Integrating machine learning (ML) into intensive care units (ICUs) can significantly enhance patient care and operational efficiency. ML algorithms can analyze vast amounts of data from electronic health records, physiological monitoring systems, and other medical devices, providing real-time insights and predictive analytics to assist clinicians in decision-making. ML has shown promising results in predictive modeling for patient outcomes, early detection of sepsis, optimizing ventilator settings, and resource allocation. For instance, predictive algorithms have demonstrated high accuracy in forecasting patient deterioration, enabling timely interventions and reducing mortality rates. Despite these advancements, challenges such as data heterogeneity, integration with existing clinical workflows, and the need for transparency and interpretability of ML models persist. The deployment of ML in ICUs also raises ethical and legal considerations regarding patient privacy and the potential for algorithmic biases. For clinicians interested in the early embracing of AI-driven changes in clinical practice, in this review, we discuss the challenges of integrating AI and ML tools in the ICU environment in several steps and issues: 1. Main categories of ML algorithms; 2. From data enabling to ML development; 3. Decision-support systems that will allow patient stratification, accelerating the foresight of adequate individual care; 4. Improving patient outcomes and healthcare efficiency, with positive society and research implications; 5. Risks and barriers to AI-ML application to the healthcare system, including transparency, privacy, and ethical concerns.
Adverse reactions associated to anti-thyroid drugs include fever, rash, arthralgia, agranulocytosis and hepatitis that are thought to be hypersensitivity reactions. Five cases of pleural effusion associated to thionamides have also been reported, two with propylthiouracil and three with carbimazole. We report here a case of a 75-year-old man admitted because of unilateral pleural effusion. The patient had a recent diagnosis of hyperthyroidism and 6 days after starting methimazole complained of pleuritic chest pain. He had elevated C-reactive protein and erythrocyte sedimentation rate and normal white blood cell count and liver enzymes. Chest radiography showed a moderate right pleural effusion and the ultrasound revealed a loculated effusion that was shown to be an eosinophilic exudate. The temporal relationship between methimazole intake and the development of pleural effusion combined with the extensive exclusion of alternative causes, namely infectious, neoplastic and primary auto-immune diseases, led to the diagnosis of hypersensitivity reaction to methimazole. The thionamide was stopped and corticosteroid was started with complete resolution of the pleural effusion in 3 months. Awareness of this rare adverse reaction of anti-thyroid drugs is important and methimazole can be added to the list of possible etiologies of drug-induced eosinophilic pleural effusion.
Disseminated necrotizing leukoencephalopathy (DNL) is characterized by multiple microscopic foci of white matter necrosis. DNL was initially thought to be exclusively associated with immunosuppression conditions but it has been recently described in immunocompetent patients in septic shock. A 90-year-old immunocompetent woman with no previous neurological impairment presented with septic shock and drowsiness that responded well to therapy with clinical improvement and a full neurological recovery. Unexpectedly deterioration with progression to coma occurred. Investigation excluded other causes and Magnetic Resonance Imaging (MRI) was consistent with the diagnosis of DNL showing bilateral multifocal white matter lesions with a nonvascular pattern with restricted diffusion. Neurological impairment persisted with progression to death. DNL is an unexpected diagnosis in an immunocompetent patient. We compared the present case to those found in the literature of DNL complicating septic shock and discuss the antemortem diagnosis based on MRI findings.