Methodological Reflections on Online Data Collection during the Covid-19 Pandemic

The pandemic closed the door for the use of conventional, face-to-face data collection methods. At the same time, it built a momentum for the exploration and utilization of online data collection methods. However, the belief about superiority of the offline data collection persists. The literature review and the authors’ research experience reveal that offline and online data collection methods yield similar result in terms of data completion and quality. All data collection methods contain weaknesses and strengths. Nonetheless, the online data collection methods are very versatile. They allow the researchers to choose the tools that best align with their research objectives.

Joint Matrix Decomposition-Based Missing Data Completion in Low-Voltage Area

In-depth mining and analysis of electricity data in low-voltage area are essential for the further intelligent development of power grids. However, in the actual data collection and measurement of low-voltage area, there will be missing data, and complete electricity data cannot be obtained. To obtain complete power data, this paper proposes a low-voltage station area missing data complement model based on joint matrix decomposition. First, we analyse the characteristics of the low-pressure station data. Then, a model that comprehensively considers the characteristics of the low-voltage station area data is proposed, which includes three parts: the construction of a low-voltage station area data tensor, the joint matrix decomposition, and the completion of the missing data, and it is named LPZ. After that, the CIM learning algorithm proposed in this paper is used to iteratively solve the model to obtain the completed data. Finally, the method proposed in this paper is used to complement the two situations of random loss and all-day loss of real current data in a low-voltage station area and compared with the traditional complement method. The experimental results show that this method is not only effective but also that the completion effect is better than that of other completion methods.

Implementation Outcomes Assessment of a Digital Clinical Support Tool for Intrapartum Care in Rural Kenya: An Observational Analysis (Preprint)

BACKGROUND To support quality of care improvements, iDeliver, a digital clinical support system for maternal and neonatal care, was developed. OBJECTIVE Taking an implementation research lens, we evaluated the adoption and fidelity of iDeliver and assessed the feasibility of its use to provide routine Ministry of Health reports. METHODS We analyzed routinely collected data from the iDeliver implemented at Trans Mara West sub-county Hospital (Kenya), from December 2018 to October 2020. To evaluate its adoption, we assessed the proportion of total facility deliveries over time. To examine the fidelity of iDeliver usage, we studied data completion to assess the plausibility of data entry by care providers during each stage of the labor and delivery workflow and if the usage reflected iDeliver’s envisioned function. We also examined the data completeness of maternal and neonatal indicators prioritized by the Kenyan Ministry of Health. RESULTS 1164 deliveries were registered in iDeliver, capturing 47.3% of the facility’s deliveries over 22 months. Registration improved significantly from 32.3% in the first to 62.2% in the second phase of implementation (P=0.003). Across iDeliver’s workflow, the overall completion rate of all variables improved significantly from 34.1% to 48.0% in the second phase (P<0.001). Data completion was highest for the Discharge-Labor Summary (67.7%) and was lowest for Labor Signs (14.4%). The completion rate of the key Ministry of Health indicators also improved significantly (P<0.001). CONCLUSIONS iDeliver’s adoption and data completeness improved significantly over time. Assessment of iDeliver’ usage fidelity suggested that some features were more easily utilized because providers had time to enter data, versus lower utilization during active childbirth when providers are necessarily engaged with the woman and baby. These insights on the adoption and fidelity of iDeliver usage prompted the team to adapt the application to reflect the users’ culture of use and further improve the implementation of iDeliver. CLINICALTRIAL newborn; neonatal health; maternal health; intrapartum care; labor and delivery; Kenya; digital clinical decision support; health information systems; digital health; implementation research

A Prototype of a Decision Support System for Equine Cardiovascular Diseases Diagnosis and Management

Proper diagnosis and management of equine cardiac diseases require a broad experience and a specialization in the field, but acquisition of specific knowledge is difficult, due, among other reasons, to the limited literature in this field. Therefore, we have designed, developed, and implemented (on a computer algebra system) a Decision Support System (DSS) for equine cardiovascular diseases diagnosis and management based on clinical practise. At this step it is appropriate for equine science teaching, but this work paves the way for a clinical decision support system that facilitated equine clinicians the management of horses with cardiac diseases, allowing improving health care in this species. The latter would require extensive testing prior to its use. The novelty of this work relies on the organization of the equine cardiology workflow in mathematical logic form, that allowed designing, develop and implement a DSS in this new field. An innovation of this work is the part of the DSS devoted to data completion (motivated by the possible lack of specialization of the users—the veterinarians).

Spatial—Temporal Traffic Flow Data Restoration and Prediction Method Based on the Tensor Decomposition

As an important part of urban big data, traffic flow data play a critical role in traffic management and emergency response. Traffic flow data contain multi-mode characteristics, which need to be deeply mined. To make full use of multi-mode characteristics, we use a 3-order tensor to represent the traffic flow data, considering “temporal-spatial-periodic” characteristics. To recover the missing data of traffic flow, we propose the Missing Data Completion Algorithm Based on Residual Value Tensor Decomposition (MDCA-RVTD), which combines linear regression, univariate spline, and CP decomposition. Then, we predict the future traffic flow data by using the proposed Traffic Flow Prediction Algorithm Based on Data Completion Strategy (TFPA-DCS). The experimental results show that recovering the missing data is helpful in improving the prediction accuracy. Additionally, the prediction accuracy of the proposed Algorithm is better than gray model and traditional tensor CP decomposition method.