A fuzzy-based prediction approach for blood delivery using machine learning and genetic algorithm

Multiple diseases require a blood transfusion on daily basis. The process of a blood transfusion is successful when the type and amount of blood is available and when the blood is transported at the right time from the blood bank to the operating room. Blood distribution has a large portion of the cost in hospital logistics. The blood bank can serve various hospitals; however, amount of blood is limited due to donor shortage. The transportation must handle several requirements such as timely delivery, vibration avoidance, temperature maintenance, to keep the blood usable. In this paper, we discuss in first section the issues with blood delivery and constraint. The second section present routing and scheduling system based on artificial intelligence to deliver blood from the blood-banks to hospitals based on single blood bank and multiple blood banks with respect of the vehicle capacity used to deliver the blood and creating the shortest path. The third section consist on solution for predicting the blood needs for each hospital based on transfusion history using machine learning and fuzzy logic. The last section we compare the results of well-known solution with our solution in several cases such as shortage and sudden changes.

Detection of Sepsis in Platelets Using MicroRNAs and Membrane Antigens

The present study proposes to legitimize in sepsis a characteristic found in platelets that suffer storage lesions in blood banks, which is the increased expression of miRNA miR-320a in relation to miR-127. Under physiologically normal conditions, an inverse relationship is observed. The aim of this study was to verify whether the analysis of miR-320a and miR-127 expression in platelets could detect a decrease in their viability and function due to the presence of pathogens in the blood of patients hospitalized in the Intensive Care Unit. We also investigated the expression of membrane antigens sensitive to platelet activation. Of the 200 patients analyzed, only those who developed sepsis (140) were found to have a higher relative quantity of miR-320a than that of miR-127. This characteristic and the increased expression of membrane antigens P2Y12, CD62P, CD41, and CD61 showed a significant association (p < 0.01) with all types of sepsis evaluated in this study. Additionally, 40% of patients hospitalized for sepsis had negative results for the first cultures. We conclude that analysis of miR-127 and miR-320a expression combined with membrane antigens evaluation, in association with the available clinical and diagnostic parameters, are important tools to detect the onset of sepsis.

Gamified Blood Donors System Based on Intelligent Agents

The population of the country of Kenya is drastically increasing thus causing the number of possible blood donors to rise. Despite this, the blood collected and stored in most blood banks is not enough to cater for the huge demand. The demand has been due to increase of number of accidents experienced in the country and the advancement in medical procedures which calls for organ transplant and blood transfusion. Even though systems have been developed which can connect the donors and recipients and location tracking, most people are dying because they don`t get this vital commodity in good time. The process of donating blood has not been enticing. There is nothing that prompts a person to donate blood. This call for developing a gamified blood donor management system based on intelligent agents so as to increase the number of donors and keep the system performance at optimal level. The project adopts Goal-Oriented Methodology in the system development process. Two agents are developed: donors’ agent and the blood admin agent. The intelligent agents help in profiles personalization thus improving the system performance. Gamification technique is implemented in the system so as to increase the traffic of blood donors interacting with the system and participating in the donation exercise. This increase the number of blood donors hence enough blood is collected to cater for the huge demand.

Design of Data Mining Techniques for Online Blood Bank Management by CNN Model

A blood bank is the organisation responsible for storing blood to transfuse it to the patients in need. The primary goal of a blood bank is to be reliable and ensure that patients get the relevant non-toxic blood to avoid transfusion-related complications since blood is a critical medicinal resource. It is difficult for the blood banks to offer high levels of precision, dependability, and automation in the blood storage and transfusion process if blood bank administration includes many human processes. This research framework is proposing to maintain blood bank records using CNN model classification method. In the pre-processing of CNN method, the datasets are tokenized and set the donor’s eligibility. It will make it easier for regular blood donors to donate regularly to charitable people and organizations. A few machine learning techniques offer the automated website updation. Jupyter note book has been used to analyze the dataset of blood donors using decision trees, neural networks, and von Bays techniques. The proposed method operates online through a website. Moreover, the donor's eligibility status with gender, body mass index, blood pressure level, and frequency of blood donations is also maintained. Finally, the comparison of different machine learning algorithms with the suggested framework is tabulated.

Seroprevalence of Dengue and Chikungunya antibodies among blood donors in Dar es Salaam and Zanzibar, Tanzania: a cross-sectional study

Background The potential shift of major causes of febrile illnesses from malaria to non-malarial febrile illnesses, including arboviral diseases such as chikungunya and dengue, is of concern. The last outbreaks of these infections were reported in 2018 and 2019 for chikungunya in Zanzibar and dengue in Dar es Salaam. We conducted a cross-sectional study that involved serological testing of stored blood samples from the blood banks in Temeke Referral Hospital in Dar es Salaam and the National Blood Bank Unit in Zanzibar. The samples were collected from Zanzibar and Dar es Salaam donors in May and June 2020, respectively. A total of 281 samples were included in the study, and their demographic information extracted from the registers. The samples were then transported to Muhimbili University of Health and Allied Sciences at the Microbiology Laboratory. They were subjected to an indirect ELISA to detect IgG and IgM against dengue and chikungunya viruses. Results Seropositive IgM samples from Dar es Salaam were 3/101 (2.97%) for chikungunya and 1/101 (0.9%) for dengue, while samples from Zanzibar were all IgM negative for both viruses. Chikungunya IgG seropositivity was significantly higher (p ≤ 0.05) in Dar es Salaam 21/101 (21.2%) than Zanzibar 22/180 (12.2%). There was no difference in dengue IgG seropositivity between Dar es Salaam 44/101 (43.5%) and Zanzibar 68/180 (37.8%). Similarly, dual IgG seropositivity for both dengue and chikungunya viruses were not different between Dar es Salaam 13/101 (12.9%) and Zanzibar 11/180 (6.1%). Conclusion Detection of IgM for dengue and chikungunya in Dar es Salaam indicates recent or ongoing transmission of the two viruses in the absence of a reported outbreak. These findings suggest the possibility of transmission of the two infections through blood transfusion. Detection of IgG antibodies for dengue and chikungunya viruses might be contributed by both; the ongoing infections and residual responses caused by preceding infections in the country. Results from blood banks may represent the tip of the iceberg. Further studies are needed to gain insight into the actual burden of the two diseases in Tanzania.

Blood Bank Management System to Establish Link between Donors and Blood Banks

Blood donation is a vital component of international healthcare and has suffered because of the pandemic. This paper aims to address this issue by proposing the creation of a totally transparent blood bank management system in which hospitals/NGOs input the quantity of each blood type in their stock, after which nearby users who are ready to donate are notified. Following extensive research, we observed that there is no structure in place that provides a communication link between the management of blood banks (Hospitals and NGOs) and the general public, allowing available donors to view which blood banks have a shortage of their blood group. The technology platform in implementing this system uses Python programming environment Django for SQL and deployment. For frontend development, HTML5, CSS3, JavaScript, and Bootstrap were utilized. The system alleviates the issues created by blood shortages in blood banks by properly managing and providing a single platform for everyone. It makes information about available stock in each blood bank available to the public and this can be extended to multiple cities. Keywords: Blood donation, Blood stock, Hospital, Donor, System

The Use of Screening Algorithm to Defer Blood Donors with Subclinical Malaria

Plasmodium falciparum infection in blood donors is common in malaria endemic countries, including Ghana. To date, there are no established exclusion criteria to defer a donor carrying malaria parasites. Therefore, based on significant independent variables identified in this study, donor malaria screening algorithm was developed to be used by blood banks to screen blood donors for subclinical malaria. Each significant variable was weighted one (1) point and its alternative response was weighted negative one (−1) point. Accumulation of the points determines the risk level of the donor. These weighted points were used to categorize infected donors as having negligible (<2 points), tolerable (3-4 points), undesirable (5–8 points), or intolerable (>9 points) risk. Based on accumulated weight of ≥5 points, the algorithm was 94.7% (54/57) sensitive but 82% (298/364) specific. With this level of specificity, 18% of the blood donors without malaria would have been deferred. Therefore, it is imperative that all donors with accumulated risk ≥5 be screened for malaria using either malaria rapid test kit or microscopy.

Determination of carboxyhaemoglobin and methaemoglobin levels in donated blood

To determine the percentages of carboxyhaemoglobin (COHb) and methaemoglobin (MeHb) in donor blood and to compare these levels between smokers and nonsmokers at different time points during blood storage. Blood donors were recruited from Haematology Service, University Hospital Alzira Velano, Alfenas-MG. The blood was kept in collecting ducts (noodles) containing citrate, phosphate and dextrose (CPD) and stored at 4°C throughout the storage period. Since the noodles kept the characteristics of the bags, COHb and MeHb levels were analysed on the day of donation and after 20 days of storage. Levels of COHb and MeHb were determined using spectrophotometric methods. Non-parametric Friedman and Mann-Whitney tests were employed to compare COHb and MeHb levels before and after the storage and groups of smokers and nonsmokers, respectively. Levels of COHb and MeHb in the blood collected from smokers and nonsmokers were statistically different (p< 0.05; Mann- Whitney test) when the samples were analyzed before the storage. In blood of smokers, COHb levels were no different over a 20-day storage period (p= 0.7009; Friedman test). On the other hand, MeHb levels were significant different over a 20-day storage period (p< 0.05). The results suggest the need to regularly assess COHb and MeHb levels in donor blood stored in blood banks.