Comparative Analysis of AI Models for Atypical Pigmented Facial Lesion Diagnosis.

Diagnosing atypical pigmented facial lesions (aPFLs) is a challenging topic for dermatologists. Accurate diagnosis of these lesions is crucial for effective patient management, especially in dermatology, where visual assessment plays a central role. Incorrect diagnoses can result in mismanagement, delays in appropriate interventions, and potential harm. AI, however, holds the potential to enhance diagnostic accuracy and provide reliable support to clinicians. This work aimed to evaluate and compare the effectiveness of machine learning (logistic regression of lesion features and patient metadata) and deep learning (CNN analysis of images) models in dermoscopy diagnosis and the management of aPFLs. This study involved the analysis of 1197 dermoscopic images of facial lesions excised due to suspicious and histologically confirmed malignancy, classified into seven classes (lentigo maligna-LM; lentigo maligna melanoma-LMM; atypical nevi-AN; pigmented actinic keratosis-PAK; solar lentigo-SL; seborrheic keratosis-SK; and seborrheic lichenoid keratosis-SLK). Image samples were collected through the Integrated Dermoscopy Score (iDScore) project. The statistical analysis of the dataset shows that the patients mean age was 65.5 ± 14.2, and the gender was equally distributed (580 males-48.5%; 617 females-51.5%). A total of 41.7% of the sample constituted malignant lesions (LM and LMM). Meanwhile, the benign lesions were mainly PAK (19.3%), followed by SL (22.2%), AN (10.4%), SK (4.0%), and SLK (2.3%). The lesions were mainly localised in the cheek and nose areas. A stratified analysis of the assessment provided by the enrolled dermatologists was also performed, resulting in 2445 evaluations of the 1197 images (2.1 evaluations per image on average). The physicians demonstrated higher accuracy in differentiating between malignant and benign lesions (71.2%) than in distinguishing between the seven specific diagnoses across all the images (42.9%). The logistic regression model obtained a precision of 39.1%, a sensitivity of 100%, a specificity of 33.9%, and an accuracy of 53.6% on the test set, while the CNN model showed lower sensitivity (58.2%) and higher precision (47.0%), specificity (90.8%), and accuracy (59.5%) for melanoma diagnosis. This research demonstrates how AI can enhance the diagnostic accuracy in complex dermatological cases like aPFLs by integrating AI models with clinical data and evaluating different diagnostic approaches, paving the way for more precise and scalable AI applications in dermatology, showing their critical role in improving patient management and the outcomes in dermatology.

Deep Learning Techniques for the Dermoscopic Differential Diagnosis of Benign/Malignant Melanocytic Skin Lesions: From the Past to the Present.

There has been growing scientific interest in the research field of deep learning techniques applied to skin cancer diagnosis in the last decade. Though encouraging data have been globally reported, several discrepancies have been observed in terms of study methodology, result presentations and validation in clinical settings. The present review aimed to screen the scientific literature on the application of DL techniques to dermoscopic melanoma/nevi differential diagnosis and extrapolate those original studies adequately by reporting on a DL model, comparing them among clinicians and/or another DL architecture. The second aim was to examine those studies together according to a standard set of statistical measures, and the third was to provide dermatologists with a comprehensive explanation and definition of the most used artificial intelligence (AI) terms to better/further understand the scientific literature on this topic and, in parallel, to be updated on the newest applications in the medical dermatologic field, along with a historical perspective. After screening nearly 2000 records, a subset of 54 was selected. Comparing the 20 studies reporting on convolutional neural network (CNN)/deep convolutional neural network (DCNN) models, we have a scenario of highly performant DL algorithms, especially in terms of low false positive results, with average values of accuracy (83.99%), sensitivity (77.74%), and specificity (80.61%). Looking at the comparison with diagnoses by clinicians (13 studies), the main difference relies on the specificity values, with a +15.63% increase for the CNN/DCNN models (average specificity of 84.87%) compared to humans (average specificity of 64.24%) with a 14,85% gap in average accuracy; the sensitivity values were comparable (79.77% for DL and 79.78% for humans). To obtain higher diagnostic accuracy and feasibility in clinical practice, rather than in experimental retrospective settings, future DL models should be based on a large dataset integrating dermoscopic images with relevant clinical and anamnestic data that is prospectively tested and adequately compared with physicians.

The Impact of Sex and Arterial Stiffness Interactions on the Outcome after an Acute Ischemic Stroke: A Retrospective Cohort Study.

Background/Objectives: Arterial stiffness (AS) is an independent predictor of cardiovascular events and is associated with a poor prognosis. While AS may represent a novel therapeutic target, recent evidence shows that it is sexually dimorphic. The aim of this study was to evaluate relative sex differences in arterial stiffness and their possible impact on the outcome of acute ischemic stroke. Methods: We retrospectively evaluated a cohort of adult patients with the following inclusion criteria: acute ischemic stroke, which occurred within 24 h from the onset of symptoms, confirmed through neuroimaging examinations, additional evaluations including extracranial and transcranial arterial ultrasound examinations, transthoracic echocardiography, a 12-lead resting ECG, and continuous 24 h in-hospital blood pressure monitoring. Based on the 24 h blood pressure monitoring, the following parameters were evaluated: systolic blood pressure, diastolic blood pressure, mean blood pressure, pulse pressure, and arterial stiffness index (ASI). The modified Rankin scale (mRS) was assessed at 90 days to evaluate the 3-month clinical outcome, defining an unfavorable outcome as an mRS score ≥ 3. To assess the factors associated with unfavorable outcomes, a stepwise logistic regression model was performed on the total sample size, and the analyses were replicated after stratifying by sex. Results: A total of 334 patients (176 males, 158 females) were included in the analysis. There was a significant sex-dependent impact of ASI on the 90-day unfavorable Rankin score (mRS score ≥ 3) as only men had a reduced likelihood of favorable outcomes with increasing arterial stiffness (OR:1.54, 95% CI: 1.06-2.23; P-interaction = 0.023). Conclusions: The influence of ASI on the 3-month functional outcome after acute ischemic stroke is at least in part sex-related, suggesting that, in males, higher ASI values are associated with a worse outcome.

A 3D-printed condom intrauterine balloon tamponade: Design, prototyping, and technical validation.

Post-partum haemorrhage is among the main causes of (preventable) mortality for women in low-resource settings (LRSs), where, in 2017, the mortality ratio was 462 out of every 100 000 live births, over 10 times higher than for high-resource settings. There are different treatments available for post-partum haemorrhage. The intrauterine balloon tamponade is a medical device that proved to be a simple and cost-effective approach. Currently, there are several balloon tamponades available, with different design and working principles. However, all these devices were designed for high-resource settings, presenting several aspects that could be inappropriate for many lower-income countries. This paper presents the results of a preclinical study aiming at informing the design, prototyping and validation of a 3D-printed intrauterine balloon tamponade concept, contributing towards the United Nation's Sustainable Development Goal 3: Good health and Well-being. Frugal engineering concepts and contextualised design techniques were applied throughout, to define the design requirements and specifications. The performance of the final prototype was validated against the requirements of the UK National Health System (NHS) technical guidelines and relevant literature, measuring the water leak and pressure drop over time, both open air and in a approximate uterus model. The resulting prototype is made up of six components, some of which are easy to retrieve, namely a water bottle, a silicone tube and an ordinary condom, while others can be manufactured locally using 3D printers, namely a modified bottle cap, a flow stopper and a valve for holding the condom in place. Validation testing bore promising results with no water or pressure leak open air, and minimal leaks in the approximate uterus model. This demonstrates that the 3D printed condom-based intrauterine balloon tamponade is performing well against the requirements and, when compared to the state of the art, it could be a more appropriate and more resilient solution to low-resource settings, as it bypasses the challenges in the supply of consumables and presents a greener option based on circular economy.

Ankyloglossia in newborns: incidence and breastfeeding follow-up at 1 and 6 months.

BACKGROUND: Ankyloglossia is an anatomical variation of the lingual frenulum that negatively interferes with the functionality of the tongue. This condition can affect breastfeeding negatively. The aim of this study is to assess the prevalence of ankyloglossia among healthy babies born in Siena Hospital and the correlation between ankyloglossia and breastfeeding difficulties. METHODS: We performed an observational prospective study conducted on healthy and breastfed newborns born in Siena Hospital in the period between January and June 2022. The evaluation of lingual frenulum in the first few days of life was performed by Martinelli's Lingual Frenulum Protocol with scores for Infants (MLFPI), while the clinical assessment of breastfeeding initiation was performed by the Breastfeeding Observation and Evaluation Form according to WHO-UNICEF guidelines. We also compared the reliability in predicting breastfeeding of a tool that measured the features of the tongue frenulum: the Bristol Tongue Assessment Tool (BTT). Breastfeeding at one and six months of babies' age was assessed by telephone interview, and information among children's nutrition, weight growth and difficulties found in breastfeeding was also collected. This study was approved by the Pediatric Ethics Committee for Clinical Trials of the Tuscany Region. RESULTS: One hundred and ninety infants were included in the study; 21 (11.05%) had a MLFPI score ≥13. Data at one month of age showed a statistically higher MLFPI score (P value <0.001) in babies with breastfeeding difficulties (median score 13.0, IQR 5.5-14), than in those without (median score 5.0, IQR 2.0-7.5). Data at 6 months of age showed a similar difference in babies with and without breastfeeding difficulties (median 12.0, IQR 4.0-14.0 vs. 5.0, IQR 2.0-8.0 respectively). A MLFPI score ≥13 is positively associated with breastfeeding difficulties at 1 and 6 months. Also, the BTT was positively a risk factor for problems in breastfeeding at 1 and 6 months. CONCLUSIONS: A high MLFPI score is a risk factor of breastfeeding difficulties. In these cases, a referral to experienced personnel is advisable: they can provide the emotional and professional support to the mother-child dyad, and/or refer for surgical evaluation and frenotomy. In our cohort, the usefulness of either MLFPI score or BTT was evident in predicting breastfeeding difficulties; the rate of surgical removal of the frenulum was nonetheless low.

Using Renal Elastography to Predict the Therapeutic Response of Nephrological Patients.

BACKGROUND: The standard method for assessing chronic renal damage is renal biopsy, which has limitations due to its invasiveness. Ultrasound elastography is a non-invasive technique that quantifies tissue elasticity and can be used to determine Young's modulus (YM). Although this breakthrough technology has been successfully employed to evaluate liver stiffness and the extent of fibrosis, its application in kidney-related conditions still needs improvement. METHODS: Our study aimed to verify the correlation between renal elastography and the chronic histological score determined via renal biopsy, evaluate the correlation between elastography and response to treatment in the short-term follow-up (6 months), and compare elastography data between renal disease patients (AKD-P) and healthy controls (HP). RESULTS: The analyzed population consisted of 82 patients (41 HP and 41 AKD-P). The AKD-P were divided into responders (R) or non-responders (NR) based on the criteria established by the guidelines. No association was found between renal stiffness and chronic histological score. Elastography data revealed median YM values of 6.15 kPa for AKD-P and 12.2 kPa for HP, with a statistically significant difference. The median YM values of the R and NR groups were 7.4 KPa and 5.6 KPa, respectively (p = 0.037). CONCLUSIONS: Patient responsiveness was associated with YM, with lower values observed in the NR group. We also found that the healthy controls exhibited significantly higher YM values than the renal disease population.

Evidence-based clinical engineering: Health information technology adverse events identification and classification with natural language processing.

The primary goal of this project is to create a framework to extract Real-World Evidence to support Health Technology Assessment, Health Technology Management, Evidence-Based Maintenance, and Post Market Surveillance (as outlined in the EU Medical Device Regulation 2017/745) of medical devices using Natural Language Processing (NLP) and Artificial Intelligence. An initial literature review on Spontaneous Reporting System databases, Health Information Technologies (HIT) fault classification, and Natural Language Processing has been conducted, from which it clearly emerges that adverse events related to HIT are increasing over time. The proposed framework uses NLP techniques and Explainable Artificial Intelligence models to automatically identify HIT-related adverse event reports. The designed model employs a pre-trained version of ClinicalBERT that has been fine-tuned and tested on 3,075 adverse event reports extracted from the FDA MAUDE database and manually labelled by experts.

Scoping Meta-Review of Methods Used to Assess Artificial Intelligence-Based Medical Devices for Heart Failure.

Artificial intelligence and machine learning (AI/ML) are playing increasingly important roles, permeating the field of medical devices (MDs). This rapid progress has not yet been matched by the Health Technology Assessment (HTA) process, which still needs to define a common methodology for assessing AI/ML-based MDs. To collect existing evidence from the literature about the methods used to assess AI-based MDs, with a specific focus on those used for the management of heart failure (HF), the International Federation of Medical and Biological Engineering (IFMBE) conducted a scoping meta-review. This manuscript presents the results of this search, which covered the period from January 1974 to October 2022. After careful independent screening, 21 reviews, mainly conducted in North America and Europe, were retained and included. Among the findings were that deep learning is the most commonly utilised method and that electronic health records and registries are among the most prevalent sources of data for AI/ML algorithms. Out of the 21 included reviews, 19 focused on risk prediction and/or the early diagnosis of HF. Furthermore, 10 reviews provided evidence of the impact on the incidence/progression of HF, and 13 on the length of stay. From an HTA perspective, the main areas requiring improvement are the quality assessment of studies on AI/ML (included in 11 out of 21 reviews) and their data sources, as well as the definition of the criteria used to assess the selection of the most appropriate AI/ML algorithm.

Rationale for the evaluation of renal functional reserve in allogeneic stem cell transplantation candidates: a pilot study.

Background: The main purpose of our study was to evaluate the ability of renal functional reserve (RFR) to stratify the risk of acute kidney injury (AKI) occurrence within 100 days of hematopoietic stem cell transplantation (HSCT) and to predict any functional recovery or the onset of chronic kidney disease. A secondary aim was to identify the clinical/laboratory risk factors for the occurrence of AKI. Methods: The study design is prospective observational. We enrolled 48 patients with normal basal glomerular filtration rate (bGFR) who underwent allogenic HSCT. A multiparameter assessment and the Renal Functional Reserve Test (RFR-T) using an oral protein load stress test were performed 15 days before the HSCT. Results: Different RFRs corresponded to the same bGFR values. Of 48 patients, 29 (60%) developed AKI. Comparing the AKI group with the group that did not develop AKI, no statistically significant difference emerged in any characteristic related to demographic, clinical or multiparameter assessment variables except for the estimated GFR (eGFR). eGFR ≤100 mL/min/1.73 m2 was significantly related to the risk of developing AKI (Fisher's exact test, P = .001). Moreover, RFR-T was lower in AKI+ patients vs AKI- patients, but did not allow statistical significance (28% vs 40%). In AKI patients, RFR >20% was associated with complete functional recovery (one-sided Fisher's exact test, P = .041). The risk of failure to recover increases significantly when RFR ≤20% (odds ratio = 5.50, 95% confidence interval = 1.06-28.4). Conclusion: RFR identifies subclinical functional deterioration conditions essential for post-AKI recovery. In our cohort of patients with no kidney disease (NKD), the degree of pre-HSCT eGFR is associated with AKI risk, and a reduction in pre-HSCT RFR above a threshold of 20% is related to complete renal functional recovery post-AKI. Identifying eGFR first and RFR second could help select patients who might benefit from changes in transplant management or early nephrological assessment.

Artificial intelligence for non-invasive glycaemic-events detection via ECG in a paediatric population: study protocol.

Purpose: Paediatric Type 1 Diabetes (T1D) patients are at greater risk for developing severe hypo and hyperglycaemic events due to poor glycaemic control. To reduce the risk of adverse events, patients need to achieve the best possible glycaemic management through frequent blood glucose monitoring with finger prick or Continuous Glucose Monitoring (CGM) systems. However, several non-invasive techniques have been proposed aiming at exploiting changes in physiological parameters based on glucose levels. The overall objective of this study is to validate an artificial intelligence (AI) based algorithm to detect glycaemic events using ECG signals collected through non-invasive device. Methods: This study will enrol T1D paediatric participants who already use CGM. Participants will wear an additional non-invasive wearable device for recording physiological data and respiratory rate. Glycaemic measurements driven through ECG variables are the main outcomes. Data collected will be used to design, develop and validate the personalised and generalized classifiers based on a deep learning (DL) AI algorithm, able to automatically detect hypoglycaemic events by using few ECG heartbeats recorded with wearable devices. Results: Data collection is expected to be completed approximately by June 2023. It is expected that sufficient data will be collected to develop and validate the AI algorithm. Conclusion: This is a validation study that will perform additional tests on a larger diabetes sample population to validate the previous pilot results that were based on four healthy adults, providing evidence on the reliability of the AI algorithm in detecting glycaemic events in paediatric diabetic patients in free-living conditions. Trial registration: ClinicalTrials.gov identifier: NCT03936634. Registered on 11 March 2022, retrospectively registered, https://www.clinicaltrials.gov/ct2/show/NCT05278143?titles=AI+for+Glycemic+Events+Detection+Via+ECG+in+a+Pediatric+Population&draw=2&rank=1. Supplementary information: The online version contains supplementary material available at 10.1007/s12553-022-00719-x.

A robotic arm for safe and accurate control of biomedical equipment during COVID-19.

Purpose: Hospital facilities and social life, along with the global economy, have been severely challenged by COVID-19 since the World Health Organization (WHO) declared it a pandemic in March 2020. Since then, countless ordinary citizens, as well as healthcare workers, have contracted the virus by just coming into contact with infected surfaces. In order to minimise the risk of getting infected by contact with such surfaces, our study aims to design, prototype, and test a new device able to connect users, such as common citizens, doctors or paramedics, with either common-use interfaces (e.g., lift and snack machine keyboards, traffic light push-buttons) or medical-use interfaces (e.g., any medical equipment keypad). Method: To this purpose, the device was designed with the help of Unified Modelling Language (UML) schemes, and was informed by a risk analysis, that highlighted some of its essential requirements and specifications. Consequently, the chosen constructive solution of the robotic system, i.e., a robotic-arm structure, was designed and manufactured using computer-aided design and 3D printing. Result: The final prototype included a properly programmed micro-controller, linked via Bluetooth to a multi-platform mobile phone app, which represents the user interface. The system was then successfully tested on different physical keypads and touch screens. Better performance of the system can be foreseen by introducing improvements in the industrial production phase. Conclusion: This first prototype paves the way for further research in this area, allowing for better management and preparedness of next pandemic emergencies.

Designing and developing a mobile application for indoor real-time positioning and navigation in healthcare facilities.

BACKGROUND: Navigation portable applications have largely grown during the last years. However, the majority of them works just for outdoor positioning and routing, due to their architecture based upon Global Positioning System signals. Real-Time Positioning System intended to provide position estimation inside buildings is known as Indoor Positioning System (IPS). OBJECTIVE: This paper presents an IPS implemented as a mobile application that can guide patients and visitors throughout a healthcare premise. METHODS: The proposed system exploits the geolocation capabilities offered by existing navigation frameworks for determining and displaying the user's position. A hybrid mobile application architecture has been adopted because it allows to deploy the code to multiple platforms, simplifying maintenance and upgrading. RESULTS: The developed application features two different working modes for on-site and off-site navigation, which offer both the possibility of actual navigation within the hospital, or planning a route from a list of available starting points to the desired target, without being within the navigable area. Tests have been conducted to evaluate the performance and the accuracy of the system. CONCLUSION: The proposed application aims to overcome the limitations of Global Navigation Satellite System by using magnetic fingerprinting in combination with sensor fusion simultaneously. This prevents to rely on a single technology, reducing possible system failures and increasing the scalability.

Radio Frequency Identification (RFID) in health care: where are we? A scoping review.

Purpose: (RFID) is a technology that uses radio waves for data collection and transfer, so data is captured efficiently, automatically and in real time without human intervention. This technology, alone or in addition to other technologies has been considered as a possible solution to reduce problems that endanger public health or to improve its management. This scoping review aims to provide readers with an up-to-date picture of the use of this technology in health care settings. Methods: This scoping review examines the state of RFID technology in the healthcare area for the period 2017-2022, specifically addressing RFID versatility and investigating how this technology can contribute to radically change the management of public health. The guidelines of the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) have been followed. Literature reviews or surveys were excluded. Only articles describing technologies implemented on a real environment or on prototypes were included. Results: The search returned 366 results. After screening, based on title and abstract, 58 articles were considered suitable for this work. 11 articles were reviewed because they met the qualifying requirements. The study of the selected articles highlighted six matters that can be profitably impacted by this technology. Conclusion: The selected papers show that this technology can improve patient safety by reducing medical errors, that can occur within operating rooms. It can also be the solution to overcome the problem of the black market in counterfeiting drugs, or as a prevention tool. Further research is needed, especially on data management, security, and privacy, given the sensitive nature of medical information.

Hypertension Diagnosis and Management in Africa Using Mobile Phones: A Scoping Review.

Target 3.4 of the third Sustainable Development Goal (SDG) of the United Nations (UN) General Assembly proposes to reduce premature mortality from non-communicable diseases (NCDs) by one-third. Epidemiological data presented by the World Health Organization (WHO) in 2016 show that out of a total of 57 million deaths worldwide, approximately 41 million deaths occurred due to NCDs, with 78% of such deaths occurring in low-and-middle-income countries (LMICs). The majority of investigations on NCDs agree that the leading risk factor for mortality worldwide is hypertension. Over 75% of the world's mobile phone subscriptions reside in LMICs, hence making the mobile phone particularly relevant to mHealth deployment in Africa. This study is aimed at determining the scope of the literature available on hypertension diagnosis and management in Africa, with particular emphasis on determining the feasibility, acceptability and effectiveness of interventions based on the use of mobile phones. The bulk of the evidence considered overwhelmingly shows that SMS technology is yet the most used medium for executing interventions in Africa. Consequently, the need to define novel and superior ways of providing effective and low-cost monitoring, diagnosis, and management of hypertension- related NCDs delivered through artificial intelligence and machine learning techniques is clear.

A Machine Learning Decision Support System (DSS) for Neuroendocrine Tumor Patients Treated with Somatostatin Analog (SSA) Therapy.

The application of machine learning (ML) techniques could facilitate the identification of predictive biomarkers of somatostatin analog (SSA) efficacy in patients with neuroendocrine tumors (NETs). We collected data from 74 patients with a pancreatic or gastrointestinal NET who received SSA as first-line therapy. We developed three classification models to predict whether the patient would experience a progressive disease (PD) after 12 or 18 months based on clinic-pathological factors at the baseline. The dataset included 70 samples and 15 features. We initially developed three classification models with accuracy ranging from 55% to 70%. We then compared ten different ML algorithms. In all but one case, the performance of the Multinomial Naïve Bayes algorithm (80%) was the highest. The support vector machine classifier (SVC) had a higher performance for the recall metric of the progression-free outcome (97% vs. 94%). Overall, for the first time, we documented that the factors that mainly influenced progression-free survival (PFS) included age, the number of metastatic sites and the primary site. In addition, the following factors were also isolated as important: adverse events G3-G4, sex, Ki67, metastatic site (liver), functioning NET, the primary site and the stage. In patients with advanced NETs, ML provides a predictive model that could potentially be used to differentiate prognostic groups and to identify patients for whom SSA therapy as a single agent may not be sufficient to achieve a long-lasting PFS.

The Inadequacy of Regulatory Frameworks in Time of Crisis and in Low-Resource Settings: Personal Protective Equipment and COVID-19.

COVID-19 pandemic is plaguing the world and representing the most significant stress test for many national healthcare systems and services, since their foundation. The supply-chain disruption and the unprecedented request for intensive care unit (ICU) beds have created in Europe conditions typical of low-resources settings. This generated a remarkable race to find solutions for the prevention, treatment and management of this disease which is involving a large amount of people. Every day, new Do-It-Yourself (DIY) solutions regarding personal protective equipment and medical devices populate social media feeds. Many companies (e.g., automotive or textile) are converting their traditional production to manufacture the most needed equipment (e.g., respirators, face shields, ventilators etc.). In this chaotic scenario, policy makers, international and national standards bodies, along with the World Health Organization (WHO) and scientific societies are making a joint effort to increase global awareness and knowledge about the importance of respecting the relevant requirements to guarantee appropriate quality and safety for patients and healthcare workers. Nonetheless, ordinary procedures for testing and certification are currently questioned and empowered with fast-track pathways in order to speed-up the deployment of new solutions for COVID-19. This paper shares critical reflections on the current regulatory framework for the certification of personal protective equipment. We hope that these reflections may help readers in navigating the framework of regulations, norms and international standards relevant for key personal protective equipment, sharing a subset of tests that should be deemed essential even in a period of crisis.

Evidence-based medical equipment management: a convenient implementation.

Maintenance is a crucial subject in medical equipment life cycle management. Evidence-based maintenance consists of the continuous performance monitoring of equipment, starting from the evidence-the current state in terms of failure history-and improvement of its effectiveness by making the required changes. This process is very important for optimizing the use and allocation of the available resources by clinical engineering departments. Medical equipment maintenance is composed of two basic activities: scheduled maintenance and corrective maintenance. Both are needed for the management of the entire set of medical equipment in a hospital. Because the classification of maintenance service work orders reveals specific issues related to frequent problems and failures, specific codes have been applied to classify the corrective and scheduled maintenance work orders at Careggi University Hospital (Florence, Italy). In this study, a novel set of key performance indicators is also proposed for evaluating medical equipment maintenance performance. The purpose of this research is to combine these two evidence-based methods to assess every aspect of the maintenance process and provide an objective and standardized approach that will support and enhance clinical engineering activities. Starting from the evidence (i.e. failures), the results show that the combination of these two methods can provide a periodical cross-analysis of maintenance performance that indicates the most appropriate procedures. Graphical abstract The left side shows a block diagram of the process needed to calculate the proposed set of KPIs, starting from technological, organizational and financial data. On the upper right it is shown an example of scheduled maintenance analysis for a specific class of equipment (legend in the article body). The bottom right part shows how the KPIs can be implemented in a business intelligence dashboard.

Testing of mechanical ventilators and infant incubators in healthcare institutions.

The medical device industry has grown rapidly and incessantly over the past century. The sophistication and complexity of the designed instrumentation is nowadays rising and, with it, has also increased the need to develop some better, more effective and efficient maintenance processes, as part of the safety and performance requirements. This paper presents the results of performance tests conducted on 50 mechanical ventilators and 50 infant incubators used in various public healthcare institutions. Testing was conducted in accordance to safety and performance requirements stated in relevant international standards, directives and legal metrology policies. Testing of output parameters for mechanical ventilators was performed in 4 measuring points while testing of output parameters for infant incubators was performed in 7 measuring points for each infant incubator. As performance criteria, relative error of output parameters for mechanical ventilators and absolute error of output parameters for infant incubators was calculated. The ranges of permissible error, for both groups of devices, are regulated by the Rules on Metrological and Technical Requirements published in the Official Gazette of Bosnia and Herzegovina No. 75/14, which are defined based on international recommendations, standards and guidelines. All ventilators and incubators were tested by etalons calibrated in an ISO 17025 accredited laboratory, which provides compliance to international standards for all measured parameters.The results show that 30% of the tested medical devices are not operating properly and should be serviced, recalibrated and/or removed from daily application.

A multi-layer monitoring system for clinical management of Congestive Heart Failure.

BACKGROUND: Congestive Heart Failure (CHF) is a serious cardiac condition that brings high risks of urgent hospitalization and death. Remote monitoring systems are well-suited to managing patients suffering from CHF, and can reduce deaths and re-hospitalizations, as shown by the literature, including multiple systematic reviews. METHODS: The monitoring system proposed in this paper aims at helping CHF stakeholders make appropriate decisions in managing the disease and preventing cardiac events, such as decompensation, which can lead to hospitalization or death. Monitoring activities are stratified into three layers: scheduled visits to a hospital following up on a cardiac event, home monitoring visits by nurses, and patient's self-monitoring performed at home using specialized equipment. Appropriate hardware, desktop and mobile software applications were developed to enable a patient's monitoring by all stakeholders. For the first two layers, we designed and implemented a Decision Support System (DSS) using machine learning (Random Forest algorithm) to predict the number of decompensations per year and to assess the heart failure severity based on a variety of clinical data. For the third layer, custom-designed sensors (the Blue Scale system) for electrocardiogram (EKG), pulse transit times, bio-impedance and weight allowed frequent collection of CHF-related data in the comfort of the patient's home. We also performed a short-term Heart Rate Variability (HRV) analysis on electrocardiograms self-acquired by 15 healthy volunteers and compared the obtained parameters with those of 15 CHF patients from PhysioNet's PhysioBank archives. RESULTS: We report numerical performances of the DSS, calculated as multiclass accuracy, sensitivity and specificity in a 10-fold cross-validation. The obtained average accuracies are: 71.9% in predicting the number of decompensations and 81.3% in severity assessment. The most serious class in severity assessment is detected with good sensitivity and specificity (0.87 / 0.95), while, in predicting decompensation, high specificity combined with good sensitivity prevents false alarms. The HRV parameters extracted from the self-measured EKG using the Blue Scale system of sensors are comparable with those reported in the literature about healthy people. CONCLUSIONS: The performance of DSSs trained with new patients confirmed the results of previous work, and emphasizes the strong correlation between some CHF markers, such as brain natriuretic peptide (BNP) and ejection fraction (EF), with the outputs of interest. Comparing HRV parameters from healthy volunteers with HRV parameters obtained from PhysioBank archives, we confirm the literature that considers the HRV a promising method for distinguishing healthy from CHF patients.

A machine learning system to improve heart failure patient assistance.

In this paper, we present a clinical decision support system (CDSS) for the analysis of heart failure (HF) patients, providing various outputs such as an HF severity evaluation, HF-type prediction, as well as a management interface that compares the different patients' follow-ups. The whole system is composed of a part of intelligent core and of an HF special-purpose management tool also providing the function to act as interface for the artificial intelligence training and use. To implement the smart intelligent functions, we adopted a machine learning approach. In this paper, we compare the performance of a neural network (NN), a support vector machine, a system with fuzzy rules genetically produced, and a classification and regression tree and its direct evolution, which is the random forest, in analyzing our database. Best performances in both HF severity evaluation and HF-type prediction functions are obtained by using the random forest algorithm. The management tool allows the cardiologist to populate a "supervised database" suitable for machine learning during his or her regular outpatient consultations. The idea comes from the fact that in literature there are a few databases of this type, and they are not scalable to our case.