Internal medicine
-
Objectives The present study evaluated the usefulness of machine learning (ML) models with the coronary artery calcification score (CACS) and clinical parameters for predicting major adverse cardiac events (MACEs). Methods The Nationwide Gender-specific Atherosclerosis Determinants Estimation and Ischemic Cardiovascular Disease Prospective Cohort study (NADESICO) of 1,187 patients with suspected coronary artery disease (CAD) 50-74 years old was used to build a MACE prediction model. The ML random forest (RF) model was compared with a logistic regression analysis. ⋯ Conclusion The ML-RF model improved the long-term prediction of MACEs compared to the logistic regression model. However, the selected variables in the internal dataset were not highly predictive of the external dataset. Further investigations are required to validate the usefulness of this model.
-
Hypercalcemia is a significant complication in cancer patients, primarily caused by parathyroid hormone-related peptide (PTHrP) and, rarely, by parathyroid hormone (PTH) production from tumors. We report a case of severe hypercalcemia in a woman with uterine cancer who exhibited elevated PTH and PTHrP levels. ⋯ A molecular analysis confirmed the expression of the PTH gene and protein within the tumor, indicating ectopic PTH production. In diagnosing and treating cancers, it is necessary to consider not only PTHrP production but also ectopic PTH production.
-
Adult multisystem Langerhans cell histiocytosis (MS-LCH) is rare and has a poor prognosis. A 67-year-old man with MS-LCH presented with a hepatic tumor rupture and multiple masses in the lungs, liver, and pancreas. ⋯ A literature review revealed a distinct subset of MS-LCH that can be managed by smoking cessation and careful observation through follow-up imaging. This suggests that careful observation through follow-up imaging may be a reasonable alternative to chemotherapy in select adult cases of MS-LCH.
-
The year 2023 marked a significant change for Internal Medicine, as the number of submissions related to the novel coronavirus infection (COVID-19) declined significantly and interest shifted to other disease fields and research areas. Our journal published its first articles on artificial intelligence (AI) and machine learning (ML), and these articles have shown that AI may be useful for the early detection of potential cardiac diseases, while ML can be used to predict the risk of serious illness in patients hospitalized with COVID-19, providing new possibilities for diagnoses and treatment. In addition to touching on the above, the present article also highlights the status of submissions to the journal (including the number of submissions and acceptance rate) in 2023.
-
Angiosarcoma is a rare malignancy that can arise from chronic pyothorax. We herein report a 75-year-old Japanese man with a history of tuberculosis who presented with left-sided chest pain that had persisted for 4 months. ⋯ Chemotherapy with paclitaxel (80 mg/m2 weekly) was ineffective and was discontinued after 3 months. Our findings emphasize that physicians should inform patients with chronic tuberculous pyothorax about malignant complications for which chest pain is the initial symptom, in addition to highlighting the need for careful follow-up.