FEMaLe: The use of machine learning for early diagnosis of endometriosis based on patient self-reported data-Study protocol of a multicenter trial.

INTRODUCTION: Endometriosis is a chronic disease that affects up to 190 million women and those assigned female at birth and remains unresolved mainly in terms of etiology and optimal therapy. It is defined by the presence of endometrium-like tissue outside the uterine cavity and is commonly associated with chronic pelvic pain, infertility, and decreased quality of life. Despite the availability of various screening methods (e.g., biomarkers, genomic analysis, imaging techniques) intended to replace the need for invasive surgery, the time to diagnosis remains in the range of 4 to 11 years. AIMS: This study aims to create a large prospective data bank using the Lucy mobile health application (Lucy app) and analyze patient profiles and structured clinical data. In addition, we will investigate the association of removed or restricted dietary components with quality of life, pain, and central pain sensitization. METHODS: A baseline and a longitudinal questionnaire in the Lucy app collects real-world, self-reported information on symptoms of endometriosis, socio-demographics, mental and physical health, economic factors, nutritional, and other lifestyle factors. 5,000 women with confirmed endometriosis and 5,000 women without diagnosed endometriosis in a control group will be enrolled and followed up for one year. With this information, any connections between recorded symptoms and endometriosis will be analyzed using machine learning. CONCLUSIONS: We aim to develop a phenotypic description of women with endometriosis by linking the collected data with existing registry-based information on endometriosis diagnosis, healthcare utilization, and big data approach. This may help to achieve earlier detection of endometriosis with pelvic pain and significantly reduce the current diagnostic delay. Additionally, we may identify dietary components that worsen the quality of life and pain in women with endometriosis, upon which we can create real-world data-based nutritional recommendations.

Serum bta-miRNA-375 as a potential biomarker for the early diagnosis of enzootic bovine leukosis.

To identify a biomarker for the early diagnosis of enzootic bovine leukosis (EBL) caused by bovine leukemia virus (BLV), we investigated the expression of a microRNA, bta-miR-375, in cattle serum. Using quantitative reverse-transcriptase PCR analysis, we measured bta-miR-375 levels in 27 samples from cattle with EBL (EBL cattle), 45 samples from animals infected with BLV but showing no clinical signs (NS cattle), and 30 samples from cattle uninfected with BLV (BLV negative cattle). In this study, we also compared the kinetics of bta-miR-375 with those of the conventional biomarkers of proviral load (PVL), lactate dehydrogenase (LDH), and thymidine kinase (TK) from the no-clinical-sign phase until EBL onset in three BLV-infected Japanese black (JB) cattle. Bta-miR-375 expression was higher in NS cattle than in BLV negative cattle (P < 0.05) and greater in EBL cattle than in BLV negative and NS cattle (P < 0.0001 for both comparisons). Receiver operating characteristic curves demonstrated that bta-miR-375 levels distinguished EBL cattle from NS cattle with high sensitivity and specificity. In NS cattle, bta-miR-375 expression was increased as early as at 2 months before EBL onset-earlier than the expression of PVL, TK, or LDH isoenzymes 2 and 3. These results suggest that serum miR-375 is a promising biomarker for the early diagnosis of EBL.

Early identification of macrophage activation syndrome secondary to systemic lupus erythematosus with machine learning.

OBJECTIVE: The macrophage activation syndrome (MAS) secondary to systemic lupus erythematosus (SLE) is a severe and life-threatening complication. Early diagnosis of MAS is particularly challenging. In this study, machine learning models and diagnostic scoring card were developed to aid in clinical decision-making using clinical characteristics. METHODS: We retrospectively collected clinical data from 188 patients with either SLE or the MAS secondary to SLE. 13 significant clinical predictor variables were filtered out using the Least Absolute Shrinkage and Selection Operator (LASSO). These variables were subsequently utilized as inputs in five machine learning models. The performance of the models was evaluated using the area under the receiver operating characteristic curve (ROC-AUC), F1 score, and F2 score. To enhance clinical usability, we developed a diagnostic scoring card based on logistic regression (LR) analysis and Chi-Square binning, establishing probability thresholds and stratification for the card. Additionally, this study collected data from four other domestic hospitals for external validation. RESULTS: Among all the machine learning models, the LR model demonstrates the highest level of performance in internal validation, achieving a ROC-AUC of 0.998, an F1 score of 0.96, and an F2 score of 0.952. The score card we constructed identifies the probability threshold at a score of 49, achieving a ROC-AUC of 0.994 and an F2 score of 0.936. The score results were categorized into five groups based on diagnostic probability: extremely low (below 5%), low (5-25%), normal (25-75%), high (75-95%), and extremely high (above 95%). During external validation, the performance evaluation revealed that the Support Vector Machine (SVM) model outperformed other models with an AUC value of 0.947, and the scorecard model has an AUC of 0.915. Additionally, we have established an online assessment system for early identification of MAS secondary to SLE. CONCLUSION: Machine learning models can significantly improve the diagnostic accuracy of MAS secondary to SLE, and the diagnostic scorecard model can facilitate personalized probabilistic predictions of disease occurrence in clinical environments.

Unlocking Preclinical Alzheimer's: A Multi-Year Label-Free In Vitro Raman Spectroscopy Study Empowered by Chemometrics.

Alzheimer's disease is a progressive neurodegenerative disorder, the early detection of which is crucial for timely intervention and enrollment in clinical trials. However, the preclinical diagnosis of Alzheimer's encounters difficulties with gold-standard methods. The current definitive diagnosis of Alzheimer's still relies on expensive instrumentation and post-mortem histological examinations. Here, we explore label-free Raman spectroscopy with machine learning as an alternative to preclinical Alzheimer's diagnosis. A special feature of this study is the inclusion of patient samples from different cohorts, sampled and measured in different years. To develop reliable classification models, partial least squares discriminant analysis in combination with variable selection methods identified discriminative molecules, including nucleic acids, amino acids, proteins, and carbohydrates such as taurine/hypotaurine and guanine, when applied to Raman spectra taken from dried samples of cerebrospinal fluid. The robustness of the model is remarkable, as the discriminative molecules could be identified in different cohorts and years. A unified model notably classifies preclinical Alzheimer's, which is particularly surprising because of Raman spectroscopy's high sensitivity regarding different measurement conditions. The presented results demonstrate the capability of Raman spectroscopy to detect preclinical Alzheimer's disease for the first time and offer invaluable opportunities for future clinical applications and diagnostic methods.

Implementation of a primary-tertiary shared care model to improve the detection of familial hypercholesterolaemia (FH): a mixed methods pre-post implementation study protocol.

INTRODUCTION: Familial hypercholesterolaemia (FH) is an autosomal dominant inherited disorder of lipid metabolism and a preventable cause of premature cardiovascular disease. Current detection rates for this highly treatable condition are low. Early detection and management of FH can significantly reduce cardiac morbidity and mortality. This study aims to implement a primary-tertiary shared care model to improve detection rates for FH. The primary objective is to evaluate the implementation of a shared care model and support package for genetic testing of FH. This protocol describes the design and methods used to evaluate the implementation of the shared care model and support package to improve the detection of FH. METHODS AND ANALYSIS: This mixed methods pre-post implementation study design will be used to evaluate increased detection rates for FH in the tertiary and primary care setting. The primary-tertiary shared care model will be implemented at NSW Health Pathology and Sydney Local Health District in NSW, Australia, over a 12-month period. Implementation of the shared care model will be evaluated using a modification of the implementation outcome taxonomy and will focus on the acceptability, evidence of delivery, appropriateness, feasibility, fidelity, implementation cost and timely initiation of the intervention. Quantitative pre-post and qualitative semistructured interview data will be collected. It is anticipated that data relating to at least 62 index patients will be collected over this period and a similar number obtained for the historical group for the quantitative data. We anticipate conducting approximately 20 interviews for the qualitative data. ETHICS AND DISSEMINATION: Ethical approval has been granted by the ethics review committee (Royal Prince Alfred Hospital Zone) of the Sydney Local Health District (Protocol ID: X23-0239). Findings will be disseminated through peer-reviewed publications, conference presentations and an end-of-study research report to stakeholders.

Strategies for optimising early detection and obstetric first response management of postpartum haemorrhage at caesarean birth: a modified Delphi-based international expert consensus.

OBJECTIVE: There are no globally agreed on strategies on early detection and first response management of postpartum haemorrhage (PPH) during and after caesarean birth. Our study aimed to develop an international expert's consensus on evidence-based approaches for early detection and obstetric first response management of PPH intraoperatively and postoperatively in caesarean birth. DESIGN: Systematic review and three-stage modified Delphi expert consensus. SETTING: International. POPULATION: Panel of 22 global experts in PPH with diverse backgrounds, and gender, professional and geographic balance. OUTCOME MEASURES: Agreement or disagreement on strategies for early detection and first response management of PPH at caesarean birth. RESULTS: Experts agreed that the same PPH definition should apply to both vaginal and caesarean birth. For the intraoperative phase, the experts agreed that early detection should be accomplished via quantitative blood loss measurement, complemented by monitoring the woman's haemodynamic status; and that first response should be triggered once the woman loses at least 500 mL of blood with continued bleeding or when she exhibits clinical signs of haemodynamic instability, whichever occurs first. For the first response, experts agreed on immediate administration of uterotonics and tranexamic acid, examination to determine aetiology and rapid initiation of cause-specific responses. In the postoperative phase, the experts agreed that caesarean birth-related PPH should be detected primarily via frequently monitoring the woman's haemodynamic status and clinical signs and symptoms of internal bleeding, supplemented by cumulative blood loss assessment performed quantitatively or by visual estimation. Postoperative first response was determined to require an individualised approach. CONCLUSION: These agreed on proposed approaches could help improve the detection of PPH in the intraoperative and postoperative phases of caesarean birth and the first response management of intraoperative PPH. Determining how best to implement these strategies is a critical next step.

[The importance of early recognition of Prader-Willi syndrome]. / Het Prader-Willi-syndroom.

Due to its rare nature and subtle dysmorphisms, Prader-Willi syndrome can be challenging to recognize and diagnose in the neonatal period. Feeding difficulties and hypotonia ('floppy infant') are the most striking characteristics. Prader-Willi syndrome requires specific follow-up and treatment, emphasizing the importance of early recognition.We encountered an infant of three months old with severe hypotonia. The hypotonia ameliorated spontaneously over time, although feeding per nasogastric tube was necessary. There were no apparent dysmorphisms. Extensive genetic investigations showed a maternal uniparental disomy of chromosome 15, fitting with Prader-Willi syndrome explaining all symptoms. After excluding contraindications, treatment with growth hormone therapy was started. Parents were educated regarding medical emergencies specific for Prader-Willi syndrome ('medical alerts'). Although Prader-Willi syndrome is rare, it should always be considered in cases of neonatal hypotonia. Early recognition is paramount as specific recommendations and treatment are warranted.

Evaluating lumbar disc degeneration by MRI quantitative metabolic indicators: the perspective of factor analysis.

PURPOSE: This study aimed to investigate an early diagnostic method for lumbar disc degeneration (LDD) and improve its diagnostic accuracy. METHODS: Quantitative biomarkers of the lumbar body (LB) and lumbar discs (LDs) were obtained using nuclear magnetic resonance (NMR) detection technology. The diagnostic weights of each biological metabolism indicator were screened using the factor analysis method. RESULTS: Through factor analysis, common factors such as the LB fat fraction, fat content, and T2* value of LDs were identified as covariates for the diagnostic model for the evaluation of LDD. This model can optimize the accuracy and reliability of LDD diagnosis. CONCLUSION: The application of biomarker quantification methods based on NMR detection technology combined with factor analysis provides an effective means for the early diagnosis of LDD, thereby improving diagnostic accuracy and reliability.

Utilizing machine learning to facilitate the early diagnosis of posterior circulation stroke.

BACKGROUND: Posterior Circulation Syndrome (PCS) presents a diagnostic challenge characterized by its variable and nonspecific symptoms. Timely and accurate diagnosis is crucial for improving patient outcomes. This study aims to enhance the early diagnosis of PCS by employing clinical and demographic data and machine learning. This approach targets a significant research gap in the field of stroke diagnosis and management. METHODS: We collected and analyzed data from a large national Stroke Registry spanning from January 2014 to July 2022. The dataset included 15,859 adult patients admitted with a primary diagnosis of stroke. Five machine learning models were trained: XGBoost, Random Forest, Support Vector Machine, Classification and Regression Trees, and Logistic Regression. Multiple performance metrics, such as accuracy, precision, recall, F1-score, AUC, Matthew's correlation coefficient, log loss, and Brier score, were utilized to evaluate model performance. RESULTS: The XGBoost model emerged as the top performer with an AUC of 0.81, accuracy of 0.79, precision of 0.5, recall of 0.62, and F1-score of 0.55. SHAP (SHapley Additive exPlanations) analysis identified key variables associated with PCS, including Body Mass Index, Random Blood Sugar, ataxia, dysarthria, and diastolic blood pressure and body temperature. These variables played a significant role in facilitating the early diagnosis of PCS, emphasizing their diagnostic value. CONCLUSION: This study pioneers the use of clinical data and machine learning models to facilitate the early diagnosis of PCS, filling a crucial gap in stroke research. Using simple clinical metrics such as BMI, RBS, ataxia, dysarthria, DBP, and body temperature will help clinicians diagnose PCS early. Despite limitations, such as data biases and regional specificity, our research contributes to advancing PCS understanding, potentially enhancing clinical decision-making and patient outcomes early in the patient's clinical journey. Further investigations are warranted to elucidate the underlying physiological mechanisms and validate these findings in broader populations and healthcare settings.

Access to early diagnosis for attention-deficit/hyperactivity disorder among children and adolescents in Mexico City at specialized mental health services.

BACKGROUND: In Mexico, this pioneering research was undertaken to assess the accessibility of timely diagnosis of Dyads [Children and adolescents with Attention Deficit Hyperactivity Disorder (ADHD) and their primary caregivers] at specialized mental health services. The study was conducted in two phases. The first phase involved designing an "Access Pathway" aimed to identify barriers and facilitators for ADHD diagnosis; several barriers, with only the teacher being identified as a facilitator. In the second phase, the study aimed to determine the time taken for dyads, to obtain a timely diagnosis at each stage of the Access Pathway. As well as identify any disparities based on gender and socioeconomic factors that might affect the age at which children can access a timely diagnosis. METHOD: In a retrospective cohort study, 177 dyads participated. To collect data, the Acceda Survey was used, based on the robust Conceptual Model Levesque, 2013. The survey consisted of 48 questions that were both dichotomous and polytomous allowing the creation of an Access Pathway that included five stages: the age of perception, the age of search, the age of first contact with a mental health professional, the age of arrival at the host hospital, and the age of diagnosis. The data was meticulously analyzed using a comprehensive descriptive approach and a nonparametric multivariate approach by sex, followed by post-hoc Mann-Whitney's U tests. Demographic factors were evaluated using univariable and multivariable Cox regression analyses. RESULTS: 71% of dyads experienced a late, significantly late, or highly late diagnosis of ADHD. Girls were detected one year later than boys. Both boys and girls took a year to seek specialized mental health care and an additional year to receive a formal specialized diagnosis. Children with more siblings had longer delays in diagnosis, while caregivers with formal employment were found to help obtain timely diagnoses. CONCLUSIONS: Our findings suggest starting the Access Pathway where signs and symptoms of ADHD are detected, particularly at school, to prevent children from suffering consequences. Mental health school-based service models have been successfully tested in other latitudes, making them a viable option to shorten the time to obtain a timely diagnosis.

Towards early diagnosis of Alzheimer's disease: advances in immune-related blood biomarkers and computational approaches.

Alzheimer's disease has an increasing prevalence in the population world-wide, yet current diagnostic methods based on recommended biomarkers are only available in specialized clinics. Due to these circumstances, Alzheimer's disease is usually diagnosed late, which contrasts with the currently available treatment options that are only effective for patients at an early stage. Blood-based biomarkers could fill in the gap of easily accessible and low-cost methods for early diagnosis of the disease. In particular, immune-based blood-biomarkers might be a promising option, given the recently discovered cross-talk of immune cells of the central nervous system with those in the peripheral immune system. Here, we give a background on recent advances in research on brain-immune system cross-talk in Alzheimer's disease and review machine learning approaches, which can combine multiple biomarkers with further information (e.g. age, sex, APOE genotype) into predictive models supporting an earlier diagnosis. In addition, mechanistic modeling approaches, such as agent-based modeling open the possibility to model and analyze cell dynamics over time. This review aims to provide an overview of the current state of immune-system related blood-based biomarkers and their potential for the early diagnosis of Alzheimer's disease.

Early detection of diabetic neuropathy based on health belief model: a scoping review.

Introduction: Uncontrolled blood sugar levels may result in complications, namely diabetic neuropathy. Diabetic neuropathy is a nerve disorder that causes symptoms of numbness, foot deformity, dry skin, and thickening of the feet. The severity of diabetic neuropathy carries the risk of developing diabetic ulcers and amputation. Early detection of diabetic neuropathy can prevent the risk of diabetic ulcers. The purpose: to identify early detection of diabetic neuropathy based on the health belief model. Method: This research searched for articles in 6 databases via Scopus, Ebsco, Pubmed, Sage journal, Science Direct, and SpringerLink with the keywords "screening Neuropathy" AND "Detection Neuropathy" AND "Scoring Neuropathy" AND "Diabetic" published in 2019-2023. In this study, articles were identified based on PICO analysis. Researchers used rayyan.AI in the literature selection process and PRISMA Flow-Chart 2020 to record the article filtering process. To identify the risk of bias, researchers used the JBI checklist for diagnostic test accuracy. Results: This research identified articles through PRISMA Flow-Chart 2020, obtaining 20 articles that discussed early detection of diabetic neuropathy. Conclusion: This review reports on the importance of early detection of neuropathy for diagnosing neuropathy and determining appropriate management. Neuropathy patients who receive appropriate treatment can prevent the occurrence of diabetic ulcers. The most frequently used neuropathy instruments are the vibration perception threshold (VPT) and questionnaire Michigan Neuropathy Screening Instrument (MNSI). Health workers can combine neuropathy instruments to accurately diagnose neuropathy.

An algorithm for the early diagnosis and correct approach to dementia management: results of a multiprofessional team.

BACKGROUNG: The early identification of cognitive disorder is a primary scope, because it could reduce the rate of severe cognitive impairment and thus contribute to reduce healthcare costs in the next future. AIMS: The present paper aimed to build a virtuous diagnostic path of cognitive impairment, highlighting all the professionalism that can serve this purpose. METHODS: The Delphi method was used by the experts, who reviewed the information available during each meeting related to the following topics: early diagnosis of cognitive impairment, definition of Mild Cognitive Impairment, unmet needs in post-stroke patients, critical decision-making nodes in complex patients, risk factors, neuropsychological, imaging diagnosis, blood tests, the criteria for differential diagnosis and the possible treatments. RESULTS: The discussion panels analyzed and discussed the available evidences on these topics and the related items. At each meeting, the activities aimed at the creation of a diagnostic-welfare flow chart derived from the proposal of the board and the suggestions of the respondents. Subsequently, the conclusions of each panel were written, and the study group reviewed them until a global consensus was reached. Once this process was completed, the preparation of the final document was carried out. CONCLUSIONS: Eventually, we built an algorithm for the early diagnosis and treatment, the risk factors, with the possible differences among the different kinds of dementia.

A machine learning model for the early diagnosis of bloodstream infection in patients admitted to the pediatric intensive care unit.

Bloodstream infection (BSI) is associated with increased morbidity and mortality in the pediatric intensive care unit (PICU) and high healthcare costs. Early detection and appropriate treatment of BSI may improve patient's outcome. Data on machine-learning models to predict BSI in pediatric patients are limited and neither study included time series data. We aimed to develop a machine learning model to predict an early diagnosis of BSI in patients admitted to the PICU. This was a retrospective cohort study of patients who had at least one positive blood culture result during stay at a PICU of a tertiary-care university hospital, from January 1st to December 31st 2019. Patients with positive blood culture results with growth of contaminants and those with incomplete data were excluded. Models were developed using demographic, clinical and laboratory data collected from the electronic medical record. Laboratory data (complete blood cell counts with differential and C-reactive protein) and vital signs (heart rate, respiratory rate, blood pressure, temperature, oxygen saturation) were obtained 72 hours before and on the day of blood culture collection. A total of 8816 data from 76 patients were processed by the models. The machine committee was the best-performing model, showing accuracy of 99.33%, precision of 98.89%, sensitivity of 100% and specificity of 98.46%. Hence, we developed a model using demographic, clinical and laboratory data collected on a routine basis that was able to detect BSI with excellent accuracy and precision, and high sensitivity and specificity. The inclusion of vital signs and laboratory data variation over time allowed the model to identify temporal changes that could be suggestive of the diagnosis of BSI. Our model might help the medical team in clinical-decision making by creating an alert in the electronic medical record, which may allow early antimicrobial initiation and better outcomes.

Early autism diagnosis based on path signature and Siamese unsupervised feature compressor.

Autism spectrum disorder has been emerging as a growing public health threat. Early diagnosis of autism spectrum disorder is crucial for timely, effective intervention and treatment. However, conventional diagnosis methods based on communications and behavioral patterns are unreliable for children younger than 2 years of age. Given evidences of neurodevelopmental abnormalities in autism spectrum disorder infants, we resort to a novel deep learning-based method to extract key features from the inherently scarce, class-imbalanced, and heterogeneous structural MR images for early autism diagnosis. Specifically, we propose a Siamese verification framework to extend the scarce data, and an unsupervised compressor to alleviate data imbalance by extracting key features. We also proposed weight constraints to cope with sample heterogeneity by giving different samples different voting weights during validation, and used Path Signature to unravel meaningful developmental features from the two-time point data longitudinally. We further extracted machine learning focused brain regions for autism diagnosis. Extensive experiments have shown that our method performed well under practical scenarios, transcending existing machine learning methods and providing anatomical insights for autism early diagnosis.

[CLINICAL MANIFESTATIONS OF AUTOIMMUNE DISEASES].

INTRODUCTION: Ocular inflammation, uveitis, represents over 40 distinct diseases, caused by infectious or non-infectious etiologies. Non-infectious uveitis may be related to systemic autoimmune diseases. Most uveitis patients are of working age, and prolonged disease may affect their independence and ability to work. Uveitis has various clinical manifestations and may result in the development of ocular complications and vision loss. Uveitis accounts for 10-15% of blindness in the developed world. Autoimmune diseases are increasing globally and often involve the eyes. Most cases occur in young active people and therefore any ocular changes have a longer effect. Symptoms may be mild but they might be severe, even blindness. It accounts for 10% to 15% of all causes of blindness among people of working age in the developed world. OBJECTIVES: To describe the ocular manifestation of uveitis related to systemic autoimmune diseases. We will describe ocular signs related to the disease and discuss the treatment approach to prevent the development of ocular complications and vision loss. METHODS: Review of clinical findings and treatment approach to non-infectious uveitis. CONCLUSIONS: Ocular involvement is commonly found in many autoimmune diseases. The severity of ocular disease varies between cases and complications may result in vision loss. Early diagnosis and treatment may prevent the development of ocular complications, maintaining visual acuity and patient independence.