Machine learning to predict cardiovascular risk Quesada, Jose A.; Lopez‐Pineda, Adriana; Gil‐Guillén, Vicente F. ...
International journal of clinical practice (Esher),
October 2019, 2019-Oct, 2019-10-00, 20191001, Letnik:
73, Številka:
10
Journal Article
Recenzirano
Odprti dostop
Aims
To analyse the predictive capacity of 15 machine learning methods for estimating cardiovascular risk in a cohort and to compare them with other risk scales.
Methods
We calculated cardiovascular ...risk by means of 15 machine‐learning methods and using the SCORE and REGICOR scales and in 38 527 patients in the Spanish ESCARVAL RISK cohort, with 5‐year follow‐up. We considered patients to be at high risk when the risk of a cardiovascular event was over 5% (according to SCORE and machine learning methods) or over 10% (using REGICOR). The area under the receiver operating curve (AUC) and the C‐index were calculated, as well as the diagnostic accuracy rate, error rate, sensitivity, specificity, positive and negative predictive values, positive likelihood ratio, and number needed to treat to prevent a harmful outcome.
Results
The method with the greatest predictive capacity was quadratic discriminant analysis, with an AUC of 0.7086, followed by Naive Bayes and neural networks, with AUCs of 0.7084 and 0.7042, respectively. REGICOR and SCORE ranked 11th and 12th, respectively, in predictive capacity, with AUCs of 0.63. Seven machine learning methods showed a 7% higher predictive capacity (AUC) as well as higher sensitivity and specificity than the REGICOR and SCORE scales.
Conclusions
Ten of the 15 machine learning methods tested have a better predictive capacity for cardiovascular events and better classification indicators than the SCORE and REGICOR risk assessment scales commonly used in clinical practice in Spain. Machine learning methods should be considered in the development of future cardiovascular risk scales.
Background
The aim of this study was to assess the clinical implications of calculating an individualized HbA1c target using a recently published algorithm in a real‐life clinical setting.
Methods
...General practitioners (GPs) from the Spanish Society of Family Medicine Diabetes Expert Group were invited to participate in the study. Each GP selected a random sample of patients with diabetes from his or her practice and submitted their demographic and clinical data for analysis. Individualized glycaemic targets were calculated according to the algorithm. Predictors of good glycaemic control were studied. The rate of patients attaining their individualized glycaemic target or the uniform target of HbA1c < 7.0% was calculated.
Results
Forty GPs included 408 patients in the study. Of the 8 parameters included in the algorithm, “comorbidities,” “risk of hypoglycaemia from treatment,” and “diabetes duration” had the greatest impact on determining the individualized glycaemic target. Number of glucose‐lowering agents and adherence were independently associated with glycaemic control. Overall, 60.5% of patients had good glycaemic control per individualized target, and 56.1% were well controlled per the uniform target of HbA1c < 7.0% (P = .20). However, 12.8% (23 of 246) of the patients with HbA1c ≥ 7.0% were adequately controlled per individualized target, and 2.6% (6 of 162) of the patients with HbA1c < 7.0% were uncontrolled since their individualized target was lower.
Conclusions
In a real‐life clinical setting, applying individualized targets did not change the overall rate of patients with good glycaemic control yet led to reclassification of 7.1% (29 of 408) of the patients. More studies are needed to validate these results in different populations.
Design and validation of an adherence scale to oral antineoplastic drugs Talens-Bolós, Amparo; López-Pintor, Elsa; Guilabert-Mora, Mercedes ...
Farmacia hospitalaria : organo oficial de expresion cientifica de la Sociedad Espanola de Farmacia Hospitalaria,
2023 Mar-Apr, Letnik:
47, Številka:
2
Journal Article
Recenzirano
Odprti dostop
To design and validate a questionnaire to measure adherence to oral antineoplastic drugs. The availability of a simple, validated tool that can be applied to routine care will make it possible to ...detect and identify non-adherence in order to establish strategies to improve adherence and optimize the quality of healthcare services.
Validation study of the questionnaire designed to assess adherence to antineoplastic drugs in a sample of outpatients who collect their medication in two Spanish hospitals. Its validity and reliability will be analyzed, based on a previous qualitative methodology study, using classical test theory and Rasch analysis. We will examine its performance, item fit, response structure and person fit to the predictions of the model, as well as dimensionality, item-person reliability, the appropriateness of the level of difficulty of the items to the sample, and the differential performance of the items according to gender.
La cirugía bariátrica (CB) ha demostrado su eficacia y eficiencia, pero solo el 1% de los pacientes seleccionados llegará a recibirla.
En comparación con el tratamiento médico de la obesidad, la CB, ...ha demostrado una mayor pérdida ponderal mantenida a largo plazo, una reducción de la mortalidad tanto total como cardiovascular (CV), mejoría o remisión de los factores de riesgo CV y de otras comorbilidades asociadas a la obesidad, así como mejor movilidad y calidad de vida.
Presenta riesgos similares a otras intervenciones quirúrgicas abdominales, con la obesidad como factor de riesgo añadido. No obstante, la mortalidad después de este tipo de cirugía es menor al 1%, siendo en centros especializados incluso inferior al 0,3%, con una morbilidad menor al 7%.
Los procedimientos quirúrgicos más comúnmente realizados en el momento actual son la gastrectomía vertical (GV) y el bypass gástrico en Y de Roux (BGYR), preferiblemente mediante abordaje laparoscópico.
Bariatric surgery (BS) has been shown to be effective and efficient, but only 1% of selected patients will ever receive it.
Compared to medical treatment of obesity, BS has demonstrated greater long-term sustained weight loss, a reduction in both total and cardiovascular (CV) mortality, improvement or remission of CV risk factors and other comorbidities associated with obesity, as well as improved mobility and quality of life.
BS presents similar risks to other abdominal surgeries, with obesity as an added risk factor. However, mortality after this type of surgery is less than 1%, being in specialised centres even lower than 0.3%, with a morbidity of less than 7%.
The most commonly performed surgical procedures at present are vertical gastrectomy and Roux---Y gastric bypass, preferably by laparoscopic approach.
Design and validate a scale to measure adherence to oral antineoplastic drugs. The availability of a simple, validated tool that can be applied to routine care will make it possible to detect and ...identify non-adherence in order to establish strategies to improve adherence and optimize the quality of healthcare services.
Validation study of the scale designed to assess adherence to antineoplastic drugs in a sample of outpatients who collect their medication in two Spanish hospitals. Its validity and reliability will be analyzed, based on a previous qualitative methodology study, using classical test theory and Rasch analysis. We will examine its performance, item fit, response structure and person fit to the predictions of the model, as well as dimensionality, item-person reliability, the appropriateness of the level of difficulty of the items to the sample, and the differential performance of the items according to gender.
Diseñar y validar una escala para medir la adherencia a antineoplásicos orales. Disponer de una herramienta sencilla, validada y aplicable a la rutina asistencial permitirá detectar e identificar falta de adherencia para establecer estrategias que permitan mejorarla y optimizar la calidad de los servicios sanitarios.
Estudio de validación de la escala diseñada para evaluar adherencia a antineoplásicos orales en una muestra de pacientes ambulatorios que recogen su medicación en cuatro hospitales españoles. Se analizará su validez y fiabilidad, elaborada a partir de un estudio previo de metodología cualitativa, mediante teoría clásica de los test y análisis Rasch. Se examinará su funcionamiento, el ajuste de los ítems, la estructura de respuesta y de las personas a las predicciones del modelo, así como la dimensionalidad, la fiabilidad ítem-persona, la adecuación del nivel de dificultad de los ítems a la muestra, y el funcionamiento diferencial de los ítems en función del sexo.
To conduct a cross-cultural adaptation and validation in Primary Care of the PREMEPA doctor-patient relationship perception questionnaire.
Descriptive, cross-sectional study, using self-administered ...questionnaires. Qualitative validation: an adapted version of the original questionnaire, was adapted to our culture. The process consisted of the evaluation, cross-cultural adaptation and consensus of a group of experts. The questionnaire was piloted on a sample of 32 patients diagnosed with at least 2 chronic pathologies.
Cognitive piloting, comprehensibility assessment, content validation and internal consistency analysis using Cronbach's alpha coefficient. Quantitative validation: the internal consistency, construct validity and validity of the questionnaire were studied by means of a confirmatory factor analysis developed in a multicenter study, randomly selecting 202 patients with at least 2 chronic pathologies.
Content validity of the new Spanish version was confirmed to be adequate. Comprehensibility and internal consistency (Cronbach's α coefficient = 0.78) were adequate. The confirmatory factor analysis showed good dimensionality, factor relationship and internal consistency, as well as acceptable construct validity. The final result was a 13-item questionnaire consisting of 2 dimensions, which explain 58.5% of the variance: participation in decision-making (accounting for 45.2% of the variance) and person-centered communication (encompassing courtesy, empathy, humanity, and trust).
This adapted version of the PREMEPA questionnaire can be considered valid for use in the Spanish population with a history of chronic pathology. This version of PREMEPA provides a new instrument to understand and improve chronic patient care, which can improve the doctor-patient relationship, encouraging adherence to treatment and enhancing health outcomes.
Background:
Atrial fibrillation (AF) is the most common arrhythmia to appear in clinical practice. People with AF have 5 times the risk of stroke compared to the general population.
Objective:
This ...study aimed to determine the prevalence of AF in people over the age of 50 without known AF, who presented to a community pharmacy to check their cardiovascular risk factors, to identify risk factors associated with AF, and to assess the risk of stroke in people who screened positive for AF.
Methods:
A multicenter observational descriptive study of a screening program took place from May to December 2016. A blood pressure monitor (Microlife Watch BP Home) was used to screen for AF, and the CHA2DS2-VASc questionnaire was used to assess stroke risk.
Results:
The study included 452 adults over the age of 50. The CRIFAFARMA study detected a prevalence of AF of 9.1%. Risk factors for AF were: age of 75 years or older (P = .024), lack of physical activity (P = .043), diabetes (P < .001), dyslipidemia (P = .003), and history of cardiovascular disease (P = .003). Diabetes (OR 2.79, P = .005) and dyslipidemia (OR 2.16, P = .031) had a combined explanatory capacity in the multivariable logistic regression model adjusted for age. 85% were at high risk of stroke according to the CHA2DS2-VASc scale.
Conclusions:
AF was detected in more than 9% of the included population. Factors associated with AF were advanced age, lack of physical activity, diabetes, dyslipidemia, and history of cardiovascular disease, with diabetes and dyslipidemia standing out as the factors with independent explanatory capacity.
Analizar un modelo de predicción de ingreso y urgencias hospitalarias basado en los Clinical Risk Groups (CRG), en la población de pacientes crónicos complejos demandantes de atención primaria.
...Estudio observacional retrospectivo y multicéntrico.
La población de estudio fue la adscrita a los Centros de Salud de Santa Pola y Raval del Departamento de Salud Elche.
Cohorte de paciente crónicos con comorbilidad, desde enero a diciembre de 2013.
Los datos sobre el número de ingresos hospitalarios, el motivo de ingreso y el nivel de complejidad asociado al ingreso se recogieron mediante revisión de la historia clínica.
Para determinar el nivel de complejidad se utilizó la clasificación incluida en la estrategia de cronicidad de la Comunidad Valenciana basada en la CRG.
Se reclutaron 504 pacientes con un grado de complejidad alta (N3) y 272 con complejidad moderada/baja (N1-N2). Se observó mayor comorbilidad de los pacientes agrupados en N3 de alta complejidad (índice de Charlson 2,90 DE: 1,8 vs. 1,90 DE: 1,3; p<0,001), y mayor grado de dependencia para las actividades básicas diarias (índice de Barthel: 16,1 n=81 vs. 7,3 n=20; p<0,001).
La asociación entre el número de ingresos hospitalarios (0,4 DE: 0,8 vs. 0,1 DE: 0,5; p<0,001) y las visitas a urgencias (0,8 DE: 1,5 vs. 0,35 DE: 0,8; p<0,001) fue significativamente mayor en los pacientes del grupo N3 frente a los del grupo N1-N2.
La capacidad predictiva del agrupador CRG mostró una alta sensibilidad para la clasificación del paciente con alto grado de complejidad. Su especificidad y valor predictivo positivo fue menor para la asociación del estrato N3 de complejidad.
To analyse a prediction model for admissions and hospital emergencies based on Clinical Risk Groups, in a population of complex chronic patients demanding primary care.
A multicentric retrospective observational study, of a cohort of chronic patients with comorbidity, from January until December 2013.
The study population was assigned to the Santa Pola and Raval health centres from the Health Department of Elche.
Cohort of chronic patients with comorbidity, from January to December 2013.
Data about the number of admissions, reasons and complexity level associated with the admission were collected by the review of medical records.
To determine the level of complexity, the classification included in the chronicity strategy of the Valencian Community based on Clinical Risk Groups was used.
Five hundred and four patients were recruited with a high complexity degree (N3) and 272 with moderate/low complexity (N1–N2). A higher comorbidity was observed in N3 patients with high complexity Charlson 2.9 (DE 1.8) vs. 1.9 (DE 1.3); P<.001, and higher dependence degree for basic diary activities Barthel 16.1 (n=81) vs. 7.3 (n=20); P<.001.
Association between the number of admissions 0.4 (DE 0.8) vs. 0.1 (DE 0.5); P<.001 and emergency visits 0.8 (DE 1.5) vs. 0.3 (DE 0.8), P<.001 was significatively higher in patients from N3 group than N1-N2 groups.
The predictive capacity of CRG grouper showed high sensibility for the patient classification with a high degree of complexity. Its specificity and positive predictive value were lower for the association of the N3 complexity stratum.
Purpose
Recent clinical practice guidelines have recommended ambulatory management of febrile neutropenia in patients with low risk of complications. Although some centers have begun developing ...management protocols for these patients, there appears to be a certain reluctance to implement them in clinical practice. Our aim is to evaluate the strengths and weaknesses of this strategy according to available evidence and to propose new lines of research.
Methods
Systematic review using a triple aim approach (efficacy, cost-effectiveness, and quality of life), drawing from literature in MEDLINE (PubMed), Embase, and Cochrane Library databases. The review includes studies that assess ambulatory management for efficacy, cost-efficiency, and quality of life.
Results
The search yielded 27 articles that met our inclusion criteria.
Conclusion
In conclusion, based on current evidence, ambulatory management of febrile neutropenia is safe, more cost-effective than inpatient care, and capable of improving quality of life in oncological patients with this complication. Ambulatory care seems to be an effective alternative to hospitalization in these patients.