Background: Living in the current digital era requires widespread adoption of information technology in the modern health care industry. Objective: The current research aimed to study key attributes and behaviours related to successful leaders'need to achieve the vision and ensure successful health IT adoption. Methods: A Delphi technique with three rounds was employed and guided by structured questions. Part of the study was conducted online due to COVID-19 guidelines on distancing norms and lockdown in some areas. The answers of the participants were evaluated on a five-point Likert scale. Results: The findings showed that similar leadership qualities are required in the healthcare sector as well as other sectors. For digital innovations in the rapidly changing healthcare space, leaders need to play a more proactive role, be visionary and dynamic, and should lead by example to take the organization to the next level. Conclusions: Leaders need to come out of their comfort zone, understand the fast-evolving scenario where the outstanding leadership qualities are essential to prove their mettle, outshine others, and create a strong foundation for the adoption of modern efficient customized digital technology in the fast-growing healthcare sector.

Machine Learning and its application in healthcare has got substantial attention in the recent past. It is because when enhanced computational ability is combined with management and use of high volume of data which is produced at a high velocity, it presents an opportunity for using machine learning algorithms for improving health outcomes. Supervised learning is a type of machine learning that is used to predict labelled data using alogrithms like linear or logistic regression, support vector machine, decision tree, LASSO regression, k nearest neighbour and naïve bayes classifier. Unsupervised machine learning models can be used to identify patterns in the data that does not have any information on the outcome. Such models can be used for fraud or anomaly detection. Examples of clinical applications of machine learning include but is not limited to formulation of different clinical decision support systems to help health professionals in managing patients in a better way. In public health, one important use of machine learning is to identify and predict population which is at high risk of developing specific adverse health outcomes and design public health interventions targeting that specific population. It is important that different concepts related to machine learning are integrated in the medical curriculum so that health professionals can effectively lead and interpret research in this area. Concept of algorithmic fairness is needed to be kept in mind to ensure compliance with ethical standards while generalizing findings from machine learning algorithms.

Background: Health Informatics is an indispensable science in light of the massive reform healthcare has undertaken recently. Method: This descriptive multiphase study used a questionnaire to assess the need and applied a competency-based postgraduate curriculum to collect the required competencies as well as their proficiency levels. Results: Eighty percent of the respondents agreed that the current training should be advanced. 73.7% of the respondents agreed that this certificate would improve the level of knowledge, and it would impact on the delivery of healthcare positively (78.9%). For the required competencies, 10 competencies scored 1.75 and above, 22 scored between 1.5 and 1.75 and 22 scored below 1.50. The expert panel came to an agreement that the competencies with 1.5 and above should be included. Discussion: The findings emphasize the need to establish PG diploma in comply with previous studies that unveiled the need to provide education and training in Health Informatics. Only the required competencies were included as the program is one-year long. The selected competencies were validated and presented by the panel. Conclusion: A PG diploma in Health Informatics is a key element in the evolution of healthcare services, therefore, a competency-based framework was provided and validated by experts.

Path planning is an NP-hard problem that is aimed to satisfy multi-constraint optimization requirements. In autonomous robotics applications, path planning together with collision avoidance presents a challenging task. It necessitates the generation of possible search directions from a designated point to a fixed varying destination location satisfying spatial constraints. This paper presents a framework for the design of an intelligent multi-objective robotic path planning algorithm. The algorithm relies on the generation of way-points by hybridizing two meta-heuristics techniques, namely Grey Wolf Algorithm (GWO) and Particle Swarm Optimization (PSO). A frequency-based modification in GWO search operators is introduced to fasten the search process. An improvised search strategy is employed for collision detection and avoidance, which converts non-desired points into the desired point. Sensors are deployed around the robot vicinity for search optimization. Mutation operators are then introduced to improve path length by smoothing out the trajectory. The proposed algorithm\'s effectivity is then validated through extensive simulations, in which different condition environments are simulated. To validate the effectiveness of the proposed methodology, the results are compared with contemporary algorithms namely Minimum Angle Artificial Bee Colony (MAABC) algorithms, Hybrid Cuckoo Search-Bat Algorithm (BA-CSA), Bacterial Bolony (BC) and Genetic Algorithm (GA) algorithms. The results conclusively demonstrated that the proposed algorithm ensures effective performance in path smoothness and safety under a wide range of conditions.

The texture is a high-flying feature in an image and has been extracted to represent the image for image retrieval applications. Many texture features are being offered for image retrieval. This paper proposes a local binary pattern based texture feature called Weber Global Statistics Tri-Directional Pattern (WGSTriDP) to retrieve the images. This pattern combines the advantage of differential excitation components in Weber Local Binary Pattern (WLBP), sign and magnitude components in Local Tri-Directional Pattern (LTriDP), and global statistics. WGSTriDP has two components: Differential Excitation (DE) and Global Statistics TriDirectional Pattern (GSTriDP). The WGSTriDP gains the benefit of discrimination concerning human perception from differential excitation as well as incorporates the global statistics into sign and magnitude components in the pattern derived from the local neighborhoods. The effectiveness of the pattern in image retrieval is experimented with in two benchmark databases such as ORL (face database) and, UIUC (texture database). The performance of WGSTriDP is compared with existing algorithms and the experimental results show that WGSTriDP outstrips the other local patterns to retrieve similar images from the database.

Information systems with complex domain logic could tremendously benefit from incorporating Semantic Web technologies and principles, be it globally relevant identifiers, Linked Data, or expressive reasoning to name just a few. While some of the Semantic Web principles may be applied on top of regular information systems backed by relational databases, others are better suited for becoming an integral part of the system itself. In this paper, we analyze the main reasons why the Semantic Web has been used so sparsely in such applications. We also discuss architectural and design implications of the choice to build a domain-specific information system based on Semantic Web technologies. This discussion is complemented by a case study comparing the development of a safety data collecting and processing system using both Semantic Web and more traditional technologies.

Missing values (MV), unobserved values in the dataset, are a difficulty often faced by researchers in real-world situations. Data imputation techniques allow the estimation of MV using different algorithms, by means of which an important data can be imputed for a particular instance. Most of the articles published in this field deal with different imputation methods, however, few studies deal with the comparative evaluation of the different methods to provide more appropriate guidelines for the selection of the method to be applied to impute data for specific situations. The objective of this work is to show a methodology for evaluating the performance of imputation methods by means of new metrics derived from data mining processes, using quality metrics of data mining models. We started from the complete dataset that was amputated with different amputation mechanisms to generate 63 datasets with MV; these were imputed using Median, k-NN, k-Means and Hot-Deck imputation methods. The performance of the imputation methods was evaluated using new metrics derived from quality metrics of the data mining processes performed with the original full file and with the imputed files. This evaluation is not based on measuring the error made when imputing (usual operation), but on considering the similarity of the values of the quality metrics of the data mining processes obtained with the original file and with the imputed files. The results show that, globally considered and according to the new metrics proposed, the imputation methods that showed the best performance were k-NN and k-Means. An additional advantage of the proposed methodology is that it provides predictive data mining models that can be used a posteriori.