454 ng/mL, sensitivity (95% CI): 63 (24-91), specificity: 73 (54-87), positive predictive value: 36 (13-65), negative predictive value: 89 (71-98) and AUC: 0.62 (0.38-0.85). The standard and age-adjusted d-dimer cut-offs, and the Wells score ≥2 did not associate with confirmed APE, albeit a cut-off value of d-dimer = 2454 ng/mL showed an relative risk: 3.21; 95% CI: 0.92-13.97; P = 0.073. Heparin at anticoagulant doses was used in 70.73% of patients before performing CTPA. CONCLUSION: Among patients presenting pulmonary deterioration after hospitalisation for non-critical COVID-19, the prevalence of APE is high. Traditional diagnostic tools to identify high APE pre-test probability patients do not seem to be clinically useful. These results support the use of a high index of suspicion for performing CTPA to exclude or confirm APE as the most appropriate diagnostic approach in this clinical setting.

Predictors of medium- and long-term mortality in elderly patients with acute pulmonary embolism.

INTRODUCTION: Data on medium- and long-term prognostic factors for death in elderly patients with acute Pulmonary Embolism (APE) are lacking. The present study aimed to assess sPESI score and the Charlson Comorbidity Index (CCI) as medium- and long-term predictors of mortality in elderly patients with haemodinamically stable APE. METHODS: All consecutive patients aged≥65 years old, evaluated at the emergency department (ED) of our hospital from 2010 through 2014, with a final diagnosis of APE, were included in this retrospective cohort study. RESULTS: Study population:162 patients, female:36.5%, median age:79 years old, 74% presented a sPESI score>0, and 61% a CCI≥ 1. All causes mortality: 19.8%, 23.5%, 26.5%, 32.1% and 48.2% at 3, 6 months, 1, 2 and 5 years after APE. Univariate regression analysis: CCI≥1 was associated with a higher mortality at 3, 6 months, 1, 2 and 5 years. Multivariate Cox analysis: CCI≥1 associated with increased mortality at 3 months (HR:4.29; IC95%:1.46-12.59), 6 months (HR:5.33; IC95%:1.84-15.44), 1 year (HR:4.87; IC95%:1.87-12.70), 2 years (HR:3.78; IC95%:1.74-8.25), and 5 years (HR:2.30; IC95%:1.33-3.99). sPESI score≥1 was not found to be related to an increased medium-or long-term mortality. Negative predictive values (IC95%) of CCI≥1 were 93.65% (87.61-99.69), 93.65% (87.61-99.69), 92.06% (85.37-98.76), 87.3% (79.05-95.55) and 71.61% (60.13-83.1) for mortality at 3, 6 months, 1, 2 and 5 years. CONCLUSION: In elderly patients with a confirmed normotensive APE, unlike sPESI score, CCI showed to be an independent prognostic factor for medium- and long-term mortality. In these patients, after the acute phase following a PE event, the assessment of the comorbidities burden represents the most appropriate approach for predicting medium- and long-term mortality.

Simultaneous validation of the SunTech CT40 automated blood pressure measurement device by the 1993 British Hypertension Society protocol and the Association for the Advancement of Medical Instrumentation/International Organization for Standardization 81060-2: 2013 standard.

OBJECTIVE: This study aimed to perform a simultaneous, third-party, independent validation of the oscillometric SunTech CT40 device for blood pressure (BP) measurement, according to the 1993 protocol of the British Hypertension Society and the standard of the Association for the Advancement of Medical Instrumentation (AAMI)/the International Organization for Standardization (ISO) 81060-2:2013. PARTICIPANTS AND METHODS: Patient recruitment, study procedures, and data analysis followed the recommendations stated by the protocols. The study was approved by the institutional review board. RESULTS: A total of 94 participants were included, 52 (55.3%) women, mean±SD age: 63.1±18.0 years, mean±SD arm circumference: 35.0±9.0 cm. The average of observers' entry BPs was 146.9±37.2 mmHg for systolic blood pressure (SBP) and 82.2±22.1 mmHg for diastolic blood pressure (DBP). Differences between the standard measurement and the test device within 5, 10, and 15 mmHg, for the better observer, were 79.4, 96.5, and 100.0% for SBP and 82.6, 97.5, and 100.0% for DBP, respectively. The mean±SD differences between the readings obtained using the test device and those obtained by the observers (AAMI/ISO 81060-2:2013 standard criterion 1) were 0.3±5.0 mmHg (SBP) and -0.8±4.3 mmHg (DBP), and the mean±SD differences between average of reference readings and average of test device readings in each patient (criterion 2) were 0.3±3.9 and -0.8±3.5 mmHg for SBP and DBP, respectively. CONCLUSION: The CT40 BP device achieved A/A grade of the British Hypertension Society protocol and fulfilled the requirements (criteria 1 and 2) of the AAMI/ISO standard. CT40 can be recommended for BP measurement in adults.

Prognostic value of D-dimer in elderly patients with Pulmonary Embolism.

In a general population with acute Pulmonary Embolism (PE) elevated D-dimer concentrations associate with increased mortality. The aim of the study was to assess the ability of D-dimer to predict 30 and 90-days mortality in elderly patients with acute PE. Hemodynamically stable patients aged ≥65 years old with confirmed PE were included in this retrospective cohort study. A pulmonary computerized tomography angiography scan, D-dimer concentrations, simplified Pulmonary Embolism Severity Index (sPESI) variables and vital status were available for all patients. The study included 154 confirmed cases of PE (23.5 % of suspected), median age 79.1 years. D-dimer was higher in patients dead than in those alive at 30 (median 14,547 vs. 8340 ng/mL, p = 0.05) and 90 days (13,604 vs. 7973 ng/mL, p = 0.013). When adding D-dimer to sPESI, the discriminant capacity to predict mortality within 30 and 90 days was increased by 0.080 and 0.089, respectively. The contribution of D-dimer to the discriminating ability was NRI = 0.286 (95 % CI -0.198 to 0.770, p value: 0.247) at 30 days and NRI = 0.605 (95 % CI 0.223-0.988, p-value: 0.002) at 90 days.D-dimer concentration was associated with 30 and 90-days mortality and showed a higher discriminant capacity than sPESI alone to predict 90-days mortality. Adding D-dimer concentrations to sPESI score seems to improve its prognostic ability, supporting multivariable risk models as the best approach to estimate prognosis in elderly patients with PE.

Mortality at 30 and 90 days in elderly patients with pulmonary embolism: a retrospective cohort study.

Pulmonary Embolism (PE) incidence increases with age. Data on mortality and prognosis in elderly patients with suspected PE are lacking. (1) To assess 30- and 90-day mortality in subjects with PE from an elderly population seen in the emergency department (ED); (2) to test the prognostic accuracy of a simplified Pulmonary Embolism Severity Index (sPESI) coupled to a highly sensitive cardiac Troponin T (hs-cTnT) level. A retrospective cohort study was performed, including patients evaluated in the ED of Vimercate Hospital for clinically suspected PE from 2010 to 2012. Study population: n = 470, 63.4% women, mean age ± SD 73.06 ± 16.0 years, 40% aged ≥80 and 77.7% ≥65 years old, confirmed PE: 22.6% (106 cases). Within 30 and 90 days, mortality among patients with confirmed PE was 14.2% (8.8-22.0) and 20.8% (16.5-41.7). In subjects aged ≥80 years, 30-day mortality was 18.9% among patients with confirmed PE, and 12.6% among those with PE excluded (p = 0.317). Ninety-day mortality rates were 29.7 and 19.9%, respectively (p = 0.193). In patients with confirmed PE, Negative Predictive Value of sPESI was 94.1% (80.3-99.3) for 30 days and 88.2% (72.3-96.7) for 90-day mortality. Adding the hs-cTnT level to sPESI did not improve its performance. (1) In an elderly population referring to the ED with clinically suspected PE, mortality was high both in subjects with and without confirmed PE; (2) the ability of sPESI and hs-cTnT to predict PE mortality seems to be lower than reported in studies based on data from younger populations. Better risk stratification tools will be necessary to improve clinical management in this setting.

The definition of valvular and non-valvular atrial fibrillation: results of a physicians' survey.

AIMS: To assess different aspects of the definition of valvular/non-valvular atrial fibrillation (AF) used in clinical practice by physicians who usually treat this condition. METHODS AND RESULTS: We prospectively conducted a web-based survey including cardiologists and internists who attended continuing medical education courses on cardiovascular medicine. A questionnaire was drawn up, containing 17 questions clustered into five main topics: (A) known rheumatic aetiology; (B) site/type of valve involvement; (C) prosthetic heart valve; (D) haemodynamic relevance; (E) miscellaneous. The overall response rate was 22.4% (21.1% for cardiologists and 24% for internists). Coexistence of both medical history of rheumatic disease and clinical signs of valvular involvement were considered as essential prerequisites for the diagnosis of rheumatic AF by half of the respondents, and one-third assumed that lone aortic valve disease was sufficient for AF to be defined as valvular. A similar proportion of respondents considered that in the presence of mitral regurgitation, AF had to be defined as valvular. The majority of responding physicians considered the degree of valvular defect of lesser importance for the definition of valvular or non-valvular origin of AF. CONCLUSION: We found important heterogeneity and uncertainties in the answers given by physicians who usually treat patients with AF, as evidence of the lack of precise and unique definitions of the origin of AF (valvular/non-valvular). It is urgent to issue clear widely accepted definitions of the origin of AF, which should improve clinical practice and research.

A higher d-dimer threshold safely rules-out pulmonary embolism in very elderly emergency department patients.

INTRODUCTION: D-dimer is commonly used in the workup of suspected Pulmonary Embolism (PE), but its specificity decreases with age. We evaluated whether using a higher cutoff value for D-dimer could increase the test specificity without reducing its sensitivity for ruling-out PE in elderly and very elderly patients presenting to the Emergency Department (ED). MATERIAL AND METHODS: All patients with D-dimer and pulmonary Computed Tomography Angiography (CTA) performed in the ED of Vimercate Hospital, from 2010 through 2012 for clinical suspicion of PE were included in this retrospective cohort study. RESULTS: Study population 481 patients (63.4% women, mean age 73.0 ± 16.1 years, confirmed PE 22.5%). In very elderly patients (aged 80 or more years, n=191), compared with standard 490 ng/mL D-dimer threshold, both higher fixed (1000 ng/mL) and age-adjusted cutoffs increase the specificity of D-dimer for the exclusion of PE maintaining a Negative Predictive Value of 100%. Potentially avoided CTAs were 12(6.3%) using 1000 ng/mL cutoff and 10(5.2%) age-adjusted. In very elderly patients the Number Needed to Test was incalculable for the standard cutoff (0 cases), 16 for 1000 ng/mL and 19 for age-adjusted. In patients with PE, index episode mortality was 6.5%, and death occurred only in subjects with D-dimer values above 1000ng/mL and age-adjusted thresholds. CONCLUSION: For very elderly patients with suspected PE in ED, both higher fixed D-dimer (1000 ng/mL) and age-adjusted thresholds increase test specificity for excluding PE without reducing its sensitivity, leading to a safe reduction in the number of CTAs.

Simultaneous validation of the SunTech 247 diagnostic station blood pressure measurement device according to the British Hypertension Society protocol, the International Protocol and the Association for the Advancement of Medical Instrumentation standards.

OBJECTIVE: SunTech 247 is an oscillometric blood pressure (BP) monitor manufactured by SunTech Medical Inc., Morrisville, North Carolina, USA. The aims of this study were (i) to determine its accuracy using the 1993 modified British Hypertension Society (BHS) protocol, the 2002 International Protocol (IP) and the 2002/2003 Association for the Advancement of Medical Instrumentation (AAMI) standards, (ii) to compare the performance of BHS protocol and IP. METHODS: Systolic BP (SBP) and diastolic BP (DBP) were recorded to the nearest 2 mmHg and measured with the arm supported at heart level. For each participant, nine sequential same arm measurements were taken by two trained observers, comparing the device to standard mercury sphygmomanometers. Procedures and data analysis were carried out following protocols guidelines. RESULTS: First, we recruited 33 participants required by the IP. Then, data collection continued to obtain 85 participants for the BHS protocol/AAMI standard. Readings differing by less than 5, 10 and 15 mmHg for SBP and DBP fulfilled IP recommendations. According to the BHS protocol, for the better observer, the percentage of test device readings differing from the mercury standard by 5, 10 and 15 mmHg or less were: 92.9, 100 and 100% for SBP and 94.9, 98.8 and 99.6% for DBP. The mean differences +/- standard deviation between the device and mercury sphygmomanometer readings were 1.7 +/- 3.1 mmHg for SBP and 1.1 +/- 3.2 mmHg for DBP, achieving AAMI requirements. Standard deviation of mean differences were 2.4 for SBP and 2.1 for DBP, following the IP, and 3.1 and 3.2, respectively, for BHS protocol. The variance of all 99 differences (total deviance), with 98 degree of freedom, was 585.6 for SBP and 444.1 for DBP. The 33 differences obtained from the mean differences for each participant (between-subject variance), with 32 degree of freedom, were 275.6 and 152.1, respectively. F test was 1.83 with P = 0.0191 for SBP, and 1.07 (P = 0.3936) for DBP. CONCLUSION: (i) The device achieved the requirements stated by the 2002 IP, fulfilled the standards stated by the AAMI, and on the basis of the standards indicated by the 1993 modified BHS protocol, can be classified as 'A' grade both for SBP and DBP. Therefore, SunTech 247 may be recommended for clinical use, (ii) IP and BHS protocol provide complementary features for device validation; the comparison of total deviance and between-subject variance confirms the estimates of IP authors for SBP.

Accuracy evaluation of the 'Cardiette BP one' ambulatory blood pressure monitor.

OBJECTIVE: Blood pressure (BP) 'Cardiette BP one' system (BP one) is an oscillometric ambulatory BP monitor manufactured in Italy in conformity to current regulations for medical devices. We decided to determine the accuracy of measures made with BP one, using the protocol of the British Hypertension Society published in 1990, and revised in 1993, for evaluating the accuracy of BP measurement devices. METHODS: The evaluation included before-use calibration, in-use assessment, after-use calibration, and static device validation that involved 85 participants. RESULTS: The mean difference between manual readings with sphygmomanometer and automatic ones with the device were -0.36+/-5.74 (mean+/-SD) for systolic values and 2.52+/-4.87 for diastolic values. On the basis of the percentages of measurements differing from the mercury sphygmomanometer standard by

Prevalence and clinical significance of a greater ambulatory versus office blood pressure ('reversed white coat' condition) in a general population.

BACKGROUND: Attention has recently been directed to a condition termed 'reversed white coat' because of an average 24 h ambulatory blood pressure (BP) uncharacteristically greater than office BP. No data are available, however, on the prevalence of this condition in the general population, as well as on its relationship to BP, age, gender, antihypertensive treatment and cardiac organ damage. METHODS: In 3200 individuals (participation rate 64%), randomly selected to be representative of the residents of Monza (Milan, Italy) for sex and decades of age (25 to 74 years), we measured office BP (average of three measurements, sphygmomanometry), ambulatory BP (automatic readings every 20 min, Spacelabs 90207) and left ventricular mass (echocardiography). RESULTS: A 'reversed white coat' condition (identified when 24-h average ambulatory systolic, diastolic or mean were higher than the corresponding office values) was seen in 15% (diastolic) to 26% (systolic) of the population as a whole. Prevalence was greater (34-40%) when the difference between office and daytime BP was considered but in both instances it remained less than the prevalence of the white-coat phenomenon. A reversed white-coat condition was similarly frequent in males and females and showed a steep reduction with age and increasing office BP values. Prevalence was greater in hypertensive subjects in whom treatment achieved BP control than in untreated or unsatisfactorily treated individuals. Within each quartile of 24-h or office BP, left ventricular mass index adjusted for demographic and biochemical values was similar in reversed white coat versus the remaining subjects. The absence of any association with left ventricular hypertrophy scores against the clinical significance of this phenomenon.