Search

Simple Summary: True personalization of internal/general medicine depends on the assessment and acknowledgment of sarcopenia and frailty characteristics of patients. The co-existence of sarcopenia, frailty, and hypothyroidism must be acknowledged by physicians, since these are common comorbidities bearing negative long-term clinical outcomes. Low ALT values could serve as a useful biomarker for screening of patients already diagnosed with hypothyroidism. Background: Hypothyroidism is very common worldwide. It is known to be associated with frailty which, in turn, is associated with increased morbidity and mortality in the elderly. Low ALT blood activity is an established marker for sarcopenia and frailty. The incidence and outcomes of the association between low ALT values and hypothyroidism, as manifested in elevated blood TSH levels, is unknown. The objective of this study was to assess if low ALT values could improve the prediction of clinical outcome in hypothyroid patients. Methods: This was a retrospective analysis of hospitalized patients in a large, tertiary hospital. Results: Over a period of 21 years, an overall population of 16,827 patients were identified as eligible to participate in this study. Within the study population, 726 (4.3%) were classified as suffering from hypothyroidism (TSH values > 6 MIU/L) and 2184 (13%) were classified as patients with sarcopenia (ALT < 12 IU/L). Within our patient population, hypothyroidism was associated with sarcopenia in a statistically significant manner (p = 0.011). Patients classified as suffering from both hypothyroidism and sarcopenia had significantly shorter survival: A multivariate analysis showed that the frail and hypothyroid group of patients had a statistically significant risk of mortality in the next 5 years (HR = 3.6; CI 2.75–4.71; p < 0.001). Conclusions: Sarcopenia and frailty are common comorbidities, bearing negative long-term clinical outcomes. Low ALT values could serve as a useful biomarker for screening of patients already diagnosed with hypothyroidism. [ABSTRACT FROM AUTHOR]

Background: Under- or late identification of pulmonary embolism (PE)-a thrombosis of 1 or more pulmonary arteries that seriously threatens patients' lives-is a major challenge confronting modern medicine., Objective: We aimed to establish accurate and informative machine learning (ML) models to identify patients at high risk for PE as they are admitted to the hospital, before their initial clinical checkup, by using only the information in their medical records., Methods: We collected demographics, comorbidities, and medications data for 2568 patients with PE and 52,598 control patients. We focused on data available prior to emergency department admission, as these are the most universally accessible data. We trained an ML random forest algorithm to detect PE at the earliest possible time during a patient's hospitalization-at the time of his or her admission. We developed and applied 2 ML-based methods specifically to address the data imbalance between PE and non-PE patients, which causes misdiagnosis of PE., Results: The resulting models predicted PE based on age, sex, BMI, past clinical PE events, chronic lung disease, past thrombotic events, and usage of anticoagulants, obtaining an 80% geometric mean value for the PE and non-PE classification accuracies. Although on hospital admission only 4% (1942/46,639) of the patients had a diagnosis of PE, we identified 2 clustering schemes comprising subgroups with more than 61% (705/1120 in clustering scheme 1; 427/701 and 340/549 in clustering scheme 2) positive patients for PE. One subgroup in the first clustering scheme included 36% (705/1942) of all patients with PE who were characterized by a definite past PE diagnosis, a 6-fold higher prevalence of deep vein thrombosis, and a 3-fold higher prevalence of pneumonia, compared with patients of the other subgroups in this scheme. In the second clustering scheme, 2 subgroups (1 of only men and 1 of only women) included patients who all had a past PE diagnosis and a relatively high prevalence of pneumonia, and a third subgroup included only those patients with a past diagnosis of pneumonia., Conclusions: This study established an ML tool for early diagnosis of PE almost immediately upon hospital admission. Despite the highly imbalanced scenario undermining accurate PE prediction and using information available only from the patient's medical history, our models were both accurate and informative, enabling the identification of patients already at high risk for PE upon hospital admission, even before the initial clinical checkup was performed. The fact that we did not restrict our patients to those at high risk for PE according to previously published scales (eg, Wells or revised Genova scores) enabled us to accurately assess the application of ML on raw medical data and identify new, previously unidentified risk factors for PE, such as previous pulmonary disease, in general populations., (©Ori Ben Yehuda, Edward Itelman, Adva Vaisman, Gad Segal, Boaz Lerner. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 30.07.2024.)