مجله انفورماتیک سلامت و زیست پزشکی
سال یازدهم شماره 2 (پیاپی 40، تابستان 1403)

In recent decades, the medical field has faced many challenges in managing and maintaining information security on waiting lists for organ transplantation patients. The lack of trust of the participants in this process, which requires more efforts to ensure the security and privacy of patients and donors, highlights the necessity for finding new security solutions.

In this study, a safe and reliable method was presented and implemented using blockchain technology based on the Network Distributed File System (IPFS) to improve waiting list management and solve the challenge of maintaining voluminous medical documents. In this method, patient information is anonymized using appropriate algorithms, and then, stored and linked to the blockchain network.

The implemented system provides an integrated and innovative method in organ transplantation management, which not only comprehensively provides the security and privacy of patients, but also reduces social inequalities and increases trust in the organ donation process, as well as fair management of patient waiting lists.

The proposed system has provided a scalable and efficient system using microservices architecture and can be provided as a reliable tool for medical stakeholders.

Larynx cancer can be benign or malignant based on various factors. This research aimed to provide a machine learning-based model to improve the diagnosis of individuals with larynx cancer.

In the first step, the voices of the people who visited the medical centers (including the sounds (A), (E), and (O)) were recorded and considered as a data set. In the second step, the data were classified into three classes (benign cancer, malignant cancer, and healthy) by a specialist. In the third step, the data cleaning was done. In the fourth step, the features related to sound were extracted from the data. In the fifth step, five machine learning models including SVM, Decision Tree, Naïve Bayes, MLP, and Random Forest were implemented on the data set. Finally, the performance of the models was evaluated using evaluation criteria such as accuracy, F-score, and other evaluation criteria.

The results of the implementation showed that the SVM model had a higher accuracy than other models for the sound (A) and sound (O) with an accuracy of 0.818, and the sound (E) with an accuracy of 0.818 in the model MLP had the highest accuracy.

The present study evaluated machine learning models for the diagnosis of laryngeal cancer based on audio data. The results showed that the use of the SVM model for the diagnosis of laryngeal cancer can help diagnose this disease more accurately and provide reliable results.

Glioblastoma is one of the common brain cancers that has a high mortality rate. In this study, the genes present in the metabolic pathways of glioblastoma stem cells were examined and nominated using bioinformatics analysis.

In this study, an appropriate dataset was selected for analysis by referring to GEO database. This dataset included gene expression profiles in stem cells isolated from glioblastoma patients. Gene clusters with high and low expression were categorized. Rich databases such as Enrichr, STRING, and GEPIA were used for more accurate data evaluation. Finally, candidate genes were isolated.

1250 genes were highly expressed in cholesterol biosynthesis, inositol triphosphate metabolism, geranyl diphosphate metabolism, zymosterol biosynthesis, and phosphatidylinositol metabolism, and 1030 genes were low in chondroitin sulfate, dermatan sulfate, N acetyl glucosamine, and glycolysis pathways. After evaluating the relationship between protein networks, genes with high and low expression were selected. All these genes were observed in the survival curve, in about 20 months. The survival rate of patients was less than 10%.

The results of this study showed that the DHCR7 gene had a significant increase in expression. However, the ENO2 gene had a significant decrease in expression. The rest of the genes had a relative increase and decrease in expression.

Hemodialysis is one of the most common methods of treating patients with chronic kidney failure. People undergoing hemodialysis face various self-management challenges such as physical, emotional, and psychological problems. Mobile phone applications are useful tools for the self-management process of chronic patients. The purpose of this study was to identify and introduce the requirements needed in designing a mobile phone-based self-management application for hemodialysis patients.

This descriptive cross-sectional study was conducted in 2024. The data collection tool was a researcher-made electronic questionnaire that included information-educational needs and application capabilities. A needs assessment was conducted on 33 people (11 doctors and 22 patients) in Afzalipour Hospital in Kerman. Data analysis was done using SPSS version 27 and descriptive statistics.

A total of 89 information-educational needs and application capabilities were identified for hemodialysis patients. The data elements identified for application capabilities were divided into 10 groups: patient profile, clinical data, medication administration, nutrition and dietary management, psychological and psychiatric challenges management, sleep management, pain management, communication, and exercise. According to the views of doctors and patients, all information-educational needs (26 data elements) and application capabilities (63 data elements) except surname, national code, and contact number, with an average greater than and equal to 2.50 (50 percent) were considered essential for designing an application program.

The identified information-educational needs and the application capabilities in this study, can assist designers in creating efficient and user-friendly self-management applications for hemodialysis.

The discovery of hidden patterns in pharmaceutical data can contribute to improving the performance of hospital pharmacies. One of the applications of advanced data analysis techniques is the identification of drug interactions.

This study was conducted using data mining techniques with the FP-growth algorithm in the RapidMiner Studio® 10.1 environment to extract association rules and frequent pharmaceutical patterns. Data preprocessing and modeling were performed based on the CRISP-DM model. The type and level of drug interactions were determined based on the algorithm's results and by referencing the database at www.drugs.com.

The results included 17 association rules and 126 prescribing patterns, ranging from single-drug to four-drug combinations. Of the 64 two-drug prescribing patterns, 56 had no interaction, 6 had moderate interactions, 1 had a minor interaction, and 1 had a major interaction. Additionally, of the 19 three-drug patterns, 18 had no interaction, and only 1 had a moderate interaction. No interactions were observed in the four-drug prescribing pattern.

The findings of this study can assist stakeholders in improving the pharmaceutical supply chain, optimizing prescriptions, reducing drug interactions, and lowering costs. The discovered patterns may also be used as part of a clinical decision support system. Although no significant drug interactions were observed in this study, the discovery of even one major interaction highlights its importance and further underscores the practical role of computer applications in medicine.