Multiple regression model to analyze the total LOS for patients undergoing laparoscopic appendectomy.

BACKGROUND: The rapid growth in the complexity of services and stringent quality requirements present a challenge to all healthcare facilities, especially from an economic perspective. The goal is to implement different strategies that allows to enhance and obtain health processes closer to standards. The Length Of Stay (LOS) is a very useful parameter for the management of services within the hospital and is an index evaluated for the management of costs. In fact, a patient's LOS can be affected by a number of factors, including their particular condition, medical history, or medical needs. To reduce and better manage the LOS it is necessary to be able to predict this value. METHODS: In this study, a predictive model was built for the total LOS of patients undergoing laparoscopic appendectomy, one of the most common emergency procedures. Demographic and clinical data of the 357 patients admitted at "San Giovanni di Dio e Ruggi d'Aragona" University Hospital of Salerno (Italy) had used as independent variable of the multiple linear regression model. RESULTS: The obtained model had an R2 value of 0.570 and, among the independent variables, the significant variables that most influence the total LOS were Age, Pre-operative LOS, Presence of Complication and Complicated diagnosis. CONCLUSION: This work designed an effective and automated strategy for improving the prediction of LOS, that can be useful for enhancing the preoperative pathways. In this way it is possible to characterize the demand and to be able to estimate a priori the occupation of the beds and other related hospital resources.

Soft Transducer for Patient's Vitals Telemonitoring with Deep Learning-Based Personalized Anomaly Detection.

This work addresses the design, development and implementation of a 4.0-based wearable soft transducer for patient-centered vitals telemonitoring. In particular, first, the soft transducer measures hypertension-related vitals (heart rate, oxygen saturation and systolic/diastolic pressure) and sends the data to a remote database (which can be easily consulted both by the patient and the physician). In addition to this, a dedicated deep learning algorithm, based on a Long-Short-Term-Memory Autoencoder, was designed, implemented and tested for providing an alert when the patient's vitals exceed certain thresholds, which are automatically personalized for the specific patient. Furthermore, a mobile application (EcO2u) was developed to manage the entire data flow and facilitate the data fruition; this application also implements an innovative face-detection algorithm that ensures the identity of the patient. The robustness of the proposed soft transducer was validated experimentally on five individuals, who used the system for 30 days. The experimental results demonstrated an accuracy in anomaly detection greater than 93%, with a true positive rate of more than 94%.

Overcrowding analysis in emergency department through indexes: a single center study.

INTRODUCTION: Overcrowding in the Emergency Department (ED) is one of the major issues that must be addressed in order to improve the services provided in emergency circumstances and to optimize their quality. As a result, in order to help the patients and professionals engaged, hospital organizations must implement remedial and preventative measures. Overcrowding has a number of consequences, including inadequate treatment and longer hospital stays; as a result, mortality and the average duration of stay in critical care units both rise. In the literature, a number of indicators have been used to measure ED congestion. EDWIN, NEDOCS and READI scales are considered the most efficient ones, each of which is based on different parameters regarding the patient management in the ED. METHODS: In this work, EDWIN Index and NEDOCS Index have been calculated every hour for a month period from February 9th to March 9th, 2020 and for a month period from March 10th to April 9th, 2020. The choice of the period is related to the date of the establishment of the lockdown in Italy due to the spread of Coronavirus; in fact on 9 March 2020 the Italian government issued the first decree regarding the urgent provisions in relation to the COVID-19 emergency. Besides, the Pearson correlation coefficient has been used to evaluate how much the EDWIN and NEDOCS indexes are linearly dependent. RESULTS: EDWIN index follows a trend consistent with the situation of the first lockdown period in Italy, defined by extreme limitations imposed by Covid-19 pandemic. The 8:00-20:00 time frame was the most congested, with peak values between 8:00 and 12:00. on the contrary, in NEDOCS index doesn't show a trend similar to the EDWIN one, resulting less reliable. The Pearson correlation coefficient between the two scales is 0,317. CONCLUSION: In this study, the EDWIN Index and the NEDOCS Index were compared and correlated in order to assess their efficacy, applying them to the case study of the Emergency Department of "San Giovanni di Dio e Ruggi d'Aragona" University Hospital during the Covid-19 pandemic. The EDWIN scale turned out to be the most realistic model in relation to the actual crowding of the ED subject of our study. Besides, the two scales didn't show a significant correlation value.

A case study to investigate the impact of overcrowding indices in emergency departments.

BACKGROUND: Emergency department (ED) overcrowding is widespread in hospitals in many countries, causing severe consequences to patient outcomes, staff work and the system, with an overall increase in costs. Therefore, health managers are constantly looking for new preventive and corrective measures to counter this phenomenon. To do this, however, it is necessary to be able to characterize the problem objectively. For this reason, various indices are used in the literature to assess ED crowding. In this work, we explore the use of two of the most widespread crowding indices in an ED of an Italian national hospital, investigate their relationships and discuss their effectiveness. METHODS: In this study, two of the most widely used indices in the literature, the National Emergency Department Overcrowding Scale (NEDOCS) and the Emergency Department Working Index (EDWIN), were analysed to characterize overcrowding in the ED of A.O.R.N. "A. Cardarelli" of Naples, which included 1678 clinical cases. The measurement was taken every 15 minutes for a period of 7 days. RESULTS: The results showed consistency in the use of EDWIN and NEDOCS indices as measures of overcrowding, especially in severe overcrowding conditions. Indeed, in the examined case study, both EDWIN and NEDOCS showed very low rates of occurrence of severe overcrowding (2-3%). In contrast, regarding differences in the estimation of busy to overcrowded ED rates, the EDWIN index proved to be less sensitive in distinguishing these variations in the occupancy of the ED. Furthermore, within the target week considered in the study, the results show that, according to both EDWIN and NEDOCS, higher overcrowding rates occurred during the middle week rather than during the weekend. Finally, a low degree of correlation between the two indices was found. CONCLUSIONS: The effectiveness of both EDWIN and NEDOCS in measuring ED crowding and overcrowding was investigated, and the main differences and relationships in the use of the indices are highlighted. While both indices are useful ED performance metrics, they are not always interchangeable, and their combined use could provide more details in understanding ED dynamics and possibly predicting future critical conditions, thus enhancing ED management.

MRI Radiomics for the Prediction of Fuhrman Grade in Clear Cell Renal Cell Carcinoma: a Machine Learning Exploratory Study.

The Fuhrman nuclear grade is a recognized prognostic factor for patients with clear cell renal cell carcinoma (CCRCC) and its pre-treatment evaluation significantly affects decision-making in terms of management. In this study, we aimed to assess the feasibility of a combined approach of radiomics and machine learning based on MR images for a non-invasive prediction of Fuhrman grade, specifically differentiation of high- from low-grade tumor and grade assessment. Images acquired on a 3-Tesla scanner (T2-weighted and post-contrast) from 32 patients (20 with low-grade and 12 with high-grade tumor) were annotated to generate volumes of interest enclosing CCRCC lesions. After image resampling, normalization, and filtering, 2438 features were extracted. A two-step feature reduction process was used to between 1 and 7 features depending on the algorithm employed. A J48 decision tree alone and in combination with ensemble learning methods were used. In the differentiation between high- and low-grade tumors, all the ensemble methods achieved an accuracy greater than 90%. On the other end, the best results in terms of accuracy (84.4%) in the assessment of tumor grade were achieved by the random forest. These evidences support the hypothesis that a combined radiomic and machine learning approach based on MR images could represent a feasible tool for the prediction of Fuhrman grade in patients affected by CCRCC.

Health technology assessment (HTA) of optoelectronic biosensors for oncology by analytic hierarchy process (AHP) and Likert scale.

BACKGROUND: The multicriteria decision method (MCDM) aims to find conflicts among alternatives by comparing and evaluating them according to various criteria to reach the best compromise solution. The evaluation of a new health technology is extremely important in the health sciences field. The aim of this work is to evaluate a new health technology to assay thyroglobulin in patients with differentiated thyroid cancer to improve its service from an organizational point of view, by planning new and appropriate training activities, ensuring proper use of resources and satisfying the needs of different users. METHODS: The evaluation was performed using two methodologies: the analytic hierarchy process (AHP) and the Likert scale. The AHP is a multicriteria decision approach that assigns a weight to each evaluation criterion according to the decision maker's pairwise comparisons of the criteria. The Likert scale is a psychometric scale employed to study the degree of user satisfaction by measuring opinions. RESULTS: Results show the need of particularly improving clinical efficiency, effectiveness, and return on sales (ROS) related to the technology; technological safety, human resources and other parameters do not need to be improved because of the high satisfaction results of the users. CONCLUSIONS: The application of both methods provided the necessary information to improve the quality of the service, allowing the decision maker to identify the most valuable service features and to improve these to ensure user satisfaction and to identify possible service improvements.

Postoperative Management of Zygomatic Arch Fractures: In-House Rapid Prototyping System for the Manufacture of Protective Facial Shields.

Zygomatic fractures account for 10% to 15% of all facial fractures. The surgical management of isolated zygomatic arch fractures usually requires open reduction treatment without fixation through an intraoral access. Therefore, the main problem in the non-fixed treatment of zygomatic arch fractures is related to the difficulty in obtaining a stable reduction for a period long enough to guarantee the physiological bone healing process. We propose an innovative "in-house" rapid prototyping (RP) protocol for the 3D-zygoma mask manufacture of a patient-specific protective device to apply after zygomatic arch fracture reduction. Our study includes 16 consecutive patients who underwent surgical open reduction for an isolated zygoma fracture without fixation between January 2017 and February 2018. The patients received regular postoperative checks at weeks 1 and 2. Before the device was removed, a multiple choice questionnaire was administered to measure the degree of wearability of the mask. The estimated cost of the production is around &OV0556;5 per case and the construction time is around 90 minutes. Based on the encouraging results, obtained in our experience, we hope that other studies can be conducted to confirm our procedure and improve its functionality in the field of facial trauma.

Lean thinking to improve emergency department throughput at AORN Cardarelli hospital.

BACKGROUND: Throughout the world, emergency departments (ED) are characterized by overcrowding and excessive waiting times. Furthermore, the related delays significantly increase patient mortality and make inefficient use of resources to the detriment of the satisfaction of employees and patients. In this work, lean thinking is applied to the ED of Cardarelli Hospital of Naples with the aim of increasing patient flow, improving the processes that contribute to facilitating the flow of patients through the various stages of medical treatment and eliminating all bottlenecks (queue) as well as all activities that generate waste. METHODS: This project was performed at National Hospital A.O.R.N. A. Cardarelli of Naples. The historical times of access to the ED were analysed from January 2015 to June 2015, for a total of 16,563 records. Subsequently, starting in November 2015, corrective actions were implemented according to the Lean Approach. Data collected after the introduced improvements were collected from April 2016 to June 2016 and compared to those collected during the starting period. RESULTS: The results acquired before application of the Lean Thinking strategy illustrated the as-is process with its drawbacks. An analysis of the non-added value activities was performed to identify the procedures that need to be improved. After implementation of the corrective actions, we observed a positive increase in the performance of the ED, quantified as percentages of hospitalized patients according to triage codes and waiting times. CONCLUSION: This work demonstrates the applicability of Lean Thinking to ED processes and its effectiveness in terms of increasing the efficiency of services and reducing waste (waiting times).

Genetic characterization, micropropagation, and potential use for arsenic phytoremediation of Dittrichia viscosa (L.) Greuter.

In the last decade, many scientists have focused their attention on the search for new plant species that can offer improved capacities to reclaim polluted soils and waters via phytoremediation. In this study, seed batches from three natural populations of Dittrichia viscosa, harvested in rural, urban, and industrial areas of central and southern Italy, were used to: (i) evaluate the genetic and morphological diversity of the populations; (ii) develop an efficient protocol for in-vitro propagation from seedling microcuttings; (iii) achieve optimal acclimatization of micropropagated plants to greenhouse conditions; (iv) test the response to arsenic (As) soil contamination of micropropagated plants. The genetic biodiversity study, based on Random Amplification of Polymorphic DNA (RAPD), as well as the morphometric analysis of 20 seedlings from each population revealed some degree of differentiation among populations. Based on these data, the most biodiverse plants from the three populations (10 lines each) were clonally multiplied by micropropagation using microcuttings of in-vitro grown seedlings. Three culture media were tested and Mureshige and Skoog medium was chosen for both seedling growth and micropropagation. The micropropagated plants responded well to greenhouse conditions and over 95% survived the acclimatization phase. Four clones were tested for their capacity to grow on soil spiked with NaAsO2 and to absorb and accumulate the metalloid. All clones tolerated up to 1.0mg As. At the end of the trial (five weeks), As was detectable only in leaves of As-treated plants and concentration varied significantly among clones. The amount of As present in plants (leaves) corresponded to ca. 0.10-1.7% of the amount supplied. However, As was no longer detectable in soil suggesting that the metalloid was taken up, translocated and probably phytovolatilized.

Long-term clinical results and MRI changes after autologous chondrocyte implantation in the knee of young and active middle aged patients.

BACKGROUND: Autologous chondrocyte implantation (ACI) represents a valid surgical option for symptomatic full-thickness chondral lesions of the knee. Here we report long-term clinical and MRI results of first-generation ACI. MATERIALS AND METHODS: Fifteen patients (mean age 21.3 years) underwent first-generation ACI for symptomatic chondral defects of the knee between 1997 and 2001. The mean size of the lesions was 5.08 cm(2) (range 2-9 cm(2)). Patients were evaluated using the International Knee Documentation Committee (IKDC) Knee Examination Form, the Tegner Activity Scale, and the Knee Injury and Osteoarthritis Outcome Score (KOOS). High-resolution MRI was used to analyze the repair tissue with nine variables (the MOCART scoring system). RESULTS: The mean follow-up period was 148 months (range 125-177 months). ACI resulted in substantial improvements in all clinical outcome parameters, even as much as 12 years after implantation. A significant decrease in the MOCART score was recorded at final measurement. Reoperation was required in 2 patients; failure was caused by partial detachment of the graft in both cases. CONCLUSION: Autologous chondrocyte implantation is an effective and durable solution for the treatment of large, full-thickness cartilage and osteochondral lesions, even in young and active middle-aged patients. High-resolution MRI is a useful and noninvasive method for evaluating the repaired tissue. LEVEL OF EVIDENCE: IV.

Lean Six Sigma Approach to Improve the Management of Patients Undergoing Laparoscopic Cholecystectomy.

Laparoscopic cholecystectomy (LC) is the gold standard technique for gallbladder diseases in both emergency and elective surgery. The incidence of the disease related to an increasingly elderly population coupled with the efficacy and safety of LC treatment resulted in an increase in the frequency of interventions without an increase in surgical mortality. For these reasons, managers implement strategies by which to standardize the process of patients undergoing LC. Specifically, the goal is to ensure, in accordance with the guidelines of the Italian Ministry of Health, a reduction in post-operative length of stay (LOS). In this study, a Lean Six Sigma (LSS) methodological approach was implemented to identify and subsequently investigate, through statistical analysis, the effect that corrective actions have had on the post-operative hospitalization for LC interventions performed in a University Hospital. The analysis of the process, which involved a sample of 478 patients, with an approach guided by the Define, Measure, Analyze, Improve, and Control (DMAIC) cycle, made it possible to reduce the post-operative LOS from an average of 6.67 to 4.44 days. The most significant reduction was obtained for the 60-69 age group, for whom the probability of using LC is higher than for younger people. The LSS offers a methodological rigor that has allowed us, as already known, to make significant improvements to the process, standardizing the result by limiting the variability and obtaining a total reduction of post-operative LOS of 67%.

Prognostic decision support using symbolic dynamics in CTG monitoring.

Foetal heart rate variability is one of the most important parameters to monitor foetal wellbeing. Linear parameters, widely employed to study foetal heart variability, have shown some limitations in highlight dynamics potentially relevant. During the last decades, therefore, nonlinear analysis methods have gained a growing interest to analyze the chaotic nature of cardiac activity. Parameters derived by techniques investigating nonlinear can be included in computerised systems of cardiotocographic monitoring. In this work, we described an application of symbolic dynamics to analyze foetal heart rate variability in healthy foetuses and a concise index, introduced for its classification in antepartum CTG monitoring. The introduced index demonstrated to be capable to highlight differences in heart rate variability and resulted correlated with the Apgar score at birth, in particular, higher variability indexes values are associated to early greater vitality at birth. These preliminary results confirm that SD can be a helpful tool in CTG monitoring, supporting medical decisions in order to assure the maximum well-being of newborns.

Classification and regression model to manage the hospitalization for laparoscopic cholecystectomy.

Gallstone disease (GD) is one of the most common morbidities in the world. Laparoscopic Cholecystectomy (LC) is currently the gold standard, performed in about 96% of cases. The most affected groups are the elderly, who generally have higher pre- and post-operative morbidity and mortality rates and longer Length of Stay (LOS). For this reason, several indicators have been defined to improve quality and efficiency and contain costs. In this study, data from patients who underwent LC at the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital of Salerno in the years 2010-2020 were processed using a Multiple Linear Regression (MLR) model and Classification algorithms in order to identify the variables that most influence LOS. The results of the 2352 patients analyzed showed that pre-operative LOS and Age were the independent variables that most affected LOS. In particular, MLR model had a R2 value equal to 0.537 and the best classification algorithm, Decision Tree, had an accuracy greater than 83%. In conclusion, both the MLR model and the classification algorithms produced significant results that could provide important support in the management of this healthcare process.

Predictive Analysis of Hospital Stay after Caesarean Section: A Single-Center Study.

Caesarean section (CS) rate has seen a significant increase in recent years, especially in industrialized countries. There are, in fact, several causes that justify a CS; however, evidence is emerging that non-obstetric factors may contribute to the decision. In reality, CS is not a risk-free procedure. The intra-operative, post-pregnancy risks and risks for children are just a few examples. From a cost point of view, it must be considered that CS requires longer recovery times, and women often stay hospitalized for several days. This study analyzed data from 12,360 women who underwent CS at the "San Giovanni di Dio e Ruggi D'Aragona" University Hospital between 2010 and 2020 by multiple regression algorithms, including multiple linear regression (MLR), Random Forest, Gradient Boosted Tree, XGBoost, and linear regression, classification algorithms and neural network in order to study the variation of the dependent variable (total LOS) as a function of a group of independent variables. We identify the MLR model as the most suitable because it achieves an R-value of 0.845, but the neural network had the best performance (R = 0.944 for the training set). Among the independent variables, Pre-operative LOS, Cardiovascular disease, Respiratory disorders, Hypertension, Diabetes, Haemorrhage, Multiple births, Obesity, Pre-eclampsia, Complicating previous delivery, Urinary and gynaecological disorders, and Complication during surgery were the variables that significantly influence the LOS. Among the classification algorithms, the best is Random Forest, with an accuracy as high as 77%. The simple regression model allowed us to highlight the comorbidities that most influence the total LOS and to show the parameters on which the hospital management must focus for better resource management and cost reduction.

COVID-19 in Eye Surgery: The Case of a University Hospital.

Coronavirus epidemic has quickly become a global health threat. The ophthalmology department, like all other departments, have adopted resource management and personnel adjustment maneuvers. The aim of this work was to describe the impact of covid on the Ophthalmology Department of University Hospital "Federico II" of Naples. In the study logistical regression was used for a comparison between the pandemic and the previous period, analyzing patient features. The analysis showed a decrease in the number of accesses; reduction of the length of stay; and the statistically dependent variables are as follows: LOS, discharge procedures and admission procedure.

Evaluation of different machine learning algorithms for predicting the length of stay in the emergency departments: a single-centre study.

Background: Recently, crowding in emergency departments (EDs) has become a recognised critical factor impacting global public healthcare, resulting from both the rising supply/demand mismatch in medical services and the paucity of hospital beds available in inpatients units and EDs. The length of stay in the ED (ED-LOS) has been found to be a significant indicator of ED bottlenecks. The time a patient spends in the ED is quantified by measuring the ED-LOS, which can be influenced by inefficient care processes and results in increased mortality and health expenditure. Therefore, it is critical to understand the major factors influencing the ED-LOS through forecasting tools enabling early improvements. Methods: The purpose of this work is to use a limited set of features impacting ED-LOS, both related to patient characteristics and to ED workflow, to predict it. Different factors were chosen (age, gender, triage level, time of admission, arrival mode) and analysed. Then, machine learning (ML) algorithms were employed to foresee ED-LOS. ML procedures were implemented taking into consideration a dataset of patients obtained from the ED database of the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital (Salerno, Italy) from the period 2014-2019. Results: For the years considered, 496,172 admissions were evaluated and 143,641 of them (28.9%) revealed a prolonged ED-LOS. Considering the complete data (48.1% female vs. 51.9% male), 51.7% patients with prolonged ED-LOS were male and 47.3% were female. Regarding the age groups, the patients that were most affected by prolonged ED-LOS were over 64 years. The evaluation metrics of Random Forest algorithm proved to be the best; indeed, it achieved the highest accuracy (74.8%), precision (72.8%), and recall (74.8%) in predicting ED-LOS. Conclusions: Different variables, referring to patients' personal and clinical attributes and to the ED process, have a direct impact on the value of ED-LOS. The suggested prediction model has encouraging results; thus, it may be applied to anticipate and manage ED-LOS, preventing crowding and optimising effectiveness and efficiency of the ED.

Evaluation of sarcopenia and sarcopenic obesity in patients affected by oral squamous cell carcinoma: A retrospective single-center study.

This retrospective single-center study aimed to evaluate the relevance of sarcopenia and sarcopenic obesity as negative prognostic factors in patients with oral squamous cell carcinoma (OSCC). The study was performed on patients who underwent oral squamous cell carcinoma resection surgery. Patients' demographic and clinical variables were collected at diagnosis (sex, age, height, weight, comorbidities, smoke and alcohol consumption, HPV positivity, TNM-stage) and corrected for known prognostic factors (age, body mass index, TNM-stage). The Skeletal Muscle Mass (SMM) and the Cross-Sectional Area (CSA) on pre-treatment CT scans and Body Mass Index (BMI) were measured to assess sarcopenia and sarcopenic obesity correlated to overall survival (OS). Chi-square statistics were used to analyze the differences between the frequencies of each categorical variable with the presence or absence of sarcopenia and sarcopenic obesity. The cumulative overall survival was calculated by the Kaplan-Meier method, and the differences between curves were evaluated by the log-rank test. A Cox proportional hazard regression model was used for univariate and multivariate analysis of the overall survival. Within the limitations of the study, in this sample, sarcopenia did not seem to cause a statistically significant reduction in the overall survival in patients with oral squamous cell carcinoma (Log Rank χ2 = 3.67, p = 0.055; HR 0.996, 95% CI 0.732-1.354, p = 0.979), however, sarcopenic obesity showed a meaningful negative prognostic impact on it (Log Rank χ2 = 5.71, p = 0.017; HR 0.985, 95% CI 0.424-2.286, p = 0.972). Within the limitations of the study it seems that sarcopenic obesity, age, BMI, and TNM-stage are more relevant negative prognostic factors, influencing overall survival in surgically treated OSCC, than sarcopenia.

Is It Possible to Predict the Length of Stay of Patients Undergoing Hip-Replacement Surgery?

The proximal fracture of the femur and hip is the most common reason for hospitalization in orthopedic departments. In Italy, 115,989 hip-replacement surgeries were performed in 2019, showing the economic relevance of studying this type of procedure. This study analyzed the data relating to patients who underwent hip-replacement surgery in the years 2010-2020 at the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital of Salerno. The multiple linear regression (MLR) model and regression and classification algorithms were implemented in order to predict the total length of stay (LOS). Lastly, using a statistical analysis, the impact of COVID-19 was evaluated. The results obtained from the regression analysis showed that the best model was MLR, with an R2 value of 0.616, compared with XGBoost, Gradient-Boosted Tree, and Random Forest, with R2 values of 0.552, 0.543, and 0.448, respectively. The t-test showed that the variables that most influenced the LOS, with the exception of pre-operative LOS, were gender, age, anemia, fracture/dislocation, and urinary disorders. Among the classification algorithms, the best result was obtained with Random Forest, with a sensitivity of the longest LOS of over 89%. In terms of the overall accuracy, Random Forest and Gradient-Boosted Tree achieved a value of 71.76% and an error of 28.24%, followed by Decision Tree, with an accuracy of 71.13% and an error of 28.87%, and, finally, Support Vector Machine, with an accuracy of 65.06% and an error of 34.94%. A significant difference in cardiovascular disease, fracture/dislocation, and post-operative LOS variables was shown by the chi-squared test and Mann-Whitney test in the comparison between 2019 (before COVID-19) and 2020 (in full pandemic emergency conditions).

Machine Learning and Lean Six Sigma to Assess How COVID-19 Has Changed the Patient Management of the Complex Operative Unit of Neurology and Stroke Unit: A Single Center Study.

Background: In health, it is important to promote the effectiveness, efficiency and adequacy of the services provided; these concepts become even more important in the era of the COVID-19 pandemic, where efforts to manage the disease have absorbed all hospital resources. The COVID-19 emergency led to a profound restructuring-in a very short time-of the Italian hospital system. Some factors that impose higher costs on hospitals are inappropriate hospitalization and length of stay (LOS). The length of stay (LOS) is a very useful parameter for the management of services within the hospital and is an index evaluated for the management of costs. Methods: This study analyzed how COVID-19 changed the activity of the Complex Operative Unit (COU) of the Neurology and Stroke Unit of the San Giovanni di Dio e Ruggi d'Aragona University Hospital of Salerno (Italy). The methodology used in this study was Lean Six Sigma. Problem solving in Lean Six Sigma is the DMAIC roadmap, characterized by five operational phases. To add even more value to the processing, a single clinical case, represented by stroke patients, was investigated to verify the specific impact of the pandemic. Results: The results obtained show a reduction in LOS for stroke patients and an increase in the value of the diagnosis related group relative weight. Conclusions: This work has shown how, thanks to the implementation of protocols for the management of the COU of the Neurology and Stroke Unit, the work of doctors has improved, and this is evident from the values of the parameters taken into consideration.

Risk Factors Analysis of Surgical Infection Using Artificial Intelligence: A Single Center Study.

Background: Surgical site infections (SSIs) have a major role in the evolution of medical care. Despite centuries of medical progress, the management of surgical infection remains a pressing concern. Nowadays, the SSIs continue to be an important factor able to increase the hospitalization duration, cost, and risk of death, in fact, the SSIs are a leading cause of morbidity and mortality in modern health care. Methods: A study based on statistical test and logistic regression for unveiling the association between SSIs and different risk factors was carried out. Successively, a predictive analysis of SSIs on the basis of risk factors was performed. Results: The obtained data demonstrated that the level of surgery contamination impacts significantly on the infection rate. In addition, data also reveals that the length of postoperative hospital stay increases the rate of surgical infections. Finally, the postoperative length of stay, surgery department and the antibiotic prophylaxis with 2 or more antibiotics are a significant predictor for the development of infection. Conclusions: The data report that the type of surgery department and antibiotic prophylaxis there are a statistically significant predictor of SSIs. Moreover, KNN model better handle the imbalanced dataset (48 infected and 3983 healthy), observing highest accuracy value.