Machine learning model prediction of 6-month functional outcome in elderly patients with intracerebral hemorrhage

Spontaneous intracerebral hemorrhage (ICH) has an increasing incidence and a worse outcome in elderly patients. The ability to predict the functional outcome in these patients can be helpful in supporting treatment decisions and establishing prognostic expectations. We evaluated the performance of a machine learning (ML) model to predict the 6-month functional status in elderly patients with ICH leveraging the predictive value of the clinical characteristics at hospital admission. Data were extracted by a retrospective multicentric database of patients?≥?70 years of age consecutively admitted for the management of spontaneous ICH between January 1, 2014 and December 31, 2019. Relevant demographic, clinical, and radiological variables were selected by a feature selection algorithm (Boruta) and used to build a ML model. Outcome was determined according to the Glasgow Outcome Scale (GOS) at 6 months from ICH: dead (GOS 1), poor outcome (GOS 2–3: vegetative status/severe disability), and good outcome (GOS 4–5: moderate disability/good recovery). Ten features were selected by Boruta with the following relative importance order in the ML model: Glasgow Coma Scale, Charlson Comorbidity Index, ICH score, ICH volume, pupillary status, brainstem location, age, anticoagulant/antiplatelet agents, intraventricular hemorrhage, and cerebellar location. Random forest prediction model, evaluated on the hold-out test set, achieved an AUC of 0.96 (0.94–0.98), 0.89 (0.86–0.93), and 0.93 (0.90–0.95) for dead, poor, and good outcome classes, respectively, demonstrating high discriminative ability. A random forest classifier was successfully trained and internally validated to stratify elderly patients with spontaneous ICH into prognostic subclasses. The predictive value is enhanced by the ability of ML model to identify synergy among variables.

     

Natural course of the vitelliform stage in best vitelliform macular dystrophy: a five-year follow-up study

Graefe's Archive for Clinical and Experimental Ophthalmology - The vitelliform stage is the typical phenotypic manifestation of Best vitelliform macular dystrophy (BVMD). As yet, no study has...     

Factors associated with 2-year persistence in fully non reimbursed lipid-lowering treatments

Objective

to evaluate the main factors associated with long-term persistence in fully paid lipid-lowering treatment.

Methods

We selected 628 moderately hypercholesterolemic subjects (M: 307; F: 311, mean age 59 ± 9 years old), to whom we firstly prescribed a statin (N. 397) or different kinds of lipid-lowering nutraceuticals (N. 231). Then, depending on their will, patients took brand statin (N. 194) or generic statins (N. 203).

Results

The main determinants of long-term persistence in therapy are female sex (OR 1.21, 95%CI 1.08–1.42), family history of early cardiovascular disease (OR 1.31, 95%CI 1.13–1.49), baseline LDL-C (OR 1.19, 95%CI 1.02–1.33) and treatment with nutraceuticals versus statins (OR 1.29, 95%CI 1.14–1.38). Persistence appears not to be influenced by patient's age, smoking habit, adverse events during treatment, and estimated cardiovascular risk.

Conclusion

Among self-paying patients with mild hyperlipidemia, medication persistence is highest among those taking nutraceuticals, followed by brand statins, followed by generic statins.     

Non-sustained ventricular tachycardia with Wenckebach exit block

A case of non-sustained, recurrent ventricular tachycardia, manifesting with irregular R-R intervals, is described. Analysis of a long electrocardiographic recording reveals that the arrhythmia is generated by a regularly discharging ectopic ventricular focus, the R-R interval variations being due to a Wenckebach form of exit block.     

Neurilemoma located at the patellar insertion of vastus medialis obliquus

We report a case of a rare neurological tumour arising in the knee joint with no apparent connection to the major nerve trunks in the area. After the patient failed to improve through rehabilitation, surgery was performed, revealing a concomitant tear of the medial meniscus as well as a mass which was excised through an external supero-medial incision into the knee. Histopathological analysis later confirmed the diagnosis of a neurilemoma.     

Lussazione dell’articolazione sternoclavicolare

Dislocation of the sternoclavicular joint is a rarely injury. Dislocations can be anterior or posterior. Anterior dislocation is a usually relatively benign injury, while posterior dislocations may be very serious. In addition to the standard projections, there are also special views for joint evaluation. Computed tomography remains the gold standard. In anterior dislocations, and degree I and II posterior instability, the treatment is conservative, while in case of degree III dislocations, the treatment consists in closed reduction. Operative stabilisation must be considered if closed reduction is unsuccessful.     

Hepatitis C virus recurrence after liver transplantation:A 10-year evaluation

AIM: To evaluate the predictors of 10-year survival of patients with hepatitis C recurrence. METHODS: Data from 358 patients transplanted between 1989 and 2010 in two Italian transplant centers and with evidence of hepatitis C recurrence were analyzed. A χ2, Fisher's exact test and Kruskal Wallis' test were used for categorical and continuous variables, respectively. Survival analysis was performed at 10 years after transplant using the Kaplan-Meier method, and a log-rank test was used to compare groups. A P level less than 0.05 was considered significant for all tests. Multivariate analysis of the predictive role of different variables on 10-year survival was performed by a stepwise Cox logistic regression.RESULTS: The ten-year survival of the entire population was 61.2%. Five groups of patients were identified according to the virological response or lack of a response to antiviral treatment and, among those who were not treated, according to the clinical status(mild hepatitis C recurrence, "too sick to be treated" and patients with comorbidities contraindicating the treatment). While the 10-year survival of treated and untreated patients was not different(59.1% vs 64.7%, P = 0.192), patients with a sustained virological response had a higher 10-year survival rate than both the "non-responders"(84.7% vs 39.8%, P 0.0001) and too sick to be treated(84.7% vs 0%, P 0.0001). Sustained virological responders had a survival rate comparable to patients untreated with mild recurrence(84.7% vs 89.3%). A sustained virological response and young donor age were independent predictors of 10-year survival. CONCLUSION: Sustained virological response significantly increased long-term survival. Awaiting the interferon-free regimen global availability, antiviral treatment might be questionable in selected subjects with mild hepatitis C recurrence.     

Comparison between orlistat plus l-carnitine and orlistat alone on inflammation parameters in obese diabetic patients

To evaluate the effects of 1-year treatment with orlistat plus L-carnitine compared to orlistat alone on body weight, glycemic and lipid control, and inflammatory parameters in obese type 2 diabetic patients. Two hundred and fifty-eight patients with uncontrolled type 2 diabetes mellitus (T2DM) [glycated hemoglobin (HbA(1c)) > 8.0%] in therapy with different oral hypoglycemic agents or insulin were enrolled in this study and randomized to take orlistat 120 mg three times a day plus L-carnitine 2 g one time a day or orlistat 120 mg three times a day. We evaluated the following parameters at baseline and after 3, 6, 9, and 12 months: body weight, body mass index (BMI), glycated hemoglobin (HbA(1c) ), fasting plasma glucose (FPG), postprandial plasma glucose (PPG), fasting plasma insulin (FPI), homeostasis model assessment insulin resistance index (HOMA-IR), total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C), triglycerides (Tg), adiponectin (ADN), leptin, tumor necrosis factor-α (TNF-α), vaspin, and high-sensitivity C-reactive protein (Hs-CRP). We observed a better decrease in body weight, glycemic profile, HOMA-IR, LDL-C, and ADN and a faster improvement in FPI, TC, Tg, leptin, TNF-α, Hs-CRP with orlistat plus L-carnitine compared to orlistat alone. We also recorded an improvement in vaspin with orlistat plus l-carnitine not reached with orlistat alone. Orlistat plus L-carnitine gave a better improvement in body weight, glycemic and lipid profile compared to orlistat alone; furthermore, a faster and better improvement in inflammatory parameters was observed with orlistat plus L-carnitine compared to orlistat alone.     

Epidemiology,pathophysiology and contemporary management of cardiogenic shock – a position statement from the Heart Failure Association of the European Society of Cardiology

Cardiogenic shock (CS) is a complex multifactorial clinical syndrome with extremely high mortality, developing as a continuum, and progressing from the initial insult (underlying cause) to the subsequent occurrence of organ failure and death. There is a large spectrum of CS presentations resulting from the interaction between an acute cardiac insult and a patient's underlying cardiac and overall medical condition. Phenotyping patients with CS may have clinical impact on management because classification would support initiation of appropriate therapies. CS management should consider appropriate organization of the health care services, and therapies must be given to the appropriately selected patients, in a timely manner, whilst avoiding iatrogenic harm. Although several consensus‐driven algorithms have been proposed, CS management remains challenging and substantial investments in research and development have not yielded proof of efficacy and safety for most of the therapies tested, and outcome in this condition remains poor. Future studies should consider the identification of the new pathophysiological targets, and high‐quality translational research should facilitate incorporation of more targeted interventions in clinical research protocols, aimed to improve individual patient outcomes. Designing outcome clinical trials in CS remains particularly challenging in this critical and very costly scenario in cardiology, but information from these trials is imperiously needed to better inform the guidelines and clinical practice. The goal of this review is to summarize the current knowledge concerning the definition, epidemiology, underlying causes, pathophysiology and management of CS based on important lessons from clinical trials and registries, with a focus on improving in‐hospital management.