Application of machine learning algorithms in classifying postoperative success in metabolic bariatric surgery: Acomprehensive study.

Objectives: Metabolic bariatric surgery is a critical intervention for patients living with obesity and related health issues. Accurate classification and prediction of patient outcomes are vital for optimizing treatment strategies. This study presents a novel machine learning approach to classify patients in the context of metabolic bariatric surgery, providing insights into the efficacy of different models and variable types. Methods: Various machine learning models, including Gaussian Naive Bayes, Complement Naive Bayes, K-nearest neighbour, Decision Tree, K-nearest neighbour with RandomOverSampler, and K-nearest neighbour with SMOTE, were applied to a dataset of 73 patients. The dataset, comprising psychometric, socioeconomic, and analytical variables, was analyzed to determine the most efficient predictive model. The study also explored the impact of different variable groupings and oversampling techniques. Results: Experimental results indicate average accuracy values as high as 66.7% for the best model. Enhanced versions of K-nearest neighbour and Decision Tree, along with variations of K-nearest neighbour such as RandomOverSampler and SMOTE, yielded the best results. Conclusions: The study unveils a promising avenue for classifying patients in the realm of metabolic bariatric surgery. The results underscore the importance of selecting appropriate variables and employing diverse approaches to achieve optimal performance. The developed system holds potential as a tool to assist healthcare professionals in decision-making, thereby enhancing metabolic bariatric surgery outcomes. These findings lay the groundwork for future collaboration between hospitals and healthcare entities to improve patient care through the utilization of machine learning algorithms. Moreover, the findings suggest room for improvement, potentially achievable with a larger dataset and careful parameter tuning.

Analysis of psychometric questionnaires used in patient selection for bariatric surgery.

INTRODUCTION: In severe forms of obesity there is a high prevalence of psychopathological comorbidity. Psychiatric evaluation is an important component of comprehensive obesity care and contributes to optimizing therapeutic results after bariatric surgery. OBJECTIVE: To assess the effectiveness of psychometric tests used in the protocol for selecting patients for bariatric surgery. MATERIAL AND METHODS: Retrospective naturalistic observational study of 100 patients who were candidates for bariatric surgery. Patients who complete the psychometric protocol and the psychiatric interview between January 2019 and June 2021 are included. Two groups are formed: those considered unfit for any psychopathological reason and those considered fit. To evaluate the effectiveness of the tests used, ROC curves will be used. The sensitivity and specificity values of each test used will be obtained. RESULTS: 97 patients included, aged between 20 and 61 years, 64.9% women. 51.5% had a family history and 38.1% a personal history of any psychiatric disorder. Regarding the area under the curve, the scales that presented a value greater than 0.7 were the YFAS total score (0.771), HADS-D (0.757), the Edinburgh Bulimia total score (0.747), the severity score of YFAS (0.722) and Edinburgh Bulimia Severity Score (0.705). The most frequent diagnoses as a cause of exclusion were Food Addiction 8 (20.5%) and Generalized Anxiety Disorder (GAD) 6 (15.5%). CONCLUSIONS: The YFAS, BITE and HADS-A scales were useful to discriminate those patients considered unsuitable for bariatric surgery for any psychopathological cause.

Interleukin 6 and depression in patients affected by Covid-19.

INTRODUCTION: Rise of central cytokines resulting from infections produces neuronal changes. Covid-19 allows the study of depressive symptoms in sustained stress and its relationship with molecular mechanisms. OBJECTIVES: To assess correlation between IL-6, IL-1ß and TNF-α and depressive symptoms. Characterize the depressive symptoms present. METHODS: Observational study. Patients admitted for Covid-19 older than 60 years with a interleukin determination were included. The Yesavage Geriatric Depression Scale was used, associating each item with a neurotransmitter. RESULTS: 27 patients included. We did not find correlation between IL-6 levels and the GDS scale score (rho = 0.204; 95% CI -0.192 to 0.543); with IL-1ß levels (rho = -0.126; 95% CI -0.490 to 0.276); nor of TNF-α (rho = -0.033; 95% CI -0.416 to 0.360). 3 patients (11.1%) presented score compatible with depressive disorder. It was associated with a deficiency of Noradrenaline and Serotonin. CONCLUSIONS: We found no correlation between the levels of IL-6, IL-1ß, and TNF-α with the GDS score. Depressive symptomatology is similar to vascular depressions.

INTRODUCCIÓN: El incremento de citocinas centrales resultante de infecciones produce cambios neuronales. La Covid-19 permite estudiar los síntomas depresivos en un estrés sostenido y su relación con mecanismos moleculares. OBJETIVOS: Valorar la correlación entre niveles de IL-6, IL-1ß y TNF-α y sintomatología depresiva. Caracterizar los cuadros depresivos presentes. MÉTODOS: Estudio observacional. Se incluyeron pacientes ingresados por Covid-19 mayores de 60 años con una determinación de interleucinas. Se utilizó la Escala de depresión geriátrica de Yesavage, asociándose cada ítem con un neurotransmisor. RESULTADOS: 27 pacientes incluidos. No encontramos correlación entre los niveles de IL-6 y la puntuación de la escala GDS (rho = 0,204; IC95% −0.192 a 0.543); con los niveles de IL-1ß (rho = −0,126; IC95% −0.490 a 0.276); ni de TNF-α (rho = −0,033; IC95% −0.416 a 0.360). 3 pacientes (11,1%) presentaron una puntuación compatible con cuadro depresivo. Se asoció a déficit de Noradrenalina y Serotonina. CONCLUSIONES: No hallamos correlación entre los niveles de IL-6, IL-1ß y TNF-α con la puntuación en la GDS. La sintomatología depresiva presenta características similares a las depresiones vasculares.

[Interleukin 6 and depression in patients affected by Covid-19]. / Relación entre los niveles de interleucina 6 y depresión en pacientes afectados por Covid-19.

INTRODUCTION: Rise of central cytokines resulting from infections produces neuronal changes. Covid-19 allows the study of depressive symptoms in sustained stress and its relationship with molecular mechanisms. OBJECTIVES: To assess correlation between IL-6, IL-1ß and TNF-α and depressive symptoms. Characterize the depressive symptoms present. METHODS: Observational study. Patients admitted for Covid-19 older than 60 years with a interleukin determination were included. The Yesavage Geriatric Depression Scale (GDS) was used, associating each item with a neurotransmitter. RESULTS: 27 patients included. We did not find correlation between IL-6 levels and the GDS scale score (rho=0.204; 95% CI -0.192 to 0.543); with IL-1ß levels (rho=-0.126; 95% CI -0.490 to 0.276); nor of TNF-α (rho=-0.033; 95% CI -0.416 to 0.360). 3 patients (11.1%) presented score compatible with depressive disorder. It was associated with a deficiency of noradrenaline and serotonin. CONCLUSIONS: We found no correlation between the levels of IL-6, IL-1ß, and TNF-α with the GDS score. Depressive symptomatology is similar to vascular depressions.

Evaluation of Dram Score as a Predictor of Poor Postoperative Outcome in Spine Surgery.

The Distress Risk Assessment Method (DRAM) was presented by Main, Wood and Hillis in 1992 as a simple means of assessing the risk of failure due to psychosocial factors in spine surgery. To our knowledge, it has not been used in our setting. The aim of this study was to analyse the usefulness of the Spanish translation of this instrument to predict poor outcomes. METHODS: A prospective blind study was conducted including 65 patients undergoing spine surgery. We created two groups of patients based on DRAM score: not distressed (NDRAM) or distressed (DDRAM). A visual analogue scale for pain and the 12-Item Short Form Health Survey (SF-12) were used at baseline, 6 weeks and 6 months. RESULTS: 24 patients were classified as DDRAM and 38 as NDRAM, with 3 patients not completing the questionnaires. The analysis found no significant differences in the demographic or clinical variables at baseline. At 6 weeks and 6 months, the NDRAM group showed improvements in low back pain (p < 0.001; p = 0.005), leg pain (p < 0.001; p = 0.017), physical health (p = 0.031; p = 0.003) and mental health (p = 0.137; p = 0.049). In contrast, in the DDRAM group, though leg pain score improved (p < 0.001; p = 0.002), there was no improvement at 6 weeks or 6 months in low back pain (p = 0.108; p = 0.287), physical health (p = 0.620; p = 0.263) or mental health (p = 0.185; p = 0.329). CONCLUSIONS: In our setting, the DRAM is a useful screening tool, and it has allowed the creation of a program between psychiatry and spine surgery.