Disease Classification System Research Articles

Creation of a Novel Classification System (PTNM) for Peyronie's Disease and Penile Curvature Using Evidence-Based Criteria.

Our goal was to identify new Peyronie's disease (PD) subtypes, non-PD penile curvature classifications, and define active (acute) vs stable (chronic) phases of disease using evidence-based analyses. A retrospective review was performed of 1098 men who presented with penile deformity, including subjective standardized and nonstandardized questionnaires and objective measures. A second cohort of 719 men who were sent a mailed survey was also utilized for the relapsing/remitting subtype. Statistical analyses were performed to identify clusters of disease characteristics representative of distinct PD and non-PD categorizations, including sensitivity/specificity analyses and subtype comparisons. Comparative analyses identified 4 distinct subtypes of PD: (1) classical and nonclassical, (2) calcifying-moderate/severe calcification, (3) progressive-subjective worsening following disease onset, and (4) relapsing/remitting-reactivation following ≥ 6 months of stability. Additional, non-PD categorizations included congenital (lifelong), maturational (developed around puberty), and trauma induced. Statistical analyses demonstrated unique profiles among each category. Penile pain was not found to be a reliable predictor for disease progression or stability. Stable phase disease (historically "chronic") was variably defined by subtype: classical (≥3 months); progressive, calcifying, or trauma induced (≥12 months + ≥3 months stable OR ≥6 months stable). Similarly, PD subtypes may be assigned at ≥ 3 months following disease onset. A PTNM staging system is proposed to help communicate disease states, in which P = PD component (Ca-calcifying, Cl-classical, P-progressive, R-relapsing/remitting, U-undifferentiated), T = trauma component (0-absent, 1-present), N = non-PD component (C-congenital, M-maturational, U-undifferentiated), and M = mode (0-stable, 1-active); for example, PClT1N0M0 = stable classical PD with prior trauma. The current study provides an evidence-based proposal for the establishment of new PD subtypes and non-PD curvature categorizations as well as a standardized definition for active vs stable phases of disease.

AI BASED ARECANUT PLANT DISEASE CLASSIFICATION SYSTEM

Arecanut, commonly known as betel nut, is a vital cash crop in many tropical regions, contributing significantly to the agricultural economy. However, like other crops, arecanut plants are susceptible to various diseases that can severely impact yield and quality. Early detection and accurate classification of these diseases are crucial for timely intervention and effective disease management. In this study, we propose an AI-based arecanut plant disease classification system that leverages deep learning techniques to automatically identify and classify different diseases affecting arecanut plants. Convolutional neural networks (CNNs) are employed for feature extraction and disease classification, with transfer learning techniques used to fine-tune pre-trained models on the specific task of arecanut disease recognition. Keywords: Arecanut, betel nut, plant disease classification, deep learning, transfer learning, agricultural AI, disease management. convolutional neural network (CNN).

Clinical Incorporation of the 2017 Classification of Periodontal Diseased Conditions: Part I (Diagnosis of Periodontitis Involving Data From 4,993 Patients).

Background The new classification system for periodontal and peri-implant diseases mentioned a few key points, including (1) "clinical gingival health," which was defined for the first time, and (2) staging and grading system. Thus, the present study defines the practicability of using the current classification system in day-to-day practice. Aim The primary aim of this study is to determine the effectiveness of the new classification system for periodontal and peri-implant diseases and its application in routine dental practices. Materials and methods This is a cross-sectional retrospective, non-interventional study consisting of 4,993 patients who were under active periodontal therapy as well as supportive periodontal therapy. Results Among patients diagnosed with dental biofilm-induced gingivitis with no underlying risk factors, 1105 (73.3%) exhibited bleeding on probing and 897 (45%) showed supragingival or subgingival calculus. Among the stage II grade B periodontitis group, 488 (28.9%) showed beginning destructive periodontal disease and 197 (50.4%) showed established destructive periodontal disease. Conclusion The implementation of the new classification system in routine dental practice has been readily accepted by clinicians. Staging and grading system of classification helps in assessing the severity, extent, and progression of disease.

Classification System for Plant Leaf Diseases Using a Hybrid Machine Learning Model

Classification System for Plant Leaf Diseases Using a Hybrid Machine Learning Model

Continuing professional development in general dentistry-experiences of an online flipped classroom.

Continuing professional development is a lifelong learning process. One pedagogical approach that can be used is active learning. Flipped classroom is a method that has been shown to improve deeper conceptual understanding. In an online setting, the method saves travel, time, and costs. To our knowledge, flipped classroom is rarely used in continuing professional education. This study in general dentistry explored experiences of an online flipped classroom course in continuing professional development. Fifteen dental hygienists, clinically active in general dental care, were interviewed. They were recruited from an online course on the latest classification system for periodontal diseases. The course had been conducted using an active learning and flipped classroom model. The interviews were semi-structured. Data were extracted using qualitative content analysis. The experiences of the dental hygienists could be summarized in three themes: Stimulation of knowledge gain through self-paced studies, The ease of virtual networking among colleagues, and Fostering of direct practical application through collaboration. New and emerging communication technology seems to open new possibilities for continuing professional development in general dentistry. Study participants felt that, in an online environment, mixing asynchronous and synchronous communication in a flipped classroom model facilitated learning in continuing professional development. Online active learning seems to work well in continuous professional development in general dentistry. After the course, the participating dental hygienists stated that they were able to use their new knowledge clinically and felt confident doing so.

Mortality, Functional Status, and Quality of Life after 5 Years of Patients Admitted to Critical Care for Spontaneous Intracerebral Hemorrhage.

The objective of this study was to assess long-term outcome in patients with spontaneous intracerebral hemorrhage admitted to the intensive care unit. Mortality and Glasgow Outcome Scale, Barthel Index, and5-level EQ-5D version (EQ-5D-5L) scores were analyzed in a multicenter cohort study of three Spanish hospitals (336 patients). Mortality was also analyzed in theMedical Information Mart for Intensive Care III (MIMIC-III) database. The median(25th percentile-75th percentile) age was 62 (50-70) years, the median Glasgow Coma Score was 7 (4-11) points, and the median Acute Physiology and Chronic Health disease Classification System II(APACHE-II) score was 21 (15-26) points. Hospital mortality was 54.17%, mortality at 90days was 56%, mortality at 1year was 59.2%, and mortality at 5years was 66.4%. In the Glasgow Outcome Scale, a normal or disabled self-sufficient situation was recorded in 21.5% of patients at 6months, in 25.5% of patients after 1year, and in 22.1% of patients after 5years of follow-up (4.5% missing). The Barthel Index score of survivors improved over time: 50 (25-80) points at 6months, 70 (35-95) points at 1year, and 90 (40-100) points at 5years (p < 0.001). Quality of life evaluated with the EQ-5D-5L at 1year and 5years indicated that greater than 50% of patients had no problems or slight problems in all items (mobility, self-care, usual activities, pain/discomfort, and anxiety/depression). In the MIMIC-III study (N = 1354), hospital mortality was 31.83% and was 40.5% at 90days and 56.2% after 5years. In patients admitted to the intensive care unit with a diagnosis of nontraumatic intracerebral hemorrhage, hospital mortality up to 90days after admission is very high. Between 90days and 5years after admission, mortality is not high. A large percentage of survivors presented a significant deficit in quality of life and functional status, although with progressive improvement over time. Five years after the hemorrhagic stroke, a survival of 30% was observed, with a good functional status seen in 20% of patients who had been admitted to the hospital.

Retinal Disease Classification using Deep Learning

Retinal disease, which consist a varying range of eye disorders, can be a serious and alarming threat to vision and ocular health. Timely diagnosis is the most important as in early stages it is easier to plan the treatment and intervention. In recent years, the involvement of the deep learning methodologies into the field of ophthalmology has been realized through medical imaging that has revolutionized the ophthalmology study. This research investigates the use of deep learning methods that help in classification of retinal diseases through high-resolution cadaver images. The focus of this work is providing an entirely operational and cutting-edge system for retinal disease classification using deep learning covering the main technical challenges and issues on ethics. The made model is a major advancement in the process of detecting retinal diseases with the aim of improving the quality and efficiency of the eye care. The model is also expected to improve patient outcomes. Keywords: Re-winding, health classification, deep learning, RNN.

Early diagnosis of skin oncologic diseases using artificial intelligence technologies

The last decade has seen significant progress in computer-aided image analysis and recognition, with modern computer-aided diagnostic algorithms not only catching up with, but in many aspects surpassing human abilities. At the heart of this breakthrough is the development of deep convolutional neural networks, which have given a new impetus to medical diagnosis, particularly of skin cancers. In this paper, we analyzed photo-based skin disease classification systems developed using algorithms based on deep learning convolutional neural networks. Such methods have been variously reported to enable automated diagnosis of skin neoplasms with high sensitivity and specificity. A disease that requires more detailed analysis of graphic images — skin melanoma — was chosen as the main object of study. Early diagnosis of melanoma is of great socio-economic importance, as in this case the prognosis of patients is significantly improved. The aim of this work is to analyze the results of artificial intelligence (AI) applications in dermatology, especially in the context of early detection of skin melanoma. Scientific articles were searched in PubMed, Scopus and eLIBRARY databases using the keywords “convolutional neural networks”, “skin cancer” and “artificial intelligence”. The depth of the search was 10 years. The final analysis included 38 sources where the results of our own research were presented. The advantages of artificial intelligence methods for dermatologists were analyzed. Artificial intelligence can significantly assist dermatologists in developing visual neoplasm diagnosis skills and improve diagnostic accuracy. The use of AI to process dermatoscopic data in conjunction with the analysis of anamnestic and clinical information from medical records will reduce the burden on the healthcare system through correctly diagnosed benign skin tumors. All of this promises to have a significant impact on the future development of dermatovenerology.

Eye Disease Classification Based On Fundus Image Using Yolo V8 Algorithm

Eye disease is a very serious problem because it affects one of the five human senses. In many cases many people ignore the impact of eye diseases in the early stages. In general, the process of examining eye diseases is carried out based on manual analysis by doctors (experts) on the fundus image of the patient's eye at a fairly expensive cost. To overcome this, the author proposes an eye disease classification system that can automatically detect eye diseases using YOLO V8. This system can be used for early detection of eye diseases to prevent the development of more serious eye diseases. From the test results of the model built, the accuracy value is 92%, precision is 91%, recall is 92%, F1-score is 91%. Overall, these results can be considered satisfactory and can be implemented for eye disease classification systems based on fundus images.

Attachment Loss Attributable to Third Molar Malposition/Extraction: The Case for Classification

Background: The 2017 World Workshop on the Classification of Periodontal and Peri-implant Diseases and Conditions established a periodontitis staging and grading scheme that—for the first time—integrates an assessment of disease severity with an appraisal of therapeutic complexity and risk for disease progression. Individuals exhibiting attachment loss attributable to third molar malposition or extraction represent a large cohort of non-periodontitis patients highly likely to respond favorably to treatment. The purpose of this clinical report is to illustrate the value in formally categorizing this common periodontal condition. Case Description: Two male patients were referred to the Department of Periodontics, Army Postgraduate Dental School, for evaluation of bone and attachment loss limited to distal surfaces of mandibular second molars. Each patient was treated using a combination of guided tissue regeneration and bone replacement grafts. Favorable clinical and radiographic outcomes were observed over follow-up periods ranging from 4 months to 4 years. Practical Implications: Many patients experiencing bone and attachment loss attributable to third molar malposition or extraction lack periodontitis risk factors/indicators, have low susceptibility to the disease, and are highly likely to respond favorably to treatment. Future classification systems of periodontal diseases and conditions should formally categorize this commonly encountered periodontal condition.

A new deep neuro-fuzzy system for Lyme disease detection and classification using UNet, Inception, and XGBoost model from medical images

A new deep neuro-fuzzy system for Lyme disease detection and classification using UNet, Inception, and XGBoost model from medical images

Deep learning based computer aided diagnosis of Alzheimer’s disease: a snapshot of last 5 years, gaps, and future directions

Alzheimer’s disease affects around one in every nine persons among the elderly population. Being a neurodegenerative disease, its cure has not been established till date and is managed through supportive care by the health care providers. Thus, early diagnosis of this disease is a crucial step towards its treatment plan. There exist several diagnostic procedures viz., clinical, scans, biomedical, psychological, and others for the disease’s detection. Computer-aided diagnostic techniques aid in the early detection of this disease and in the past, several such mechanisms have been proposed. These techniques utilize machine learning models to develop a disease classification system. However, the focus of these systems has now gradually shifted to the newer deep learning models. In this regards, this article aims in providing a comprehensive review of the present state-of-the-art techniques as a snapshot of the last 5 years. It also summarizes various tools and datasets available for the development of the early diagnostic systems that provide fundamentals of this field to a novice researcher. Finally, we discussed the need for exploring biomarkers, identification and extraction of relevant features, trade-off between traditional machine learning and deep learning models and the essence of multimodal datasets. This enables both medical, engineering researchers and developers to address the identified gaps and develop an effective diagnostic system for the Alzheimer’s disease.

Enhanced Skin Disease Detection and Classification System Using Deep Learning Technique

Even in this era of advanced technology, physicians still encounter challenges in accurately identifying skin diseases. Severe skin conditions necessitate urgent hospitalization, yet the diagnostic process involves costly tests with delayed results, exacerbating the worsening of infections. In rural areas, patients often ignore initial symptoms due to limited medical services, allowing conditions to progress unchecked. This underscores the pressing need for highly accurate automated skin disease detection systems. In response to this demand, we developed a multiclass convolutional neural network model aimed at discerning between healthy and diseased skin. Employing Python, we constructed a program utilizing this convolutional neural network with pre-trained networks- AlexNet and VGG19 to address the issue effectively. The primary objective of our project was to categorize five different skin illnesses using input images. By providing our model with pictures of affected skin regions, we aimed to detect ailments like Eczema, Nail fungus, Melanoma, Bullous, and Vascular Tumor. Upon processing the input image, our model would accurately identify and output the specific illness affecting the skin. This streamlined approach significantly aids in timely and accurate diagnosis, crucial for early intervention and treatment of various skin conditions

An optimized deep belief system for heart disease classification and severity prediction

An optimized deep belief system for heart disease classification and severity prediction

Secure cloud storage for IoT based distributed healthcare environment using blockchain orchestrated and deep learning model

Internet of Things (IoT), a distributed healthcare system has integrated different medical resources with sensors and actuators. In this research paper proposes a secure healthcare monitoring system for IoT based distributed healthcare systems in the cloud using blockchain and deep learning (DL) mechanisms. The proposed system involved three phases: secure data transmission, data storage, and disease classification system. Initially, the patients are authenticated via blockchain mechanism and their data is encrypted via Effective Key-based Rivest Shamir Adelman (EKRSA), in which the keys are generated using Circle chaotic map and Linear inertia weight-based Honey Badger Optimization (CLHBO) algorithm. Next, in the data storage phase, these encrypted IoT data are securely stored in the cloud using blockchain technology in a distributed manner. Finally, in the disease classification, the data are gathered from the publicly available dataset, and these collected datasets are preprocessed to handle missing values and data normalization. After that, the proposed system applies a radial basis kernel-based linear discriminant analysis (RBKLDA) model to reduce the dimensionality of the dataset. At last, the disease classification is done by optimal parameter-centered bidirectional long short-term memory (OPCBLSTM). The proposed EKRSA system archives maximum throughput of 99.05% and reliability of 99.66, which is superior to the existing approaches. The OPCBLSTM is investigated for its disease classification process, the proposed one achieves 99.64% accuracy with less processing time of 6 ms, which is superior to the existing classifiers. The experimental analysis proves that the system attained better security and classification metrics results than the existing methods.

Prevalence of Periodontitis Based on the American Academy of Periodontology and European Federation of Periodontology 2017 Classification Scheme in Patients Visiting a Tertiary Care Center in New Delhi – An Epidemiological Study

Introduction: Periodontitis is one of the major reasons for tooth loss in adults. Therefore, it is important to know the true prevalence of the disease. Aim: This study was designed to find out the prevalence of periodontitis in Delhi state based on the American Academy of Periodontology (AAP) and European Federation of Periodontology (EFP) 2017 classification scheme. Materials and Methods: It was a descriptive cross-sectional study involving 2200 patients. Periodontal data were collected using the Community Periodontal Index of Treatment Needs-Epidemiological probe. Periodontal disease was diagnosed with the 2017 AAP and EFP definitions and classifications. Results: Of the study population, 93.2% had no detectable clinical attachment loss (CAL), 34.8% (n = 52) were classified with Stage I, 34.8% (n = 52) with Stage II, 16.8% (n = 25) with Stage III, and none with Stage IV periodontitis. Grade A was the predominant grade, being diagnosed in 50% of the periodontitis cases. The majority of cases (62%) demonstrated generalized periodontitis. Conclusion: The new periodontal disease classification system introduced in 2017 has provided a comprehensive description of periodontal disease which can classify the periodontal disease on the basis of various factors. Based on this, our study reported a maximum number of Stage I and II periodontitis patients.

Cancer patients admitted in the intensive care unit: Characteristics and outcomes

ObjectiveThe aim of this study was to identify the profile of cancer patients admitted in the intensive care unit (ICU) and compares the outcomes with non-cancer patients hospitalized in the same period. DesignThis is a cross-sectional study. SettingData were collected from medical records at Hospital Universitário Santa Terezinha, Joaçaba-SC, Brazil. PatientsAdmitted at ICU from April to November 2018. InterventionsNA. Main variables of interestICU outcomes. ResultsOf the 183 patients, 92 were cancer patients and 91 were non-cancer patients. There was a predominance of females for cancer and males for non-caner group, mostly elderly. Most hospitalizations of cancer patients were postoperative (49.4%). The cause of hospitalization of non-cancer patients was pneumonia, followed by traumatic brain injury, postoperative period, polytrauma, and septicemia. On the Sequential Organ Failure Assessment (SOFA) scale, cancer patients scored an average of 7.8 (±4.2) and on the Acute Physiology and Chronic Health Disease Classification System (APACHE II) 13.3 points (±8.6), whereas non-cancer scored 7.6 (±3.55) and 20.9 points (±7.2), respectively. Non-cancer patients used more invasive mechanical ventilation and vasoactive drugs. ConclusionCancer patients received less sedation and used less mechanical ventilation than non-cancer patients. In addition, cancer patients had a lower APACHE II score, denoting a less severe condition. Most surgical cancer patients demonstrate to benefit from intensive care, but it is still necessary to create more specific criteria for ICU admission.

From progression to progress: The future of multiple sclerosis.

Significant advances have been made in the diagnosis and treatment of multiple sclerosis in recent years yet challenges remain. The current classification of MS phenotypes according to disease activity and progression, for example, does not adequately reflect the underlying pathophysiological mechanisms that may be acting in an individual with MS at different time points. Thus, there is a need for clinicians to transition to a management approach based on the underlying pathophysiological mechanisms that drive disability in MS. A Canadian expert panel convened in January 2023 to discuss priorities for clinical discovery and scientific exploration that would help advance the field. Five key areas of focus included: identifying a mechanism-based disease classification system; developing biomarkers (imaging, fluid, digital) to identify pathologic processes; implementing a data-driven approach to integrate genetic/environmental risk factors, clinical findings, imaging and biomarker data, and patient-reported outcomes to better characterize the many factors associated with disability progression; utilizing precision-based treatment strategies to target different disease processes; and potentially preventing disease through Epstein-Barr virus (EBV) vaccination, counselling about environmental risk factors (e.g. obesity, exercise, vitamin D/sun exposure, smoking) and other measures. Many of the tools needed to meet these needs are currently available. Further work is required to validate emerging biomarkers and tailor treatment strategies to the needs of individual patients. The hope is that a more complete view of the individual's pathobiology will enable clinicians to usher in an era of truly personalized medicine, in which more informed treatment decisions throughout the disease course achieve better long-term outcomes.

A novel location classification system for Crohn's disease based on small bowel involvement: a better predictor of disease progression.

Small bowel involvement is related to poor prognosis in Crohn's disease (CD), which may be a potential marker to stratify patients with a high risk of progression. This study aimed to establish a novel location classification system for CD and to develop a predictive model for disease progression. Consecutive patients with non-stricturing/non-penetrating CD were retrospectively included in the Sixth Affiliated Hospital, Sun Yat-sen University (Guangzhou, P. R. China) between January 2012 and January 2018. Patients were classified into two groups according to disease location: small bowel involvement group and isolated colon group. The primary outcome was disease progression to stricturing or penetrating phenotypes. Progression-free survival was estimated using Cox proportional hazards regression analysis and Kaplan-Meier method. A total of 463 patients were analysed, with a median follow-up time of 55.3 months. Patients with small bowel involvement had a higher risk of disease progression than those with isolated colon disease (hazard ratio = 1.998, P = 0.007), while no differences were found between Montreal location classification and disease progression. Median progression-free survival was higher in the isolated colon group than in the small bowel involvement group (84.5 vs 77.3 months, P = 0.006). Four independent factors associated with disease progression were identified: small bowel involvement, duration of onset of >1 year, deep mucosal ulcer, and C-reactive protein levels of ≥10 mg/L (all P < 0.05). The nomogram model based on these factors showed good performance in predicting disease progression, with a C-index of 0.746 (95% confidence interval, 0.707-0.785). Classifying CD based on small bowel involvement and isolated colon was superior to the Montreal location classification for predicting disease progression.

Vitamin C deficiency in critically ill COVID-19 patients admitted to intensive care unit.

To determine vitamin C plasma kinetics, through the measurement of vitamin C plasma concentrations, in critically ill Coronavirus infectious disease 2019 (COVID-19) patients, identifying eventually the onset of vitamin C deficiency. Prospective, observational, single-center study. Intensive Care Unit (ICU), Vall d'Hebron University Hospital, Barcelona. Study period from November 12th, 2020, to February 24th, 2021. Patients who had a severe hypoxemic acute respiratory failure due to COVID-19 were included. Plasma vitamin C concentrations were measured on days 1, 5, and 10 of ICU admission. There were no vitamin C enteral nor parenteral supplementation. The supportive treatment was performed following the standard of care or acute respiratory distress syndrome (ARDS) patients. Plasma vitamin C concentrations were analyzed using an ultra-performance liquid chromatography (UPLC) system with a photodiode array detector (wavelength set to 245 nm). We categorized plasmatic levels of vitamin C as follows: undetectable: < 1,5 mg/L, deficiency: <2 mg/L. Low plasma concentrations: 2-5 mg/L; (normal plasma concentration: > 5 mg/L). Forty-three patients were included (65% men; mean age 62 ± 10 years). The median Sequential Organ Failure Assessment (SOFA) score was 3 (1-4), and the Acute Physiology and Chronic Health disease Classification System (APACHE II) score was 13 (10-22). Five patients had shock. Bacterial coinfection was documented in 7 patients (16%). Initially all patients required high-flow oxygen therapy, and 23 (53%) further needed invasive mechanical ventilation during 21 (± 10) days. The worst PaO2/FIO2 registered was 93 (± 29). ICU and hospital survival were 77 and 74%, respectively. Low or undetectable levels remained constant throughout the study period in the vast majority of patients. This observational study showed vitamin C plasma levels were undetectable on ICU admission in 86% of patients with acute respiratory failure due to COVID-19 pneumonia requiring respiratory support. This finding remained consistent throughout the study period.