Association of new obesity indices: visceral adiposity index and body adiposity index, with metabolic syndrome parameters in obese patients with or without type 2 diabetes mellitus

Using Machine Learning and Electronic Health Records to Identify Neuropsychiatric Risk Scores for Delirium in ICU and General Hospital Settings

Objective

Delirium is a common and acute neuropsychiatric syndrome that requires timely intervention to prevent its associated morbidity and mortality. Yet, its diagnosis and symptoms are often overlooked due to its variable clinical presentation and fluctuating nature. Thus, in this study, we address the barriers to delirium diagnosis by utilizing a machine learning-based predictive algorithm for incident delirium that relies on archived electronic health records (EHRs) data.

Methods

We used the Medical Information Mart for Intensive Care (MIMIC) database to create a detailed dataset for identifying delirium in intensive care unit (ICU) patients. Our approach involved training machine learning models on this dataset to pinpoint critical clinical features for delirium detection. These features were then refined and applied to non-ICU patients using EHRs from the American University of Beirut Medical Center (AUBMC).

Results

Our study assessed machine learning models like Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Classification and Regression Trees (CART), Random Forest (RF), Neural Oblivious Decision Ensembles (NODE), and Logistic Regression (LR), highlighting superior delirium detection in diverse clinical settings. The CatBoost model excelled in ICU environments with an F1 Score of 89.2%, while XGBoost performed best in general hospital settings with a 75.4% F1 Score. Interpretations using Tabular Local Interpretable Model-agnostic Explanations (LIME) revealed critical indicators such as prothrombin time and hematocrit levels, enhancing model transparency and clinical applicability. These clinical insights help differentiate the delirium predictors between ICU patients, who are often sensitive to various factors.

Conclusion

The proposed predictive algorithm improves delirium detection rates and streamlines efficiency in hospital electronic systems, thereby enabling prompt interventions to prevent delirium progression and associated complications. The clinical indicators for delirium that we identified in general hospital settings and ICU can greatly help healthcare professionals identify potential causes of delirium and reduce misdiagnosis.

Chronic California herbal tea use causing biopsy-proven Melanosis coli

Melanosis coli is a dark to brown pigmentation of the colon due to lipofuscin deposition within the cytoplasm of cells. It is a benign condition associated with excessive use of laxatives, particularly those that are anthracene derivatives and common herbal remedies like Cassia Angustifolla (senna). It is usually asymptomatic and diagnosed incidentally during colonoscopy or histopathologic evaluation. We present a case of a 56-year-old male patient who presented with diarrhea of 3 months duration, which started after he began to use California herbal tea for his constipation. Colonoscopic evaluation revealed an intense pigmentation throughout the colon suggestive of Melanosis coli, which was confirmed on histopathology. In patients with prolonged use of California herbal tea and dark to brown pigmentations of colonic mucosa on colonoscopy, there should be a high index of suspicion for Melanosis coli. And patients should be aware of the risk of developing Melanosis coli following prolonged herbal tea use. The findings presented in our case are in support of few previous literature that showed relations between chronic herbal tea use and Melanosis coli.

Continuous Tunneled Infraclavicular Nerve Catheter for Palliative Management of Critical Limb Ischemia: A Case Report

Critical limb ischemia (CLI) is limb pain occurring at rest or impending limb loss as a result of lack of blood flow to the affected extremity. CLI pain is challenging to control despite multimodal pharmacologic analgesia and surgical intervention. We describe the successful use of a continuous local anesthetic infusion via an infraclavicular nerve catheter to control severe refractory ischemic upper limb pain in a patient with metastatic lung cancer for whom surgical and pharmacological intervention was unsuccessful. As her opioid requirements increased due to worsening ischemic pain, she subsequently developed opioid toxicity, hence prompting the palliative use of a tunneled infraclavicular nerve catheter under ultrasound guidance to minimize opioid requirements. Her opioid requirements tailed down subsequently with the successful insertion of the infraclavicular nerve catheter and she remained pain free till her death. Palliative use of nerve catheters is a safe and an effective alternative in patients with refractory cancer pain, and we describe our methods to prolong its use and minimizing its associated long-term complications.

Study of metabolic syndrome indicators in newly diagnosed diabetes mellitus type 2 patients in Pakistani population

BACKGROUND

Metabolic syndrome (MetS) being a biological abnormality confers the highest risk of type 2 diabetes mellitus (T2DM).

AIM

To assess MetS indicators in the newly diagnosed T2DM Pakistani population.

METHODS

A cross-sectional study (N = 123) with newly diagnosed T2DM patients (gender: both, MeanAge: 49.24 ± 6.84 years) was selected from Medical OPD, Pakistan Institute of Medical Sciences, Islamabad. Basic profile, family history, and physical activity were recorded through a predesigned questionnaire, dietary intake through seven days Food Diary and Food Frequency Questionnaire. Blood pressure and selected clinical signs and symptoms were recorded. Anthropometric measurements included mid-upper arm circumference (MUAC), body mass index (BMI), waist circumference (WC), waist-and-hip ratio (WHR), waist-to-height ratio (WHtR), and conicity index. Lab parameters included fasting blood glucose, HbA1c, insulin levels, and lipid profile. Homeostatic model assessment of insulin resistance (HOMA-IR) was computed to assess insulin resistance.

RESULTS

Almost all parameters related to MetS were higher than normal. The prevalence of MetS was 59.7%. BMI, MUAC, and WHtR were independently associated with HOMA-IR, but WC, WHR, and the conicity index had no relationship MetS indicators.

CONCLUSION

The prevalence rate of MetS was found to be 59.7% in newly diagnosed T2DM patients. MUAC was found to be a better parameter for the diagnosis of central obesity and insulin resistance in the selected population.

Pathophysiology of Post-COVID syndromes: a new perspective

Most COVID-19 patients recovered with low mortality; however, some patients experienced long-term symptoms described as "long-COVID" or "Post-COVID syndrome" (PCS). Patients may have persisting symptoms for weeks after acute SARS-CoV-2 infection, including dyspnea, fatigue, myalgia, insomnia, cognitive and olfactory disorders. These symptoms may last for months in some patients. PCS may progress in association with the development of mast cell activation syndrome (MCAS), which is a distinct kind of mast cell activation disorder, characterized by hyper-activation of mast cells with inappropriate and excessive release of chemical mediators. COVID-19 survivors, mainly women, and patients with persistent severe fatigue for 10 weeks after recovery with a history of neuropsychiatric disorders are more prone to develop PCS. High D-dimer levels and blood urea nitrogen were observed to be risk factors associated with pulmonary dysfunction in COVID-19 survivors 3 months post-hospital discharge with the development of PCS. PCS has systemic manifestations that resolve with time with no further complications. However, the final outcomes of PCS are chiefly unknown. Persistence of inflammatory reactions, autoimmune mimicry, and reactivation of pathogens together with host microbiome alterations may contribute to the development of PCS. The deregulated release of inflammatory mediators in MCAS produces extraordinary symptoms in patients with PCS. The development of MCAS during the course of SARS-CoV-2 infection is correlated to COVID-19 severity and the development of PCS. Therefore, MCAS is treated by antihistamines, inhibition of synthesis of mediators, inhibition of mediator release, and inhibition of degranulation of mast cells.

The crucial role of prolactin-lactogenic hormone in Covid-19

Prolactin (PRL) is a peptide hormone secreted from anterior pituitary involved in milk production in the females and regulation of sex drive in both sexes. PRL has pro-inflammatory and anti-inflammatory functions. High PRL serum level or hyperprolactinemia is associated with different viral infections. In coronavirus disease 2019 (Covid-19), which caused by positive-sense single-strand RNA virus known as severe acute respiratory distress syndrome coronavirus type 2 (SARS-CoV-2), PRL serum level is increased. PRL in Covid-19 may exacerbate the underlying inflammatory status by induction release of pro-inflammatory cytokines. However, PRL through its anti-inflammatory effects may reduce the hyperinflammatory status in Covid-19. The underlying mechanism of increasing PRL in Covid-19 is poorly understood. Therefore, in this review we try to find the potential anti-inflammatory or pro-inflammatory role of PRL in Covid-19. As well, this review was aimed to discuss the underlying causes and mechanisms for Covid-19-induced hyperprolactinemia.