RESUMO
Nano-based drug delivery systems (DDSs) have demonstrated the ability to address challenges posed by therapeutic agents, enhancing drug efficiency and reducing side effects. Various nanoparticles (NPs) are utilised as DDSs with unique characteristics, leading to diverse applications across different diseases. However, the complexity, cost and time-consuming nature of laboratory processes, the large volume of data, and the challenges in data analysis have prompted the integration of artificial intelligence (AI) tools. AI has been employed in designing, characterising and manufacturing drug delivery nanosystems, as well as in predicting treatment efficiency. AI's potential to personalise drug delivery based on individual patient factors, optimise formulation design and predict drug properties has been highlighted. By leveraging AI and large datasets, developing safe and effective DDSs can be accelerated, ultimately improving patient outcomes and advancing pharmaceutical sciences. This review article investigates the role of AI in the development of nano-DDSs, with a focus on their therapeutic applications. The use of AI in DDSs has the potential to revolutionise treatment optimisation and improve patient care.
RESUMO
RATIONALE AND OBJECTIVES: The process of generating radiology reports is often time-consuming and labor-intensive, prone to incompleteness, heterogeneity, and errors. By employing natural language processing (NLP)-based techniques, this study explores the potential for enhancing the efficiency of radiology report generation through the remarkable capabilities of ChatGPT (Generative Pre-training Transformer), a prominent large language model (LLM). MATERIALS AND METHODS: Using a sample of 1000 records from the Medical Information Mart for Intensive Care (MIMIC) Chest X-ray Database, this investigation employed Claude.ai to extract initial radiological report keywords. ChatGPT then generated radiology reports using a consistent 3-step prompt template outline. Various lexical and sentence similarity techniques were employed to evaluate the correspondence between the AI assistant-generated reports and reference reports authored by medical professionals. RESULTS: Results showed varying performance among NLP models, with Bart (Bidirectional and Auto-Regressive Transformers) and XLM (Cross-lingual Language Model) displaying high proficiency (mean similarity scores up to 99.3%), closely mirroring physician reports. Conversely, DeBERTa (Decoding-enhanced BERT with disentangled attention) and sequence-matching models scored lower, indicating less alignment with medical language. In the Impression section, the Word-Embedding model excelled with a mean similarity of 84.4%, while others like the Jaccard index showed lower performance. CONCLUSION: Overall, the study highlights significant variations across NLP models in their ability to generate radiology reports consistent with medical professionals' language. Pairwise comparisons and Kruskal-Wallis tests confirmed these differences, emphasizing the need for careful selection and evaluation of NLP models in radiology report generation. This research underscores the potential of ChatGPT to streamline and improve the radiology reporting process, with implications for enhancing efficiency and accuracy in clinical practice.
RESUMO
Purpose: Ovarian cancer is a common type of cancer and a leading cause of death in women. Therefore, accurate and fast prediction of ovarian tumors is crucial. One of the appropriate and precise methods for predicting and diagnosing this cancer is to build a model based on artificial intelligence methods. These methods provide a tool for predicting ovarian cancer according to the characteristics and conditions of each person. Method: In this study, a data set included records related to 171 cases of benign ovarian tumors, and 178 records related to cases of ovarian cancer were analyzed. The data set contains the records of blood test results and tumor markers of the patients. After data preprocessing, including removing outliers and replacing missing values, the weight of the effective factors was determined using information gain indices and the Gini index. In the next step, predictive models were created using random forest (RF), support vector machine (SVM), decision trees (DT), and artificial neural network (ANN) models. The performance of these models was evaluated using the 10-fold cross-validation method using the indicators of specificity, sensitivity, accuracy, and the area under the receiver operating characteristic curve. Finally, by comparing the performance of the models, the best predictive model of ovarian cancer was selected. Results: The most important predictive factors were HE4, CA125, and NEU. The RF model was identified as the best predictive model, with an accuracy of more than 86%. The predictive accuracy of DT, SVM, and ANN models was estimated as 82.91%, 85.25%, and 79.35%, respectively. Various artificial intelligence (AI) tools can be used with high accuracy and sensitivity in predicting ovarian cancer. Conclusion: Therefore, the use of these tools can help specialists and patients with early, easier, and less expensive diagnosis of ovarian cancer. Future studies can leverage AI to integrate image data with serum biomarkers, thereby facilitating the creation of novel models and advancing the diagnosis and treatment of ovarian cancer.
RESUMO
Background and Aims: Hypospadias, a congenital anomaly, can have long-term effects on sexual, urinary, and reproductive functions, making proper postoperative care essential for desirable outcomes, which could be facilitated through a mobile application for diseases with long-term complications. The aim of this study was to investigate the data and functional requirements or minimum data set of a postoperative education mobile application for caregivers of children with hypospadias. Methods: A literature review of papers published until April 2023 using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement was conducted to determine the data and functional requirements of a mobile application that provides postoperative education to caregivers of children with congenital hypospadias. Based on the results, a questionnaire was prepared, and its content validity and reliability were evaluated by CVI and CVR. Additionally, data was examined by 30 residents, specialists, and subspecialists in pediatric surgery using the Delphi approach. Results: The study identified 28 data elements in three main categories: demographic data, clinical data, and application function. Functional requirements of the mobile application were suggested for use in designing the application. Also, the most critical data elements included the definition of disease, the importance of treatment, surgical preparation, bandage, hygiene, symptoms and infection, bleeding, and emergency condition. Conclusion: The study will pave the way for developing postoperative educational applications for caregivers of children with congenital hypospadias. M-Health app developers and clinician specialists can utilize these findings to design practical applications that assist caregivers in managing the care of hypospadias patients.
RESUMO
BACKGROUND AND OBJECTIVE: Pharmacokinetic studies encompass the examination of the absorption, distribution, metabolism, and excretion of bioactive compounds. The pharmacokinetics of drugs exert a substantial influence on their efficacy and safety. Consequently, the investigation of pharmacokinetics holds great importance. However, laboratory-based assessment necessitates the use of numerous animals, various materials, and significant time. To mitigate these challenges, alternative methods such as artificial intelligence have emerged as a promising approach. This systematic review aims to review existing studies, focusing on the application of artificial intelligence tools in predicting the pharmacokinetics of drugs. METHODS: A pre-prepared search strategy based on related keywords was used to search different databases (PubMed, Scopus, Web of Science). The process involved combining articles, eliminating duplicates, and screening articles based on their titles, abstracts, and full text. Articles were selected based on inclusion and exclusion criteria. Then, the quality of the included articles was assessed using an appraisal tool. RESULTS: Ultimately, 23 relevant articles were included in this study. The clearance parameter received the highest level of investigation, followed by the area under the concentration-time curve (AUC) parameter, in pharmacokinetic studies. Among the various models employed in the articles, Random Forest and eXtreme Gradient Boosting (XGBoost) emerged as the most commonly utilized ones. Generalized Linear Models and Elastic Nets (GLMnet) and Random Forest models showed the most performance in predicting clearance. CONCLUSION: Overall, artificial intelligence tools offer a robust, rapid, and precise means of predicting various pharmacokinetic parameters based on a dataset containing information of patients or drugs.
Assuntos
Inteligência Artificial , Farmacocinética , Humanos , Preparações Farmacêuticas/metabolismo , Animais , Modelos Biológicos , Área Sob a CurvaRESUMO
Nanoparticle toxicity analysis is critical for evaluating the safety of nanomaterials due to their potential harm to the biological system. However, traditional experimental methods for evaluating nanoparticle toxicity are expensive and time-consuming. As an alternative approach, machine learning offers a solution for predicting cellular responses to nanoparticles. This study focuses on developing ML models for nanoparticle toxicity prediction. The training dataset used for building these models includes the physicochemical properties of nanoparticles, exposure conditions, and cellular responses of different cell lines. The impact of each parameter on cell death was assessed using the Gini index. Five classifiers, namely Decision Tree, Random Forest, Support Vector Machine, Naïve Bayes, and Artificial Neural Network, were employed to predict toxicity. The models' performance was compared based on accuracy, sensitivity, specificity, area under the curve, F measure, K-fold validation, and classification error. The Gini index indicated that cell line, exposure dose, and tissue are the most influential factors in cell death. Among the models tested, Random Forest exhibited the highest performance in the given dataset. Other models demonstrated lower performance compared to Random Forest. Researchers can utilize the Random Forest model to predict nanoparticle toxicity, resulting in cost and time savings for toxicity analysis.
Assuntos
Nanopartículas , Redes Neurais de Computação , Teorema de Bayes , Aprendizado de Máquina , Nanopartículas/toxicidade , Árvores de Decisões , Máquina de Vetores de SuporteRESUMO
BACKGROUND: Breast Cancer (BC) is a formidable global health challenge, and Iran is no exception, with BC accounting for a significant proportion of women's malignancies. To gain deeper insights into the epidemiological characteristics of BC in Iran, this study employs advanced geospatial techniques and feature selection methods to identify significant risk factors and spatial patterns associated with BC incidence. METHODS: Using rigorous statistical methods, geospatial data from Iran, including cancer-related, sociodemographic, healthcare infrastructure, environmental, and air quality data at the provincial level, were meticulously analyzed. Age-standardized incidence rates (ASR) are calculated, and different regression models are used to identify significant variables associated with BC incidence. Spatial analysis techniques, including global and local Moran's index, geographically weighted regression, and Emerging hotspot analysis, were utilized to examine geospatial patterns, identify clustering and hotspots, and assess spatiotemporal distribution of BC incidence. RESULTS: The findings reveal that BC predominantly affects women (98.03%), with higher incidence rates among those aged 50 to 79. Isfahan (ASR = 26.1) and Yazd (ASR = 25.7) exhibit the highest rates. Significant predictors of BC incidence, such as marriage, tertiary education attainment rate, physician-to-population ratio, and PM2.5 air pollution, are identified through regression models. CONCLUSION: The study's results provide valuable information for the development of evidence-based prevention strategies to reduce the burden of BC in Iran. The findings underscore the importance of early detection, health education campaigns, and targeted interventions in high-risk clusters and adjacent regions. The geospatial insights generated by this study have implications for policy-makers, researchers, and public health practitioners, facilitating the formulation of effective BC prevention strategies tailored to the unique epidemiological patterns in Iran.
Assuntos
Neoplasias da Mama , Humanos , Feminino , Neoplasias da Mama/epidemiologia , Neoplasias da Mama/prevenção & controle , Irã (Geográfico)/epidemiologia , Fatores de Risco , Análise Espacial , IncidênciaRESUMO
Background and Aims: Data mining methods are effective and well-known tools for developing predictive models and extracting useful information from various data of patients. The present study aimed to predict the severity of patients with COVID-19 by applying the rule mining method using characteristics of medical images. Methods: This retrospective study has analyzed the radiological data from 104 COVID-19 hospitalized patients diagnosed with COVID-19 in a hospital in Iran. A data set containing 75 binary features was generated. Apriori method is utilized for association rule mining on this data set. Only rules with confidence equal to one were generated. The performance of rules is calculated by support, coverage, and lift indexes. Results: Ten rules were extracted with only X-ray-related features on cases referred to ICU. The Support and Coverage index of all of these rules was 0.087, and the Lift index of them was 1.58. Thirteen rules were extracted from only CT scan-related features on cases referred to ICU. The CXR_Pleural effusion feature has appeared in all the rules. The CXR_Left upper zone feature appears in 9 rules out of 10. The Support and Coverage index of all rules was 0.15, and the Lift index of all rules was 1.63. the CT_Adjacent pleura thickening feature has appeared in all rules, and the CT_Right middle lobe appeared in 9 rules out of 13. Conclusion: This study could reveal the application and efficacy of CXR and CT scan imaging modalities in predicting ICU admission to a major COVID-19 infection via data mining methods. The findings of this study could help data scientists, radiologists, and clinicians in the future development and implementation of these methods in similar conditions and timely and appropriately save patients from adverse disease outcomes.
RESUMO
Background: The Glu-Urea-Lys (EUK) pharmacophore as prostate-specific membrane antigen (PSMA)-targeted ligand was synthesized, radiolabeled with 99mTc-tricarbonyl-imidazole-BPS chelation system, and biological activities were evaluated. The strategy [2 + 1] ligand is applied for tricarbonyl labeling. (5-imidazole-1-yl)pentanoic acid as a monodentate ligand and bathophenanthroline disulfonate (BPS) as a bidentate ligand formed a chelate system with 99mTc-tricarbonyl. EUK-pentanoic acid-imidazole and EUK were evaluated for PSMA active site using AutoDock 4 software. Materials and Methods: EUK-pentanoic acid-imidazole was synthesized in two steps. BPS was radiolabeled with 99mTc-tricarbonyl at 100°C for 30 min. The purified 99mTc(CO)3(H2O)BPS was used to radiolabel EUK-pentanoic acid-imidazole at 100°C, 30 min. Radiochemical purity, Log P, and stability studies were carried out within 24 h. Affinity of 99mTc(CO)3BPS-imidazole-EUK was performed in the saturation binding studies using LNCaP cells at 37°C for 1 h with a range of 0.001-1000 nM radiolabeled compound range. Internalization studies were performed in LNCaP cells with 1000 nM radiolabeled compound incubated for (0-2) h at 37°C. Biodistribution was studied in normal male Balb/c mice. The artificial intelligence predicts the uptake of radiolabeled compound in tumor. Results: The structures of synthesized compounds were confirmed by mass spectroscopy. Radiochemical purity, Log P, and protein binding were ≥95%, -0.2%, and 23%, respectively. The radiolabeled compound was stable in saline and human plasma within 24 h with radiochemical purity ≥90%. There was no release of 99mTc within 4 h in competition with histidine. The affinity was 82 ± 26.38 nM, and the activity increased inside the cells over time. Biodistribution studies showed radioactivity accumulation in kidneys less than 99mTc-HYNIC-PSMA. There was a moderate accumulation of radioactivity in the liver and intestine. Conclusion: Based on the results, 99mTc(CO)3BPS-imidazole-EUK can potentially be used as an imaging agent for studies at prostate bed and distal areas. The chelate system can be potentially labeled with rhenium for imaging studies (fluorescent or scintigraphy) and therapy.
Assuntos
Antígenos de Superfície , Glutamato Carboxipeptidase II , Animais , Humanos , Masculino , Camundongos , Inteligência Artificial , Quelantes/química , Imidazóis , Ligantes , Próstata , Compostos Radiofarmacêuticos , Tecnécio/química , Distribuição Tecidual , Ureia/química , Ureia/farmacologia , Glutamato Carboxipeptidase II/antagonistas & inibidoresRESUMO
Fingerprints or dermatoglyphics contain patterns that were formed by parallel ridges on the bare skin of fingertips. This property on the skin, especially on the finger, makes it possible to hold objects with our fingers, and this feature can also be used to determine identity. After cardiovascular diseases, cancer is the second cause of death worldwide. In this paper, we reviewed the associations reported between fingerprint patterns (dermatoglyphics) and cancer types. In this review, we focused on six types of cancer, including gynecological cancers, oral cancer, prostate cancer, gastric cancer, leukemia, and pituitary tumors, and their connection with fingerprints. The dermatoglyphic could be a potentially useful tool for early diagnosis of predisposition in developing some diseases. As some patterns inform us about leading to deadly diseases, such as cancer, which could be prevented, or at least by early diagnosis and taking proper care, the mortality rate could decline. Thus, the fingerprints that have been primarily observed in particular cancers require more research.
RESUMO
Nanoparticles have been used extensively in different scientific fields. Due to the possible destructive effects of nanoparticles on the environment or the biological systems, their toxicity evaluation is a crucial phase for studying nanomaterial safety. In the meantime, experimental approaches for toxicity assessment of various nanoparticles are expensive and time-consuming. Thus, an alternative technique, such as artificial intelligence (AI), could be valuable for predicting nanoparticle toxicity. Therefore, in this review, the AI tools were investigated for the toxicity assessment of nanomaterials. To this end, a systematic search was performed on PubMed, Web of Science, and Scopus databases. Articles were included or excluded based on pre-defined inclusion and exclusion criteria, and duplicate studies were excluded. Finally, twenty-six studies were included. The majority of the studies were conducted on metal oxide and metallic nanoparticles. In addition, Random Forest (RF) and Support Vector Machine (SVM) had the most frequency in the included studies. Most of the models demonstrated acceptable performance. Overall, AI could provide a robust, fast, and low-cost tool for the evaluation of nanoparticle toxicity.
Assuntos
Nanopartículas Metálicas , Nanoestruturas , Inteligência Artificial , Nanopartículas Metálicas/toxicidade , Bases de Dados Factuais , ÓxidosRESUMO
Background and Aims: Overweight and obesity lead to the development of physical diseases. Cognitive factors play a vital role in controlling one's weight. Currently, cognitive-behavioral therapy (CBT) interventions are recognized as a subcategory of lifestyle modification programs that can be implemented to control weight and modify eating patterns as well as physical activity. Nowadays, smartphone-based applications are utilized to implement behavioral interventions. The main purpose of this study is to evaluate the quality of CBT-based smartphone applications available on Google Play and the App Store in the field of overweight control. Methods: Smartphone-based utility applications available on Google Play and App Store were identified in March 2021. Weight control smartphone applications were obtained based on inclusion and exclusion criteria. The app name, platform, version, number of downloads, password protection, affiliations, and features of retrieved apps were tabulated. The Mobile Application Rating Scale was utilized to evaluate the quality of the identified apps. Results: Seventeen CBT-based weight control smartphone apps were retrieved. The average engagement, functionality, aesthetics, and information quality scores were 3.65, 3.92, 3.80, and 3.91, respectively. Also, the average score in an aspect containing the usefulness of the app, frequency of using the application, cost, and user satisfaction was 3.5. Conclusion: Future applications related to this field can be improved by providing a personalization program according to the needs of users and the possibility of online chatting with the therapist. Further improvements can be achieved by improving the areas of engagement, aesthetics, and subjective quality as well as having appropriate privacy policies.
RESUMO
BACKGROUND: Patients with colorectal cancer who undergo surgery face many postoperative problems. These problems include the risk of relapse, side effects, and long-term complications. OBJECTIVE: This study sought to design and develop a remote monitoring system as a technological solution for the postdischarge care of these patients. METHODS: This research was conducted in 3 main steps: system feature extraction, system design, and evaluation. After feature extraction from a systematic review, the necessary features were defined by 18 clinical experts in Iran. In the next step, the architecture of the system was designed based on the requirements; the software and hardware parts of the system were embedded in the architecture, then the software system components were drawn using the unified modeling language diagrams, and the details of software system implementation were identified. Regarding the hardware design, different accessible hardware modules were evaluated, and suitable ones were selected. Finally, the usability of the system was evaluated by demonstrating it over a Skype virtual meeting session and using Nilsen's usability principles. RESULTS: A total of 21 mandatory features in 5 main categories, including patient information registration, periodic monitoring of health parameters, education, reminders, and assessments, were defined and validated for the system. The software was developed using an ASP.Net core backend, a Microsoft SQL Server database, and an Ionic frontend alongside the Angular framework, to build an Android app. The user roles of the system included 3 roles: physicians, patients, and the system administrator. The hardware was designed to contain an Esp8266 as the Internet of Things module, an MLX90614 infrared temperature sensor, and the Maxim Integrated MAX30101 sensor for sensing the heartbeat. The hardware was designed in the shape of a wristband device using SolidWorks 2020 and printed using a 3D printer. The firmware of the hardware was developed in Arduino with the capability of firmware over the air. In evaluating the software system from the perspective of usability, the system received an average score of 3.8 out of 5 from 4 evaluators. CONCLUSIONS: Sensor-based telemonitoring systems for patients with colorectal cancer after surgery are possible solutions that can make the process automatic for patients and caregivers. The apps for remote colorectal patient monitoring could be designed to be useful; however, more research regarding the developed system's implementation in clinic settings and hospitals is required to understand the probable barriers and limitations.
RESUMO
Background: The rapid prevalence of coronavirus disease 2019 (COVID-19) has caused a pandemic worldwide and affected the lives of millions. The potential fatality of the disease has led to global public health concerns. Apart from clinical practice, artificial intelligence (AI) has provided a new model for the early diagnosis and prediction of disease based on machine learning (ML) algorithms. In this study, we aimed to make a prediction model for the prognosis of COVID-19 patients using data mining techniques. Methods: In this study, a data set was obtained from the intelligent management system repository of 19 hospitals at Shahid Beheshti University of Medical Sciences in Iran. All patients admitted had shown positive polymerase chain reaction (PCR) test results. They were hospitalized between February 19 and May 12 in 2020, which were investigated in this study. The extracted data set has 8621 data instances. The data include demographic information and results of 16 laboratory tests. In the first stage, preprocessing was performed on the data. Then, among 15 laboratory tests, four of them were selected. The models were created based on seven data mining algorithms, and finally, the performances of the models were compared with each other. Results: Based on our results, the Random Forest (RF) and Gradient Boosted Trees models were known as the most efficient methods, with the highest accuracy percentage of 86.45% and 84.80%, respectively. In contrast, the Decision Tree exhibited the least accuracy (75.43%) among the seven models. Conclusion: Data mining methods have the potential to be used for predicting outcomes of COVID-19 patients with the use of lab tests and demographic features. After validating these methods, they could be implemented in clinical decision support systems for better management and providing care to severe COVID-19 patients.
RESUMO
Background: Despite many studies done to predict severe coronavirus 2019 (COVID-19) patients, there is no applicable clinical prediction model to predict and distinguish severe patients early. Based on laboratory and demographic data, we have developed and validated a deep learning model to predict survival and assist in the triage of COVID-19 patients in the early stages. Methods: This retrospective study developed a survival prediction model based on the deep learning method using demographic and laboratory data. The database consisted of data from 487 patients with COVID-19 diagnosed by the reverse transcription-polymerase chain reaction test and admitted to Imam Khomeini hospital affiliated to Tehran University of Medical Sciences from February 21, 2020, to June 24, 2020. Results: The developed model achieved an area under the curve (AUC) of 0.96 for survival prediction. The results demonstrated the developed model provided high precision (0.95, 0.93), recall (0.90,0.97), and F1-score (0.93,0.95) for low- and high-risk groups. Conclusion: The developed model is a deep learning-based, data-driven prediction tool that can predict the survival of COVID-19 patients with an AUC of 0.96. This model helps classify admitted patients into low-risk and high-risk groups and helps triage patients in the early stages.
RESUMO
Background and Aims: The Internet of Things (IoTs) is a set of connected objects and devices that share data and pursue a common goal in different areas. IoT technology can significantly help the healthcare system by enabling the monitoring of elderly and chronic disease patients. Along with the growth of this technology, its challenges and limitations such as Connectivity, Compatibility, Standards, cost, legal, and ethical also increase. One of the most critical and challenging issues in the IoT is ethical issues. This study aims to explore the key ethical aspects of the IoT and Categorize them based on the executive phases of IoT in healthcare. Methods: The current study was conducted in two phases using the mixed-method approach. In the first phase, a systematic review was conducted in relevant databases to identify ethical issues of the IoT. In the second phase, a focus group discussion was conducted to classify the extracted data elements based on executive phases of IoT by medical informatics experts and computer engineerings. Results: Among the 138 papers retrieved through the search strategy, 11 articles were selected, and 12 ethical issues related to IoT were identified. The obtained results revealed the importance of ethical issues of IoT, including security, confidentiality, privacy, anonymity, freedom to withdraw, informed consent, integrity, availability, authorization, access control, censoring, and eavesdropping. They were classified into five main categories of executive phases of IoT based on the five experts' opinions affiliated with SUMS, including data collection, data storage, data process, data transmission, and data delivery. Conclusion: Because of the key role of the IoT in disease prevention, real-time tele-monitoring of patient's functions, testing of treatments, health management, and health research, considering the risks relating to Health care and patient data is essential. Moreover, health policymakers should be aware of the ethical commitment to using IoT technology.
RESUMO
Background: Breast cancer is considered one of the most common cancers in women caused by various clinical, lifestyle, social, and economic factors. Machine learning has the potential to predict breast cancer based on features hidden in data. Objective: This study aimed to predict breast cancer using different machine-learning approaches applying demographic, laboratory, and mammographic data. Material and Methods: In this analytical study, the database, including 5,178 independent records, 25% of which belonged to breast cancer patients with 24 attributes in each record was obtained from Motamed cancer institute (ACECR), Tehran, Iran. The database contained 5,178 independent records, 25% of which belonged to breast cancer patients containing 24 attributes in each record. The random forest (RF), neural network (MLP), gradient boosting trees (GBT), and genetic algorithms (GA) were used in this study. Models were initially trained with demographic and laboratory features (20 features). The models were then trained with all demographic, laboratory, and mammographic features (24 features) to measure the effectiveness of mammography features in predicting breast cancer. Results: RF presented higher performance compared to other techniques (accuracy 80%, sensitivity 95%, specificity 80%, and the area under the curve (AUC) 0.56). Gradient boosting (AUC=0.59) showed a stronger performance compared to the neural network. Conclusion: Combining multiple risk factors in modeling for breast cancer prediction could help the early diagnosis of the disease with necessary care plans. Collection, storage, and management of different data and intelligent systems based on multiple factors for predicting breast cancer are effective in disease management.
RESUMO
BACKGROUND: Since the beginning of the COVID-19 outbreak, a significant number of mobile health apps have been created around the world and in Iran to help consequence reduction of this emerging pandemic. OBJECTIVES: This study aimed to review the characteristics of Persian Android and iOS apps related to COVID-19 and determine their use-cases based on a reference model. METHODS: This was a cross-sectional descriptive study conducted in three main steps. First, a systematic search was conducted via Iranian mobile apps' markets using the keywords related to COVID-19 in January 2021. Then, the retrieved apps were analyzed according to their characteristics. Finally, the use-cases of the given apps were determined and categorized based on a reference model. RESULTS: Based on our inclusion criteria, 122 apps were selected and evaluated. Most of these apps (87.7%) was free. Small proportions (5%) of reviewed apps have been developed with participation of clinical expert and half of the apps mentioned the references they used. Furthermore, about half of the apps (50.8%) were provided contact information of the developers. The studied apps were classified into four use-case major categories, including educational (98%), fulfilling a contextual need (18%), communicating, and/or sharing the information (0.83%), and health-related management (2%). CONCLUSION: The results showed that the Persian mobile apps for COVID-19 are not in a satisfying situation. Furthermore, although these apps are significant in quantity but in terms of use-cases, they are not widespread.
RESUMO
BACKGROUND: Colorectal cancer survivors face multiple challenges after discharge. eHealth may potentially support them by providing tools such as smartphone apps. They have lots of capabilities to exchange information and could be used for remote monitoring of these patients. OBJECTIVE: In this study, we addressed the required features for apps designed to follow up colorectal cancer patients based on survivors' and clinical experts' views. METHODS: A mixed methods study was conducted. Features of related apps were extracted through the literature; the features were categorized, and then, they were modified. A questionnaire was designed containing the features listed and prioritized based on the MoSCoW (Must have, Should have, Could have, Won't have) technique and an open question for each category. The link to the questionnaire was shared among clinical experts in Iran. The answers were analyzed using the content validity ratio (CVR), and based on the value of this measure, the minimum feature set of a monitoring app to follow up patients with colorectal cancer was addressed. In addition, a telephone interview with colorectal cancer survivors was conducted to collect their viewpoints regarding a remote monitoring system for colorectal cancer cases. RESULTS: The questionnaire contained 10 sections evaluating 9 categories of features. The questionnaire was completed by 18 experts. The minimum set of features in the app was identified as patient information registration, sign and symptom monitoring, education, reminders, and patient evaluation (0.42 < CVR < 0.85). Features including physical activity, personalized advice, and social network did not achieve the minimum score (-0.11 < CVR < 0.39). We interviewed 9 colorectal cancer survivors. Information registration, sign and symptom monitoring, education, and personalized advice were the features with high priority from the survivors' perspectives. Scheduling, shopping, and financial support features were emphasized by survivors in the interview. CONCLUSIONS: The requirement set could be used to design an app for the targeted population or patients affected by other cancers. As the views from both survivors and clinical experts were considered in this study, the remote system may more adequately fulfill the need for follow-up of survivors. This eases the patients' and health care providers' communication and interaction.