No abstract

Background/Aim: To investigate whether a radiomic machine learning (ML) approach employing texture-analysis (TA) features extracted from primary tumor lesions (PTLs) is able to predict tumor grade (TG) and nodal status (NS) in patients with oropharyngeal (OP) and oral cavity (OC) squamous-cell carcinoma (SCC). Patients and Methods: Contrast-enhanced CT images of 40 patients with OP and OC SCC were post-processed to extract TA features from PTLs. A feature selection method and different ML algorithms were applied to find the most accurate subset of features to predict TG and NS. Results: For the prediction of TG, the best accuracy (92.9%) was achieved by Naïve Bayes (NB), bagging of NB and K Nearest Neighbor (KNN). For the prediction of NS, J48, NB, bagging of NB and boosting of J48 overcame the accuracy of 90%. Conclusion: A radiomic ML approach applied to PTLs is able to predict TG and NS in patients with OC and OP SCC.

Stroke is among the leading causes of death and disability worldwide. Approximately 20–25% of stroke survivors present severe disability, which is associated with increased mortality risk. Prognostication is inherent in the process of clinical decision-making. Machine learning (ML) methods have gained increasing popularity in the setting of biomedical research. The aim of this study was twofold: assessing the performance of ML tree-based algorithms for predicting three-year mortality model in 1207 stroke patients with severe disability who completed rehabilitation and comparing the performance of ML algorithms to that of a standard logistic regression. The logistic regression model achieved an area under the Receiver Operating Characteristics curve (AUC) of 0.745 and was well calibrated. At the optimal risk threshold, the model had an accuracy of 75.7%, a positive predictive value (PPV) of 33.9%, and a negative predictive value (NPV) of 91.0%. The ML algorithm outperformed the logistic regression model through the implementation of synthetic minority oversampling technique and the Random Forests, achieving an AUC of 0.928 and an accuracy of 86.3%. The PPV was 84.6% and the NPV 87.5%. This study introduced a step forward in the creation of standardisable tools for predicting health outcomes in individuals affected by stroke.

Purpose The best treatment for femur fractures is the surgical one within 48 h from the admission to the hospital. These fractures have serious consequences, both in terms of morbidity and socio-economic impact. In the hospital A.O.R.N. Cardarelli of Naples in Italy, the mean pre-operative length of hospital stay (LOS) was nine days and just 4 per cent of patients was operated within the suggested time. Therefore, a diagnostic-therapeutic-assistance path (DTAP) was implemented to improve the process. Design/methodology/approach This paper analyzes two groups of patients (534 and 562, respectively) before and after the introduction of DTAP, through six sigma (SS) based on define, measure, analyze, improve and control cycle. Age, gender, American Society of Anaesthesiologists (ASA) score, cardiovascular diseases, diabetes and allergies were used as independent subgrouping variables. The t-tests and chi-square were performed to compare the groups, tools of SS were used. Findings The analyses were conducted considering overall patients and some subgroups. The overall reduction in LOS was about 54 per cent, patients without cardiovascular diseases and with a low ASA score had the highest reduction, more than 60 per cent. All the p-values proved a high statistically significant difference between the two groups. Research limitations/implications The influence of the Italian health-care system is a minor limitation while, unfortunately, the lack of a follow-up did not allow quantifying the real gain in health of patients. A lean thinking analysis would suit this context. Practical implications There are practical advantages for both hospital and patients: the hospital will have an increase in admissions and more beds available, while patients will benefit of a faster intervention and a shorter wait. Originality/value This is the first analysis through SS of DTAP showing its positive influences in terms of both socio-economic impact and patients’ outcome. Policy leaders could use this study as an example to evaluate the introduction of the same clinical pathway in other health facilities.

Purpose Since healthcare spending accounts for approximately 6.6 per cent of the gross domestic product, reducing waste in health facilities is necessary to generate significant cost savings. After previous work concerning the application of Lean Six Sigma (LSS) to hip surgery, the purpose of this paper is to use LSS as the correct methodology to analyse a clinical pathway. Fast track surgery was introduced to the Complex Operative Unit of Orthopaedic and Traumatology of the University Hospital “Federico II” to improve quality and further reduce costs associated with prosthetic hip replacement surgery. Design/methodology/approach The DMAIC (Define, measure, analyse, improve, control) roadmap was used as the typical problem-solving approach of the LSS methodology. A rigorous process of defining, measuring, analysing, improving and controlling business problems can be used to reach fixed goals. The paper was written following the Standards for Quality Improvement Reporting Excellence (SQUIRES Guidelines). Findings In this work, the authors found that multiple variables could influence the length of hospital stay (LOS) for inpatient treatment, thereby increasing patient management costs due to longer periods of hospitalisation. Therefore, LSS analysis of the implemented corrective actions demonstrated the efficacy and efficiency of the novel protocol. The average LOS was reduced from 10.66 to 7.8 days (−26.8 per cent). Originality/value The introduction of fast track surgery was validated through a rigorous LSS analysis, which demonstrated that the new protocol benefitted both patients and the hospital.