Machine Learning-Based Prediction of Changes in the Clinical Condition of Patients With Complex Chronic Diseases: 2-Phase Pilot Prospective Single-Center Observational Study.

BACKGROUND: Functional impairment is one of the most decisive prognostic factors in patients with complex chronic diseases. A more significant functional impairment indicates that the disease is progressing, which requires implementing diagnostic and therapeutic actions that stop the exacerbation of the disease. OBJECTIVE: This study aimed to predict alterations in the clinical condition of patients with complex chronic diseases by predicting the Barthel Index (BI), to assess their clinical and functional status using an artificial intelligence model and data collected through an internet of things mobility device. METHODS: A 2-phase pilot prospective single-center observational study was designed. During both phases, patients were recruited, and a wearable activity tracker was allocated to gather physical activity data. Patients were categorized into class A (BI≤20; total dependence), class B (2060; moderate or mild dependence, or independent). Data preprocessing and machine learning techniques were used to analyze mobility data. A decision tree was used to achieve a robust and interpretable model. To assess the quality of the predictions, several metrics including the mean absolute error, median absolute error, and root mean squared error were considered. Statistical analysis was performed using SPSS and Python for the machine learning modeling. RESULTS: Overall, 90 patients with complex chronic diseases were included: 50 during phase 1 (class A: n=10; class B: n=20; and class C: n=20) and 40 during phase 2 (class B: n=20 and class C: n=20). Most patients (n=85, 94%) had a caregiver. The mean value of the BI was 58.31 (SD 24.5). Concerning mobility aids, 60% (n=52) of patients required no aids, whereas the others required walkers (n=18, 20%), wheelchairs (n=15, 17%), canes (n=4, 7%), and crutches (n=1, 1%). Regarding clinical complexity, 85% (n=76) met patient with polypathology criteria with a mean of 2.7 (SD 1.25) categories, 69% (n=61) met the frailty criteria, and 21% (n=19) met the patients with complex chronic diseases criteria. The most characteristic symptoms were dyspnea (n=73, 82%), chronic pain (n=63, 70%), asthenia (n=62, 68%), and anxiety (n=41, 46%). Polypharmacy was presented in 87% (n=78) of patients. The most important variables for predicting the BI were identified as the maximum step count during evening and morning periods and the absence of a mobility device. The model exhibited consistency in the median prediction error with a median absolute error close to 5 in the training, validation, and production-like test sets. The model accuracy for identifying the BI class was 91%, 88%, and 90% in the training, validation, and test sets, respectively. CONCLUSIONS: Using commercially available mobility recording devices makes it possible to identify different mobility patterns and relate them to functional capacity in patients with polypathology according to the BI without using clinical parameters.

Genetic profile in patients with complicated acute aortic syndrome: the GEN-AOR study.

INTRODUCTION AND OBJECTIVES: Genetic testing is becoming increasingly important for diagnosis and personalized treatments in aortopathies. Here, we aimed to genetically diagnose a group of acute aortic syndrome (AAS) patients consecutively admitted to an intensive care unit and to explore the clinical usefulness of AAS-associated variants during treatment decision-making and family traceability. METHODS: We applied targeted next-generation sequencing, covering 42 aortic diseases genes in AAS patients with no signs consistent with syndromic conditions. Detected variants were segregated by Sanger sequencing in available family members. Demographic features, risk factors and clinical symptoms were statistically analyzed by Fisher or Fisher-Freeman-Halton Exact tests, to assess their relationship with genetic results. RESULTS: Analysis of next-generation sequencing data in 73 AAS patients led to the detection of 34 heterozygous candidate variants in 14 different genes in 32 patients. Family screening was performed in 31 relatives belonging to 9 families. We found 13 relatives harboring the family variant, of which 10 showed a genotype compatible with the occurrence of AAS. Statistical tests revealed that the factors associated with a positive genetic diagnosis were the absence of hypertension, lower age, family history of AAS and absence of pain. CONCLUSIONS: Our findings broaden the spectrum of the genetic background for AAS. In addition, both index patients and studied relatives benefited from the results obtained, establishing the most appropriate level of surveillance for each group. Finally, this strategy could be reinforced by the use of stastistically significant clinical features as a predictive tool for the hereditary character of AAS. CLINICALTRIALS: gov (Identifier: NCT04751058).

Traducción y adaptación transcultural al español de la escala MULTIPleS en pacientes de edad avanzada con multimorbilidad / Cross-cultural adaptation into Spanish of the MULTIPleS scale in elderly patients with multimorbidity

Antecedentes y objetivo: La escala Multimorbidity Illness Perceptions Scale (MULTIPleS) analiza si padecer dos o más enfermedades crónicas repercute en la calidad de vida, coste y resultados clínicos de los pacientes. El objetivo fue traducir y adaptar transculturalmente al español la escala MULTIPleS.MétodosTraducción directa y retrotraducción seguidas de síntesis y adaptación por un tercer traductor y un panel de expertos para garantizar la equivalencia conceptual, semántica y de contenido entre ambas versiones. Posteriormente, se realizó un análisis de comprensibilidad en una muestra de pacientes.ResultadosSe obtuvo la versión española de la escala MULTIPleS. El grado de dificultad medio en la traducción directa y la retrotraducción del título y de las preguntas demostró una dificultad baja. En la fase de síntesis y adaptación, se resolvieron 6 discrepancias. El análisis de comprensibilidad se realizó en 10 pacientes, lográndose el requisito establecido (> 80%) para todos los ítems.ConclusionesSe trata de la primera adaptación transcultural al español de la escala MULTIPleS. Disponer de esta escala retrotraducida permitirá analizar la percepción de los pacientes ante la enfermedad y aplicar así mejoras en su asistencia sanitaria. (AU)

Background and objective: The Multimorbidity Illness Perceptions Scale (MULTIPleS) analyzes whether suffering from two or more chronic diseases affects the quality of life, cost and clinical results of patients. The objective was to translate and cross-culturally adapt the MULTIPleS scale into Spanish.MethodsDirect translation and back translation followed by synthesis and adaptation by a third translator and a panel of experts to guarantee the conceptual, semantic and content equivalence between both versions. Subsequently, a comprehensibility analysis was performed on a sample of patients.ResultsThe Spanish version of the MULTIPleS scale was obtained. The medium degree of difficulty in the direct translation and the back translation of the title and the questions showed a low difficulty. In the synthesis and adaptation phase, 6 discrepancies were resolved. The comprehensibility analysis was performed in 10 patients, achieving the established requirement (> 80%) for all items.ConclusionsThis is the first cross-cultural adaptation to Spanish of the MULTIPleS scale. Having this back-translated scale will make it possible to analyze patients’ perception of the disease and thus apply improvements in their healthcare. (AU)

Cross-cultural adaptation into Spanish of the MULTIPleS scale in elderly patients with multimorbidity. / Traducción y adaptación transcultural al español de la escala MULTIPleS en pacientes de edad avanzada con multimorbilidad.

BACKGROUND AND OBJECTIVE: The Multimorbidity Illness Perceptions Scale (MULTIPleS) analyzes whether suffering from two or more chronic diseases affects the quality of life, cost and clinical results of patients. The objective was to translate and cross-culturally adapt the MULTIPleS scale into Spanish. METHODS: Direct translation and back translation followed by synthesis and adaptation by a third translator and a panel of experts to guarantee the conceptual, semantic and content equivalence between both versions. Subsequently, a comprehensibility analysis was performed on a sample of patients. RESULTS: The Spanish version of the MULTIPleS scale was obtained. The medium degree of difficulty in the direct translation and the back translation of the title and the questions showed a low difficulty. In the synthesis and adaptation phase, 6 discrepancies were resolved. The comprehensibility analysis was performed in 10 patients, achieving the established requirement (> 80%) for all items. CONCLUSIONS: This is the first cross-cultural adaptation to Spanish of the MULTIPleS scale. Having this back-translated scale will make it possible to analyze patients' perception of the disease and thus apply improvements in their healthcare.