A survey on Artificial Intelligence and Big Data utilisation in Italian clinical laboratories.

OBJECTIVES: The Italian Society of Clinical Biochemistry and Clinical Molecular Biology (SIBioC) Big Data and Artificial Intelligence (BAI) Working Group promoted a survey to frame the knowledge, skills and technological predisposition in clinical laboratories. METHODS: A questionnaire, focussing on digitization, information technology (IT) infrastructures, data accessibility, and BAI projects underway was sent to 1,351 SIBioC participants. The responses were evaluated using SurveyMonkey software and Google Sheets. RESULTS: The 227 respondents (17%) from all over Italy (47% of 484 labs), mainly biologists, laboratory physicians and managers, mostly from laboratories of public hospitals, revealed lack of hardware, software and corporate Wi-Fi, and dearth of PCs. Only 25% work daily on clouds, while 65%-including Laboratory Directors-cannot acquire health data from sources other than laboratories. Only 50% of those with access can review a clinical patient's health record, while the other access only to laboratory information. The integration of laboratory data with other health data is mostly incomplete, which limits BAI-type analysis. Many are unaware of integration platforms. Over 90% report pulling data from the Laboratory Information System, with varying degrees of autonomy. Very few have already undertaken BAI projects, frequently relying on IT partnerships. The majority consider BAI as crucial in helping professional judgements, indicating a growing interest. CONCLUSIONS: The questionnaire received relevant feedback from SIBioC participants. It highlighted the level of expertise and interest in BAI applications. None of the obstacles stands out more than the others, emphasising the need to all-around work: IT infrastructures, data warehouses, BAI analysis software acquisition, data accessibility and training.

A computer model for professional competence assessment according to ISO 15189.

Background As defined by ISO 15189 competence is the "demonstrated ability to apply knowledge and skills" thus, its assessment is fundamental for ensuring the quality of the total testing process in order to reduce the risk for the patient. We have developed a functional software for the measurement of professional competences in order to standardize the procedure and to collect all the data in a single platform, avoiding redundancy and dispersion. Methods Our model objectively assesses the skills, as they become measurable and comparable with appropriate standards and involves both managers and operators, to increase their active engagement. The assessment concerns everyone, but the standards to be met (numerical values) can vary according to the responsibilities. Several subjective and objective criteria are evaluated: each parameter can contribute in a variable proportion to the total skills measured according to the needs of the organization. Results The data are automatically analyzed and can be easily monitored in real time in the form of indicators, thanks to dashboards. The comparison between the skills required and those measured allows highlighting the gap useful for planning personalized training paths. Conclusions Our tool is reliable and highly adaptable to laboratories about competences to track criteria, standards and monitored indicators. The computerized management is a strategic action as it fulfills the requirements of registration, traceability, communication, data analysis and indicators development, which are the tenets of continuous improvement, and allows planning to be made on the basis of the actual training needs.

Defining and Managing the Preanalytical Phase With FMECA: Automation and/or "Human" Control.

OBJECTIVE: Our scope is to provide methodological elements on how to manage effectively the preanalytical phase in the laboratory testing process, by objectively measuring the risk connected to the phases handled by man with respect to those managed by machines. BACKGROUND: Preanalytical errors account for most of the mistakes related to laboratory testing and can affect patient care. Hence, it is necessary to manage the risk connected to the preanalytical phase, as required by certification and accreditation bodies. The risk assessment discloses the steps at greater risk and gives indications to make decisions. METHOD: We have reviewed the state of art in the automation of the preanalytical phase, addressing needs and problems. We have used the proactive risk assessment methodology FMECA (Failure Mode, Effects, and Criticality Analysis) to identify the most critical phases in our preanalytical process and have calculated the risk associated. RESULTS: The most critical phases were the human controlled ones. In particular, the highest risk indexes were associated to manual acceptance of test orders, identification of the patients, tube labeling, and sample collection. CONCLUSION: Automation in the preanalytical phase is fundamental to replace, support, or extend the human contribution. Nevertheless each organization is different about workloads and competencies, so the most suitable management must be tailor-made in each context. APPLICATION: We present a method by which each organization is able to find its best balance between automation and human contribution in the control of the preanalytical phase.

Methodology to Evaluate Clinical Impact of 0/3 Hour High-Sensitivity Cardiac Troponin T Protocol on Managing Acute Coronary Syndrome in Daily Emergency Department Practice.

OBJECTIVE: Sex-/age-differentiated cutoffs and the magnitude of serial changes in high-sensitivity cardiac troponins (hs-cTn) for acute coronary syndrome (ACS) diagnosis algorithms are still under discussion. This study presents a methodology to evaluate decision-making limits and to assess whether sex-specific cutoffs could improve diagnostic accuracy. METHODS: A high-sensitivity cardiac troponin T (hs-cTnT) 0-/3-hour protocol was adopted, applying the 2015 European Society of Cardiology Guidelines. Decision-making limits (99th percentile: 14 ng/L; delta change ≥ 30%) were agreed upon with the emergency department (ED) at the University Hospital of Siena in Siena, Italy. One-year requests (5177) for hs-cTnT serial determination were compared with the final International Classification of Diseases, 9th revision, clinical modifications diagnosis (contingency tables; receiver operating characteristic curves). RESULTS: The algorithm's capability to exclude or confirm ACS was verified by remarkable negative predictive value (97%) and high areas under the curve for the first troponin sampling (0.712), troponin sampling at 3 hours (0.789), and delta (0.744). The clinical utility for the general population-even those with comorbidities-accessing the ED was verified. Our data did not support a sex-differentiated cutoff utility because it would not have affected patient management. CONCLUSION: This methodology allowed us to confirm the effectiveness of our decision-making limits.