Quick and accurate medical diagnoses are crucial for the successful treatment of diseases. Using machine learning algorithms and based on laboratory blood test results, we have built two models to predict a haematologic disease. One predictive model used all the available blood test parameters and the other used only a reduced set that is usually measured upon patient admittance. Both models produced good results, obtaining prediction accuracies of 0.88 and 0.86 when considering the list of five most likely diseases and 0.59 and 0.57 when considering only the most likely disease. The models did not differ significantly, which indicates that a reduced set of parameters can represent a relevant “fingerprint” of a disease. This knowledge expands the model’s utility for use by general practitioners and indicates that blood test results contain more information than physicians generally recognize. A clinical test showed that the accuracy of our predictive models was on par with that of haematology specialists. Our study is the first to show that a machine learning predictive model based on blood tests alone can be successfully applied to predict haematologic diseases. This result and could open up unprecedented possibilities for medical diagnosis.
Physicians taking care of patients with COVID-19 have described different changes in routine blood parameters. However, these changes hinder them from performing COVID-19 diagnoses. We constructed a machine learning model for COVID-19 diagnosis that was based and cross-validated on the routine blood tests of 5333 patients with various bacterial and viral infections, and 160 COVID-19-positive patients. We selected the operational ROC point at a sensitivity of 81.9% and a specificity of 97.9%. The cross-validated AUC was 0.97. The five most useful routine blood parameters for COVID-19 diagnosis according to the feature importance scoring of the XGBoost algorithm were: MCHC, eosinophil count, albumin, INR, and prothrombin activity percentage. t-SNE visualization showed that the blood parameters of the patients with a severe COVID-19 course are more like the parameters of a bacterial than a viral infection. The reported diagnostic accuracy is at least comparable and probably complementary to RT-PCR and chest CT studies. Patients with fever, cough, myalgia, and other symptoms can now have initial routine blood tests assessed by our diagnostic tool. All patients with a positive COVID-19 prediction would then undergo standard RT-PCR studies to confirm the diagnosis. We believe that our results represent a significant contribution to improvements in COVID-19 diagnosis.
Background: Adverse Drug Reactions (ADRs) have been regarded as a major public health problem since they represent a sizable percentage of admissions. Unfortunately, there is a wide variation of ADR related admissions among different studies. The aim of this study was to evaluate the frequency of ADR related admissions and its dependency on reporting and method of detection, urgency of admissions and included medical departments reflecting department/hospital type within one study.
The information on patient medication on hospital admission and discharge is incomplete. Half of patients on admission and almost two-thirds on discharge had pDDIs. ADRs due to DDIs caused 1.2% of admissions to medical departments in Ljubljana's primary city and tertiary referral hospital.
There are very limited pre-clinical comparative data and no randomised controlled trials assessing effectiveness of the antivenoms against different Vipera species. Most descriptive data suggest the efficacy of Zagreb, ViperFAV and ViperaTAb antivenoms by the intravenous route but not intramuscular route, although this is level D evidence. Reported adverse reactions were rare, suggesting that the modern intravenous antivenoms are of good quality. Better and more systematic data, including perhaps randomized controlled trials comparing different antivenoms, are required for the many hundreds of antivenom administrations that occur annually across Europe.
Acute symptomatic hyponatremia after ecstasy (3,4 methyldioxymethamphetamine; MDMA) ingestion is well documented and has been attributed to the syndrome of inappropriate antidiuretic hormone (SIADH). We report the case of an 18-year-old woman who took five tablets of ecstasy in a suicide attempt and drank 1700 ml water at the Emergency Department (ED). The laboratory findings obtained 5 h after ingestion showed a serum sodium concentration of 130 mmol/l, plasma osmolality of 264 mOsm/kg, urinary osmolality of 335 mOsm/kg and natriuresis of 101 mmol/l. The plasma arginine vasopressin level by radioimmunoassay was 33.7 pmol/l 5 h after ingestion. A gas chromatography-mass spectrometry assay confirmed MDMA in blood samples, with serum concentrations of 0.87 mg/l on arrival. This case report strongly suggests that MDMA reduces serum sodium levels through the dual pathways of SIADH and polydipsia. Accordingly, we believe that hyponatremia may be prevented in ED patients after MDMA ingestion by the early restriction of water intake.
Patients on a stable baclofen regime can develop baclofen toxicity due to acute renal failure. Haemodialysis removes baclofen as effectively as normal kidneys, and it would appear that haemodialysis is a reasonable treatment modality in patients with accidental baclofen overdose due to acute renal failure.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.