Medical Entities Research Articles

Valuable Knowledge Mining: Deep Analysis of Heart Disease and Psychological Causes Based on Large-Scale Medical Data

The task of accurately identifying medical entities and extracting entity relationships from large-scale medical text data has become a hot topic in recent years, aiming to mine potential rules and knowledge. How to conduct in-depth context analysis from biomedical texts, such as medical procedures, diseases, therapeutic drugs, and disease characteristics, and identify valuable knowledge in the medical field is our main research content. Through the process of knowledge mining, a deeper understanding of the complex relationships between various factors in diseases can be gained, which holds significant guiding implications for clinical research. An approach based on context semantic analysis is proposed to realize medical entity recognition and entity relationship extraction. In addition, we build a medical knowledge base related to coronary heart disease and combine the NCBI disease dataset and the medical lexicon dataset extracted from the text as the test data of the experiment. Experimental results show that this model can effectively identify entities in medical text data; the WBC model achieved an F1 score of 89.2% in the experiment, while the CSR model achieved an F1 score of 83.4%, and the result is better than other methods.

CLART: A cascaded lattice-and-radical transformer network for Chinese medical named entity recognition

Chinese medical named entity recognition (NER) is a fundamental task in Chinese medical natural language processing, aiming to recognize Chinese medical entities within unstructured medical texts. However, it poses significant challenges mainly due to the extensive usage of medical terms in Chinese medical texts. Although previous studies have made attempts to incorporate lexical or radical knowledge in order to improve the comprehension of medical texts, these studies either focus solely on one of these aspects or utilize a basic concatenation operation to combine these features, which fails to fully utilize the potential of lexical and radical knowledge. In this paper, we propose a novel Cascaded LAttice-and-Radical Transformer (CLART) network to exploit both lexical and radical information for Chinese medical NER. Specifically, given a sentence, a medical lexicon, and a radical dictionary, we first construct a flat lattice (i.e., character-word sequence) for the sentence and radical components of each Chinese character through word matching and radical parsing, respectively. We then employ a lattice Transformer module to capture the dense interactions between characters and matched words, facilitating the enhanced utilization of lexical knowledge. Subsequently, we design a radical Transformer module to model the dense interactions between the lattice and radical features, facilitating better fusion of the lexical and radical knowledge. Finally, we feed the updated lattice-and-radical-aware character representations into a Conditional Random Fields (CRF) decoder to obtain the predicted labels. Experimental results conducted on two publicly available Chinese medical NER datasets show the effectiveness of the proposed method.

HealthNet: A Health Progression Network via Heterogeneous Medical Information Fusion.

Numerous electronic health records (EHRs) offer valuable opportunities for understanding patients' health status at different stages, namely health progression. Extracting the health progression patterns allows researchers to perform accurate predictive analysis of patient outcomes. However, most existing works on this task suffer from the following two limitations: 1) the diverse dependencies among heterogeneous medical entities are overlooked, which leads to the one-sided modeling of patients' status and 2) the extraction granularity of patient's health progression patterns is coarse, limiting the model's ability to accurately infer the patient's future status. To address these challenges, a pretrained Health progression network via heterogeneous medical information fusion, HealthNet, is proposed in this article. Specifically, a global heterogeneous graph in HealthNet is built to integrate heterogeneous medical entities and the dependencies among them. In addition, the proposed health progression network is designed to model hierarchical medical event sequences. By this method, the fine-grained health progression patterns of patients' health can be captured. The experimental results on real disease datasets demonstrate that HealthNet outperforms the state-of-the-art models for both diagnosis prediction task and mortality prediction task.

Sprawozdanie z konferencji pn. "Ogólnopolskie Forum wymiany doświadczeń i dobrych praktyk między Wojskowym Instytutem Medycznym a współpracującymi z nim podmiotami w zwalczaniu skutków COVID-19"

17 listopada 2022 r. odbyła się w Warszawie konferencja pn. „Ogólnopolskie Forum wymiany doświadczeń i dobrych praktyk między Wojskowym Instytutem Medycznym a współpracującymi z nim podmiotami w zwalczaniu skutków COVID-19” zorganizowana przez Zakład Zdrowia Publicznego, Epidemiologii i Wakcynologii z Poradnią Szczepień i Rejonową Bazą Zaopatrzenia Medycznego Wojskowego Instytutu Medycznego – Państwowego Instytutu Badawczego.

Application of Entity-BERT model based on neuroscience and brain-like cognition in electronic medical record entity recognition.

In the medical field, electronic medical records contain a large amount of textual information, and the unstructured nature of this information makes data extraction and analysis challenging. Therefore, automatic extraction of entity information from electronic medical records has become a significant issue in the healthcare domain. To address this problem, this paper proposes a deep learning-based entity information extraction model called Entity-BERT. The model aims to leverage the powerful feature extraction capabilities of deep learning and the pre-training language representation learning of BERT(Bidirectional Encoder Representations from Transformers), enabling it to automatically learn and recognize various entity types in medical electronic records, including medical terminologies, disease names, drug information, and more, providing more effective support for medical research and clinical practices. The Entity-BERT model utilizes a multi-layer neural network and cross-attention mechanism to process and fuse information at different levels and types, resembling the hierarchical and distributed processing of the human brain. Additionally, the model employs pre-trained language and sequence models to process and learn textual data, sharing similarities with the language processing and semantic understanding of the human brain. Furthermore, the Entity-BERT model can capture contextual information and long-term dependencies, combining the cross-attention mechanism to handle the complex and diverse language expressions in electronic medical records, resembling the information processing method of the human brain in many aspects. Additionally, exploring how to utilize competitive learning, adaptive regulation, and synaptic plasticity to optimize the model's prediction results, automatically adjust its parameters, and achieve adaptive learning and dynamic adjustments from the perspective of neuroscience and brain-like cognition is of interest. Experimental results demonstrate that the Entity-BERT model achieves outstanding performance in entity recognition tasks within electronic medical records, surpassing other existing entity recognition models. This research not only provides more efficient and accurate natural language processing technology for the medical and health field but also introduces new ideas and directions for the design and optimization of deep learning models.

Clinical and Pathophysiological Aspects of Curling Ulcer: A Comprehensive Exploration of its Manifestations and Therapeutic Approaches

Curling's ulcer, also known as stress ulcer, represents a medical entity of considerable significance, characterized by the formation of ulcerative lesions in the gastric or duodenal mucosa in critically ill and traumatized patients. This condition, although infrequent, imposes a significant burden in terms of morbidity and mortality, due to its unpredictable clinical manifestations and its rapid and potentially unfavorable evolution. This article delves into the intricate pathophysiologic mechanisms underlying Curling's ulcer, highlighting the fundamental relationship with physiologic stress and hemodynamic alterations present in conditions such as extensive burns and severe trauma. The cascade of events culminating in mucosal barrier disruption, including tissue ischemia, exaggerated release of free radicals and proinflammatory cytokines, as well as imbalance in the production of gastroprotective prostaglandins, is comprehensively examined. The clinical manifestations and diagnostic challenges associated with Curling's ulcer are explored in detail, emphasizing the need for a high index of suspicion in critically ill patients to avoid delays in detection and treatment. Modern imaging techniques and endoscopic methods that facilitate accurate assessment of ulcerative lesions and their extent are described. In terms of therapeutic strategies, the medical and surgical approaches available to address Curling's ulcer are discussed in depth. The importance of hemodynamic support therapy and stress reduction in preventing ulcer formation is highlighted, as well as the benefits and risks of pharmacologic interventions aimed at mitigating inflammation and promoting mucosal healing are discussed. In addition, criteria for surgical intervention are discussed and guidelines for optimal procedure selection in specific clinical situations are provided. In summary, this article provides a comprehensive overview of Curling's ulcer, from its pathophysiological basis to its clinical implications and treatment options. A detailed understanding of this essential entity in the context of critical and critical care medicine is vital to improve early identification, effective management, and ultimately outcomes in affected patients.

The Role of the Intellectual Potential of Employees in Creating the Goodwill of a Teaching Hospital

Hospitals are medical entities providing health services to patients. The dominant share of labour costs in the cost structure of the healthcare entity is evidence of the critical role of employees in a hospital's activities. Specialized medical staff provide medical services and educate future medical staff, while also conducting clinical trials and supporting the development of medical technologies. The article aims to recognize the impact of the intellectual potential of employees on creating goodwill in a teaching hospital. The inference was made based on the financial data available on hospital employees' income and labour costs as factors in the development of the goodwill of a teaching hospital. The following research questions were posed: whether the existing legal regulations regarding the financing of the activities of teaching hospitals in Poland, including the costs of medical staff, are conducive to the creation and development of goodwill of teaching hospitals; whether the ratio of the value of operating revenues to labour costs can be considered as a determinant of the increase in the goodwill of a teaching hospital. The research was conducted based on reporting data for 2018 - 2019 involving selected teaching hospitals as the basic units associating high-class medical specialists. The research was empirical and based on quantitative and qualitative data. The analyses were of an expert nature, from the perspective of a statutory auditor and a long-term researcher of the problems of the functioning of medical entities - hospitals. The preliminary findings indicate that the intellectual capital of teaching hospitals is crucial in creating and developing the goodwill measured by the ratio of the value of operating revenues to labour costs. The considerations undertaken in the article are an essential voice in recognizing the conditions for developing hospitals as entities with intellectual capital that is helpful in solving health problems on an international scale. The article is a continuation of the author's research on the development of intellectual capital of employees of teaching hospitals in Poland.

Cutaneous Endometriosis: a rare medical entity

Endometriosis is a unique entity described in the extensive literature as the decidualization of endometrial tissues under the influence of gynecologic hormones outside the uterine cavity; Estrogen-dependent endocrine-gynecological pathology, common in women in the fertile period or menopause, a unique entity described as the presence of endometrial tissue in extrauterine sites; Cutaneous endometriosis is rare, and accounts for about 5% of reports of extrapelvic endometriosis, localizing mainly in the umbilicus region. To identify scientific findings on the diagnosis and clinical management of this rare clinical entity. Integrative review used in this article aims to review methods, theories and/or empirical studies on a topic; For the construction, six steps were outlined and included articles published in the last 10 running years. Cutaneous endometriosis is a rare condition in which endometrial tissue grows outside the uterus. Diagnosis is challenging, but symptoms such as pain and swelling in the umbilicus may be indicative. Dermatoscopy and biopsy are helpful in diagnosis. Treatment can be surgical or hormonal, with surgical excision being the preferred option. Recurrence is low after complete excision. Prognosis is generally favorable with appropriate surgery. Cutaneous endometriosis can affect quality of life and fertility, but many women are able to become pregnant after surgical treatment. Preventive measures include care during cesarean section surgery. Cutaneous endometriosis is a rare and difficult to diagnose disease. Treatment involves surgical resection with clear margins. The lack of scientific studies makes clinical management difficult, but summarizing the best evidence can help in early identification and prevention of complications.

Local and global character representation enhanced model for Chinese medical named entity recognition

Chinese medical named entity recognition (CMNER) aims to extract entities from Chinese unstructured medical texts. Existing character-based NER models do not comprehensively consider character’s characteristics from different perspectives, which limits their performance in applying to CMNER. In this paper, we propose a local and global character representation enhanced model for CMNER. For the input sentence, the model fuses the spacial and sequential character representation using autoencoder to get the local character representation; extracts the global character representation according to the corresponding domain words; integrates the local and global representation through gating mechanism to obtain the enhanced character representation, which has better ability to perceive medical entities. Finally, the model sent the enhanced character representation to the Bi-LSTM and CRF layers for context encoding and tags decoding respectively. The experimental results demonstrate that our model achieves a significant improvement over the best baseline, increasing the F1 values by 1.04% and 0.62% on the IMCS21 and CMeEE datasets, respectively. In addition, we verify the effectiveness of each component of our model by ablation experiments.

A BERT-Span model for Chinese named entity recognition in rehabilitation medicine.

Due to various factors such as the increasing aging of the population and the upgrading of people's health consumption needs, the demand group for rehabilitation medical care is expanding. Currently, China's rehabilitation medical care encounters several challenges, such as inadequate awareness and a scarcity of skilled professionals. Enhancing public awareness about rehabilitation and improving the quality of rehabilitation services are particularly crucial. Named entity recognition is an essential first step in information processing as it enables the automated extraction of rehabilitation medical entities. These entities play a crucial role in subsequent tasks, including information decision systems and the construction of medical knowledge graphs. In order to accomplish this objective, we construct the BERT-Span model to complete the Chinese rehabilitation medicine named entity recognition task. First, we collect rehabilitation information from multiple sources to build a corpus in the field of rehabilitation medicine, and fine-tune Bidirectional Encoder Representation from Transformers (BERT) with the rehabilitation medicine corpus. For the rehabilitation medicine corpus, we use BERT to extract the feature vectors of rehabilitation medicine entities in the text, and use the span model to complete the annotation of rehabilitation medicine entities. Compared to existing baseline models, our model achieved the highest F1 value for the named entity recognition task in the rehabilitation medicine corpus. The experimental results demonstrate that our method outperforms in recognizing both long medical entities and nested medical entities in rehabilitation medical texts. The BERT-Span model can effectively identify and extract entity knowledge in the field of rehabilitation medicine in China, which supports the construction of the knowledge graph of rehabilitation medicine and the development of the decision-making system of rehabilitation medicine.

An In-Depth Analysis of Medullary Strokes at a Tertiary Care Stroke Center: Incidence, Clinical and Radiological Characteristics, Etiology, Treatment, and Prognosis.

Introduction Medullary infarctions (MI) are a rare medical entity that is classified mainly as the more commonly lateral medullary infarcts (LMI) and the less common medial medullary infarcts (MMI). Lateral medullary syndrome, also known as Wallenberg syndrome, results when the medulla oblongata is affected and predominantly occurs secondary to atherosclerotic occlusion of the vertebrobasilar arteries. Previous studies have focused more on the anatomical, clinical, and topographical aspects of medullary infarcts. We describe the incidence of their presentation, radiological findings, etiology, treatment, and outcome at our comprehensive stroke center. Material and method This is a retrospective cohort study of 108 medullary stroke patients with confirmed clinical and radiological diagnoses of MI at Hamad General Hospital, Doha, between January 1, 2018 and December 31, 2020. We evaluated the electronic medical records of all stroke patients. Result During the selected period, a total of 2,912 ischemic strokes were reported. Of these, 843 (28.8%) were posterior circulation strokes. Only 108 (3.7%) patients had medullary strokes. Commonly encountered neurological features were dizziness (94.4%), limb ataxia (84.3%), dysarthria (44.4%), ipsilateral facial sensory loss (32.4%), headache (32.4%), contralateral limb sensory loss (25%), ipsilateral hemiparesis (24%), dysphagia (19.4%), and hiccups (13%). Most strokes reported were either minor (73% with National Institutes of Health Stroke Scale [NIHSS] 1-4) or moderate (26% with NIHSS 5-15). LMIs (87.9%) were the most common, followed by medial paramedian MI (10%). Twenty-five percent had extramedullary involvement, predominantly of the cerebellum (17.6%). Out of the total number of patients, 44 (40.7%) had large vessel atherosclerotic disease, followed by 41 (37.6%) whose stroke was due to small vessel disease, 15 (13.8 %) due to undetermined etiology, and 6 (5.5%) due to arterial dissection. Twenty-eight patients (25.4%) underwent 48-hour Holter monitoring, which detected atrial fibrillation in two patients (1.85%). The majority of patients (98.2%, or 106 patients) received antiplatelet therapy, while 68.5% (74 patients) received single antiplatelet therapy (SAPT), and 29.6% (32 patients) received dual antiplatelet therapy (DAPT). Noteworthy is that only 2.7% (three patients) received thrombolysis as an acute reperfusion therapy. Forty-seven percent (51 patients) were discharged home (mRS 0-2), and 51.9% (56 patients) were transferred to rehabilitation facilities. Follow-up assessments were performed at the stroke clinic for 57.4% (62) of the patients. The assessments found that 46 of the follow-up patients were functionally independent at that time (mRS 0-2). Conclusion This is the first large local study of medullary strokes to determine their frequency, presentation, etiology, treatment, and clinical outcome. Medullary strokes represent 3.7% of total ischemic strokes at our comprehensive stroke center. MI is rare and could present with a variety of neurological and non-specific symptoms that mimic common benign conditions. Prompt and early recognition with a high index of suspicion, the use of posterior NIHSS (POST-NIHSS), and urgent MRI-diffusion-weighted imaging (DWI) of the brain in acute settings can improve early diagnosis and the rate of reperfusion therapy. Further studies are needed to enable the early recognition and treatment of medullary infarcts.

Medical Named Entity Recognition Fusing Part-of-Speech and Stroke Features

It is highly significant from a research standpoint and a valuable practice to identify diseases, symptoms, drugs, examinations, and other medical entities in medical text data to support knowledge maps, question and answer systems, and other downstream tasks that can provide the public with knowledgeable answers. However, when contrasted with other languages like English, Chinese words lack a distinct dividing line, and medical entities have problems such as long length and multiple entity types nesting. Therefore, to address these issues, this study suggests a medical named entity recognition (NER) approach that combines part-of-speech and stroke features. First, the text is fed into the BERT pre-training model to get the semantic representation of the text, while the part-of-speech feature vector is obtained using the part-of-speech dictionary, and the stroke feature of the text is extracted through a convolution neural network (CNN). The word vector is then joined with the part-of-speech and stroke feature vectors, respectively, and input into the BiLSTM and CRF layer for training. Additionally, to balance the disparity in data volume across several types of entities, the class-weighted loss function is included in the loss function. According to the experimental findings, our model’s F1 score on the CCKS2019 dataset reaches 78.65%, and the recognition performance exceeds many existing algorithms.

GWBNER: A named entity recognition method based on character glyph and word boundary features for Chinese EHRs

Electronic Health Records (EHRs) contain unprecedented volumes of data related to health such as diagnosis and treatment information. Based on the technologies of named entity recognition (NER), EHRs mining has become a research focus in health domain. Nevertheless, the complex medical entities are challenging to be recognized, especially in Chinese EHRs. In this paper, a Glyph and Word Boundary-based Named Entity Recognition (GWBNER) method is presented, which takes into account both the Chinese character glyph and word boundary features in Chinese EHRs. Specifically, the character glyphs are utilized to capture the character-level global structural features, and the word boundaries are adopted to extract the word-level local structural features in Chinese. Therefore, the medical entities are fully recognized with rich semantic features from diverse perspectives in Chinese EHR texts. Finally, we conduct extensive experiments to evaluate the novel approach, and the F1 scores of 0.879, 0.998 and 0.962 are achieved on three EHR datasets, respectively. The experimental results demonstrate the optimal performance of the GWBNER method compared with the state-of-the-art models in NER community.

Health and safety challenges in medical entities and the powers of the social labor inspector: Lessons related to the COVID-19 outbreak in the context of internal control of employee health and safety

Employees in the medical profession in a situation where the life of a patient is at risk cannot refrain from working due to unsafe working conditions. Therefore, enforcing the right to safe and hygienic working conditions is particularly important so that employees can provide health care services without additional burdens. The purpose of the study is to determine how the social labour inspector can respond to Occupational Health and Safety (OHS) hazards and whether the current powers of the social labor inspectorate as the employer's internal OHS control body are sufficient. The study conducted a regulatory analysis and used relevant literature, including recent studies on law enforcement. In addition, a questionnaire survey was conducted among trade union representatives of medical professionals on the evaluation of social labour inspector activities and OHS hazards during the COVID-19 epidemic period. In this period characterized by many OHS risks in medical entities, the difficulties faced by employers in carrying out their duty to protect the health of their employees became apparent. The system of internal control with the participation of the social labour inspection in this context needs changes, due to the fact that it is used in an inefficient manner. The reasons for this are primarily incomplete legal regulations. The legislator should guarantee the social labour inspector the right to use both methods of rewarding the employer as an incentive for the proper performance of duties and measures to deter violations of the law. Despite the fact that Polish labour law guarantees mechanisms for OHS control by the social labour inspector, it would be appropriate to expand the catalog of measures used by him to effectively motivate employers to protect worker health. This study is a prelude to a broader discussion of OHS monitoring in the context of OHS hazards occurring in healthcare entities. Med Pr Work Health Saf. 2023;74(4):301-16.

Chinese medical entity recognition based on the dual-branch TENER model.

Named Entity Recognition (NER) is a long-standing fundamental problem in various research fields of Natural Language Processing (NLP) and has been practiced in many application scenarios. However, the application results of NER methods in Chinese electronic medical records (EMRs) are not satisfactory, mainly due to the following two problems: (1) Existing methods do not take into account the impact of medical terminology on model recognition performance, resulting in poor model performance. (2) Existing methods do not fully utilize the Chinese language features contained in EMR, resulting in poor model robustness. Therefore, it is imminent to solve these two problems regarding the performance of the NER model for EMRs. In this paper, a TENER-based radical feature and entity augmentation model for NER in Chinese EMRs is proposed. The TENER model is first used in the pre-training stage to extract deep semantic information from each layer of the feature extractor. In the decoder part, the recognition of medical entity boundary and entity category are divided into two branch tasks. We compare the overall performance of the proposed model with existing models on different datasets using the computed F1 score evaluation metric. The experimental results show that our model achieves the best F1 score of 82.67%, 74.37%, 70.16% on the CCKS2019, ERTCMM, and CEMR data sets. Meanwhile, in the CMeEE challenge, our model surpassed the top-3 with the F1 score of 68.39%. Our proposed model is the first to divide the NER task into a two-branch tasks, entity boundary and types recognition. Firstly, the medical entity dictionary information is integrated into TENER to obtain the feature information of professional terms in Chinese EMRs. Secondly, the features of Chinese radicals in Chinese EMRs extracted by CNN are added to the entity category recognition task. Finally, the effectiveness of the model is validated on four datasets and competitive results are achieved.

Combining knowledge extension with convolution neural network for diabetes prediction

Prediction and diagnosis of diabetes are critical issues in the field of smart healthcare. However, the dependence of large-scale annotated diabetes data and the lack of diabetes knowledge represent significant challenges for diabetes prediction. To address these challenges, we propose a new diabetes prediction model named KE-CNN, which combines knowledge extension and convolution neural network. The KE-CNN model first extracts abnormal indicator features from physical examination index data of diabetic patients and uses Word2vec to embed the feature words. We then employ entity recognition technique named BERT-BiLSTM-CRF to identify medical entities in the condition description text and utilize a knowledge graph to extend the knowledge of each medical entity, followed by using pre-trained Chinese word vectors to embed the extended description text. Finally, we construct a semantic enhanced convolutional neural network model with word embedding vectors and text embedding vectors as dual-channel input, aiming to enhance the feature expression of the KE-CNN model. Our model not only learns and captures more fine-grained features of diabetes information, but also significantly reduces the amount of data required for model training and improves the prediction performance of convolutional neural network models. Our experiments show that the KE-CNN model effectively improves the accuracy of diabetes prediction compared with the benchmark model.

Literature Review: Clinical Data Interoperability Models

A medical entity (hospital, nursing home, rest home, revalidation center, etc.) usually includes a multitude of information systems that allow for quick decision-making close to the medical sensors. The Internet of Medical Things (IoMT) is an area of IoT that generates a lot of data of different natures (radio, CT scan, medical reports, medical sensor data). However, these systems need to share and exchange medical information in a seamless, timely, and efficient manner with systems that are either within the same entity or other healthcare entities. The lack of inter- and intra-entity interoperability causes major problems in the analysis of patient records and leads to additional financial costs (e.g., redone examinations). To develop a medical data interoperability architecture model that will allow providers and different actors in the medical community to exchange patient summary information with other caregivers and partners to improve the quality of care, the level of data security, and the efficiency of care should take stock of the state of knowledge. This paper discusses the challenges faced by medical entities in sharing and exchanging medical information seamlessly and efficiently. It highlights the need for inter- and intra-entity interoperability to improve the analysis of patient records, reduce financial costs, and enhance the quality of care. The paper reviews existing solutions proposed by various researchers and identifies their limitations. The analysis of the literature has shown that the HL7 FHIR standard is particularly well adapted for exchanging and storing health data, while DICOM, CDA, and JSON can be converted in HL7 FHIR or HL7 FHIR to these formats for interoperability purposes. This approach covers almost all use cases.

Lingual abscess, an uncommon cause of tongue oedema: Case series

Lingual abscess is a rare but potentially life-threatening medical entity. Consequently, it requires high medical suspicion in order to prevent misdiagnosis. Unilateral tongue oedema constitutes the characteristic clinical feature.

Intelligent and assisted medicine dispensing machine for elderly visual impaired people with deep neural network fingerprint authentication system

Offering a medication to Elderly and Visually Impaired People (EVIP) in rural areas without staff assistance is a difficult task in the field of health care. The current pill dispenser has limitations when it comes to administering medication before and after food, doesn't take into account over- and under-dosing situations, and doesn't send notifications to the relevant medical entities when the weight of the pills falls below the threshold. Despite the availability of numerous techniques and methods for automating the delivery of pills, there is no assistive method for the timely and secure delivery of medication. The suggested architecture provides EVIP with five crucial capabilities that aren't present in any of the current pill dispensers in an integrated way. In this paper, we present a biometric sensor-based secure access method for medication kits. The right person is only allowed access to the kit based on the finger print scanner. Second, the suggested architecture provides a self-managed and patient-centric service through assisted and automatic medication delivery. The third feature of this paper is the design method for the efficient delivery of pills before and after meals. A method of alerting the medical entities whenever a medication is over or under dosed is a fourth feature of the system. As a fifth feature, the implementation also automatically notifies the pharmacist and doctor when the weight of the pill strips in the chamber falls below the threshold value. Through the use of an integrated Timely Assistance Messaging (TAM) algorithm, all five features are implemented in the suggested architecture. A finger print recognition system is included with VGG-16 deep neural network with image enhancement. The EVIP can use this proposed system in residences, medical facilities, and retirement communities.

Efficient Medical Knowledge Graph Embedding: Leveraging Adaptive Hierarchical Transformers and Model Compression

Medical knowledge graphs have emerged as essential tools for representing complex relationships among medical entities. However, existing methods for learning embeddings from medical knowledge graphs, such as DistMult, RotatE, ConvE, InteractE, JointE, and ConvKB, may not adequately capture the unique challenges posed by the domain, including the heterogeneity of medical entities, rich hierarchical structures, large-scale, high-dimensionality, and noisy and incomplete data. In this study, we propose an Adaptive Hierarchical Transformer with Memory (AHTM) model, coupled with a teacher–student model compression approach, to effectively address these challenges and learn embeddings from a rich medical knowledge dataset containing diverse entities and relationship sets. We evaluate the AHTM model on this newly constructed “Med-Dis” dataset and demonstrate its superiority over baseline methods. The AHTM model achieves substantial improvements in Mean Rank (MR) and Hits@10 values, with the highest MR value increasing by nearly 56% and Hits@10 increasing by 39%. Furthermore, we observe similar performance enhancements on the “FB15K-237” and “WN18RR” datasets. Our model compression approach, incorporating knowledge distillation and weight quantization, effectively reduces the model’s storage and computational requirements, making it suitable for resource-constrained environments. Overall, the proposed AHTM model and compression techniques offer a novel and effective solution for learning embeddings from medical knowledge graphs and enhancing our understanding of complex relationships among medical entities, while addressing the inadequacies of existing approaches.