Traditional Clinical Diagnosis Research Articles

Designing the First Trials for Parkinson's Prevention.

For decades the greatest goal of Parkinson's disease (PD) research has often been distilled to the discovery of treatments that prevent the disease or its progression. However, until recently only the latter has been realistically pursued through randomized clinical trials of candidate disease-modifying therapy (DMT) conducted on individuals after they received traditional clinical diagnosis of PD (i.e., tertiary prevention trials). Now, in light of major advances in our understanding of the prodromal stages of PD, as well as its genetics and biomarkers, the first secondary prevention trials for PD are beginning. In this review, we take stock of DMT trials to date, summarize the breakthroughs that allow the identification of cohorts at high risk of developing a traditional diagnosis of PD, and describe key design elements of secondary prevention trials and how they depend on the prodromal stage being targeted. These elements address whom to enroll, what interventions to test, and how to measure secondary prevention (i.e., slowed progression during the prodromal stages of PD). Although these design strategies, along with the biological definition, subtype classification, and staging of the disease are evolving, all are driven by continued progress in the underlying science and integrated by a broad motivated community of stakeholders. While considerable methodological challenges remain, opportunities to move clinical trials of DMT to earlier points in the disease process than ever before have begun to unfold, and the prospects for PD prevention are nowtangible.

Models for depression recognition and efficacy assessment based on clinical and sequencing data

Major depression is a complex psychiatric disorder that includes genetic, neurological, and cognitive factors. Early detection and intervention can prevent progression, and help select the best treatment. Traditional clinical diagnosis tends to be subjective and misdiagnosed. Based on this, this study leverages clinical scale assessments and sequencing data to construct disease prediction models. Firstly, data undergoes preprocessing involving normalization and other requisite procedures. Feature engineering is then applied to curate subsets of features, culminating in the construction of a model through the implementation of machine learning and deep learning algorithms. In this study, 18 features with significant differences between patients and healthy controls were selected. The depression recognition model was constructed by deep learning with an accuracy of 87.26 % and an AUC of 91.56 %, which can effectively distinguish patients with depression from healthy controls. In addition, 33 features selected by recursive feature elimination method were used to construct a prognostic effect model of patients after 2 weeks of treatment, with an accuracy of 75.94 % and an AUC of 83.33 %. The results show that the deep learning algorithm based on clinical and sequencing data has good accuracy and provides an objective and accurate method for the diagnosis and pharmacodynamic prediction of depression. Furthermore, the selected differential features can serve as candidate biomarkers to provide valuable clues for diagnosis and efficacy prediction.

Serum metabolomics study reveals a distinct metabolic diagnostic model for renal calculi

Renal calculi (RC) represent a prevalent disease of the urinary system characterized by a high incidence rate. The traditional clinical diagnosis of RC emphasizes imaging and stone composition analysis. However, the significance of metabolic status in RC diagnosis and prevention remains unclear. This study aimed to investigate serum metabolites in RC patients to identify those associated with RC and to develop a metabolite-based diagnostic model. We employed nontargeted metabolomics utilizing ultra-performance liquid chromatography‒mass spectrometry (UPLC‒MS) to compare serum metabolites between RC patients and healthy controls. Our findings demonstrated significant disparities in serum metabolites, particularly in fatty acids and glycerophospholipids, between the two groups. Notably, the glycerophospholipid (GP) metabolic pathway in RC patients was significantly disrupted. Logistic regression models using differentially abundant metabolites revealed that elevated levels of 2-butyl-4-methyl phenol and reduced levels of phosphatidylethanolamine (P-16:0/22:6(4Z,7Z,10Z,13Z,16Z,19Z)) had the most substantial effect on RC risk. Overall, our study indicates that RC induces notable alterations in serum metabolites and that the diagnostic model based on these metabolites effectively distinguishes RC. This research offers promising insights and directions for further diagnostic and mechanistic studies on RC.

Clinical research on neurological and psychiatric diagnosis and monitoring using wearable devices: A literature review

AbstractWearable devices have opened up exciting possibilities for monitoring and managing home health, particularly in the realm of neurological and psychiatric diseases. These devices capture signals related to physiological and behavioral changes, including heart rate, sleep patterns, and motor functions. Their emergence has resulted in significant advancements in the management of such conditions. Traditional clinical diagnosis and assessment methods heavily rely on patient reports and evaluations conducted by healthcare professionals, often leading to a detachment of patients from their home environment and creating additional burdens for both patients and healthcare providers. The increasing popularity of wearable devices offers a potential solution to these challenges. This review focuses on the clinical utility of wearable devices in diagnosing and monitoring neurological and psychiatric diseases. Through research findings and practical examples, we highlight the potential role of wearable devices in diagnosing and monitoring conditions such as autism spectrum disorder, depression, epilepsy, stroke prognosis, Parkinson's disease, dementia, and other diseases. Additionally, the review discusses the benefits and limitations of wearable devices in clinical applications, while highlighting the challenges they face. Finally, it provides prospects for enhancing the value of wearable devices in the monitoring and diagnosis of neurological and psychiatric diseases.

High-throughput fluorescence sensing array based on tetraphenylethylene derivatives for detecting and distinguishing pathogenic microbes

Infections induced by pathogenic microorganisms will bring negative effects such as diseases that damage health and result in heavy economic burden. Therefore, it is very important to detect and identify the pathogens in time. Moreover, traditional clinical diagnosis or food testing often faces the problem of dealing with a large number of samples. Here, we designed a high-throughput fluorescent sensor array based on the different binding ability of five tetraphenylethylene derivatives (TPEs) with various side chains to different kinds of pathogenic microbes, which is used to detect and distinguish various species, so as to realize rapid mass diagnosis, and hopefully provide guidance for further determination of microbial infections and clinical treatment.

Parkinson’s Disease Detection

Abstract: Parkinson’s Disease is a disorder that affects the nervous system. Parkinson’s disease does not directly cause people to die but can make some people more vulnerable to serious and life-threatening infections. This research addresses the limitations of traditional clinical diagnosis by harnessing the potential of advanced data analysis techniques and machine learning algorithms. The project’s primary objectives include dataset compilation, feature extraction, model development, multimodal fusion, model validation, and considerations for clinical applicability. The dataset will encompass a diverse range of participants diagnosed with PD as well as healthy controls, ensuring the representation of various demographic and clinical factors. By extracting distinctive features from voice recordings, handwriting dynamics, and gait patterns, the project aims to capture unique biomarkers associated with PD. Machine learning models, tailored for each modality, will be developed to classify individuals as PD-positive or PD-negative

Simulating atrial fibrillation patterns and screening strategies using virtual patient-level models

Abstract Introduction Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with increased morbidity and mortality. However, early detection and treatment of AF are hampered by highly variable occurrence and duration of AF episodes, heterogenous patterns of AF progression, and poor symptom-rhythm correlation present in many patients. Purpose To develop a computational patient-level model for simulating individual AF episodes, AF progression, and associated clinical outcomes, and to compare the effectiveness of systematic or symptom-based 1-minute electrocardiography (ECG) or 14-day Holter screening using this model. Methods We developed a Markov model with 7 different rhythm and/or clinical states (sinus rhythm (SR), asymptomatic and symptomatic AF, each with or without previous stroke, and death) and age/sex-dependent transition probabilities estimated based on clinical data (Figure 1A). Additionally, transitions between SR and AF states were modulated by AF-related remodeling, which itself was controlled by the time in AF and age. Results The virtual patient-level model enabled the simulation of changes in rhythm status and clinical outcomes during an entire lifetime with minute-level resolution (Figure 1B). Age/sex-specific AF prevalence / incidence, the proportion of symptomatic episodes and mortality in 4000 virtual patients were in good agreement with clinical data (Figure 1C). We employed the perfect knowledge about rhythm status at any moment in time provided by the model to evaluate systematic and symptom-based 1-minute ECG and 14-day Holter screening for AF in this population. In total, 2372 virtual patients >65 years developed AF. Systematic yearly 1-minute ECG recordings only identified 58 (2.4%) patients. In contrast, 14-day Holter-monitoring detected 18% of AF patients over 65 with a median of 532 days earlier than their clinical AF diagnosis, and identified 11.8% of AF patients who were either completely asymptomatic or only had symptomatic episodes <3 hours. Short-term (2-week) screening after a first symptom had a very low yield, which increased with increasing screening frequency and duration of follow-up (Figure 2). The majority of the remaining AF patients could be diagnosed when their symptoms lasted ≥3 hours, providing time for a traditional clinical diagnosis. Conclusion Our novel patient-level AF model can simulate individual AF patterns and clinical outcomes such as stroke and death in large cohorts of virtual patients. The model highlights the variability of AF episodes that makes effective early detection of asymptomatic AF with short-term monitoring challenging, and provides a tool for future studies into AF progression, screening and prevention of AF-related stroke and mortality.Figure 1Figure 2

Recent Advances in Field Effect Transistor Biosensors: Designing Strategies and Applications for Sensitive Assay

In comparison with traditional clinical diagnosis methods, field-effect transistor (FET)-based biosensors have the advantages of fast response, easy miniaturization and integration for high-throughput screening, which demonstrates their great technical potential in the biomarker detection platform. This mini review mainly summarizes recent advances in FET biosensors. Firstly, the review gives an overview of the design strategies of biosensors for sensitive assay, including the structures of devices, functionalization methods and semiconductor materials used. Having established this background, the review then focuses on the following aspects: immunoassay based on a single biosensor for disease diagnosis; the efficient integration of FET biosensors into a large-area array, where multiplexing provides valuable insights for high-throughput testing options; and the integration of FET biosensors into microfluidics, which contributes to the rapid development of lab-on-chip (LOC) sensing platforms and the integration of biosensors with other types of sensors for multifunctional applications. Finally, we summarize the long-term prospects for the commercialization of FET sensing systems.

MHA: a multimodal hierarchical attention model for depression detection in social media.

As a serious mental disease, depression causes great harm to the physical and mental health of individuals, and becomes an important cause of suicide. Therefore, it is necessary to accurately identify and treat depressed patients. Compared with traditional clinical diagnosis methods, a large amount of real and different types of data on social media provides new ideas for depression detection research. In this paper, we construct a depression detection data set based on Weibo, and propose a Multimodal Hierarchical Attention (MHA) model for social media depression detection. Multimodal data is fed into the model and the attention mechanism is applied within and between modalities at the same time. Experimental results show that the proposed model achieves the best classification performance. In addition, we propose a distribution normalization method, which can optimize the data distribution and improve the accuracy of depression detection.

Heart Disease Prediction; a Machine Learning Approach

Machine learning has been one of the most widely used tools in medical science. It has shown promising application in disease detection as well as in disease prediction. In this paper we focus on the artificial intelligence-based heart disease prediction system using machine learning algorithms. We discuss various algorithms that have been employed by researchers in healthcare sector and chalk out the comparative analysis among these various algorithms. Traditional clinical diagnosis methods have their own limitations, with the help of our study we would be focusing on accuracy and ability to detect the heart disease at early stage. We have discussed some most recent works in heart disease prediction and done a comparative analysis on the accuracy and fusibility of these methods.

Discriminating memory disordered patients from controls using diffusion model parameters from recognition memory.

One hundred and five memory disordered (MD) patients and 57 controls were tested on item recognition memory and lexical decision tasks, and diffusion model analyses were conducted on accuracy and response time distributions for correct and error responses. The diffusion model fit the data well for the MD patients and control subjects, the results replicated earlier studies with young and older adults, and individual differences were consistent between the item recognition and lexical decision tasks. In the diffusion model analysis, MD patients had lower drift rates (with mild Alzheimer's [AD] patients lower than mild cognitive impairment [MCI] patients) as well as wider boundaries and longer nondecision times. These data and results were used in a series of studies to examine how well MD patients could be discriminated from controls using machine-learning techniques, linear discriminant analysis, logistic regression, and support vector machines (all of which produced similar results). There was about 83% accuracy in separating MD from controls, and within the MD group, AD patients had about 90% accuracy and MCI patients had about 68% accuracy (controls had about 90% accuracy). These methods might offer an adjunct to traditional clinical diagnosis. Limitations are noted including difficulties in obtaining a matched group of control subjects as well as the possibility of misdiagnosis of MD patients. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Spectral Representation of Behaviour Primitives for Depression Analysis

Depression is a serious mental disorder affecting millions of people all over the world. Traditional clinical diagnosis methods are subjective, complicated and require extensive participation of clinicians. Recent advances in automatic depression analysis systems promise a future where these shortcomings are addressed by objective, repeatable, and readily available diagnostic tools to aid health professionals in their work. Yet there remain a number of barriers to the development of such tools. One barrier is that existing automatic depression analysis algorithms base their predictions on very brief sequential segments, sometimes as little as one frame. Another barrier is that existing methods do not take into account what the context of the measured behaviour is. In this article, we extract multi-scale video-level features for video-based automatic depression analysis. We propose to use automatically detected human behaviour primitives as the low-dimensional descriptor for each frame. We also propose two novel spectral representations, i.e., spectral heatmaps and spectral vectors, to represent video-level multi-scale temporal dynamics of expressive behaviour. Constructed spectral representations are fed to Convolution Neural Networks (CNNs) and Artificial Neural Networks (ANNs) for depression analysis. We conducted experiments on the AVEC 2013 and AVEC 2014 benchmark datasets to investigate the influence of interview tasks on depression analysis. In addition to achieving state of the art accuracy in severity of depression estimation, we show that the task conducted by the user matters, that fusion of a combination of tasks reaches highest accuracy, and that longer tasks are more informative than shorter tasks, up to a point.

Application of Gold Nanoparticles in Magnetic Resonance Imaging for Targeted Diagnosis and Treatment of Breast Cancer

This study aimed to explore the application of super paramagnetic gold magnetic nanoparticles (Au-M-NPs) in the magnetic resonance imaging (MRI) images for targeted diagnosis and treatment of breast cancer. The reducibility of ethylene glycol to ferric chloride (FeCl3) was adopted to synthesize the Au-M-NPs by solvothermal method by taking acetic acid as the base source and trisodium citrate as the stabilizer. Besides, the synthesized Au-M-NPs were applied in the MRI images for targeted therapy of breast cancer. Patients from a blank group (group A), a control group (group B), and an experimental group (group C) received the traditional clinical diagnosis treatment, MRI diagnosis, and Au-M-NPs targeted therapy with MRI in turn. The results showed that the prepared Au-M-NPs were featured with small particle size and good dispersibility, and were monodispersive after surface modification. The intraoperative blood loss of patients from group A (115.3±9.33 mL) and group B (94.6±9.72 mL) was obviously higher than the loss of group C (68.4±8.7 mL) (P < 0.05). The drainage volume of patients from group B (162.4±12.3 mL) and group C (131.9±11.8 mL) decreased sharply after surgery compared with group A (193.7±11.8 mL), and that in group C was the lowest (P < 0.05). The proportion of local recurrence in patients from group B (12.3%) and group C (6.4%) dropped steeply in contrast to the proportion of group A (13.2%) (P < 0.05). The proportion of tumor metastasis in patients from group B (11.2%) and group C (8.4%) was greatly lower than that of group A (14.8%) (P < 0.05). In conclusion, the application of Au-M-NPs in the diagnosis and treatment of breast cancer with MRI could effectively reduce the incidence of intraoperative and postoperative adverse reactions.

Serum Metabolomic Profiling to Reveal Potential Biomarkers for the Diagnosis of Fatty Liver Hemorrhagic Syndrome in Laying Hens.

Fatty liver hemorrhage syndrome (FLHS), a nutritional and metabolic disease that frequently occurs in laying hens, causes serious losses to the poultry industry. Nowadays, the traditional clinical diagnosis of FLHS still has its limitations. Therefore, searching for some metabolic biomarkers and elucidating the metabolic pathway in vivo are useful for the diagnosis and prevention of FLHS. In the present study, a model of FLHS in laying hens induced by feeding a high-energy, low-protein diet was established. Gas chromatography time-of-flight mass spectrometry (GC-TOF-MS) was used to analyze the metabolites in serum at days 40 and 80. The result showed that, in total, 40 differential metabolites closely related to the occurrence and development of FLHS were screened and identified, which were mainly associated with lipid metabolism, amino acid metabolism, and energy metabolism pathway disorders. Further investigation of differential metabolites showed 10 potential biomarkers such as 3-hydroxybutyric acid, oleic acid, palmitoleic acid, and glutamate were possessed of high diagnostic values by analyzing receiver operating characteristic (ROC) curves. In conclusion, this study showed that the metabolomic method based on GC-TOF-MS can be used in the clinical diagnosis of FLHS in laying hens and provide potential biomarkers for early risk evaluation of FLHS and further insights into FLHS development.

Point-of-Care Emergency Ultrasonography in Non-Traumatic Cardiac Arrest and Near-Arrest Emergency Patients; A Pilot Trial

Background: In this study, we evaluated the applicability and interpretation of point-of-care emergency ultrasound (POCEUS) performed by an emergency physician (EP) in non-traumatic adult cardiac arrest and near-arrest patients at presentation to the Emergency Department (ED). Methods: POCEUS was performed in 5 steps on 73 adults to assess; 1. Qualitative global cardiac function, cardiac chambers and presence of pericardial effusion; 2. Presence of pleural sliding, B-lines, A-lines or consolidation on anterior-superior; 3. Presence of an abdominal aorta aneurysm and pelvic free fluid; 4. Presence of pleural effusion, consolidation, free fluid on lateral-inferior; 5. Qualitative width and collapsibility of the inferior vena cava. A fulfilled checklist and real-time images of ultrasonography were sent by WhatsApp to the head of the study to generate the evidence and collect the data. The process of patient care, in-hospital diagnosis and survival were retrieved from digital hospital records. This prospective multicenter sample study was conducted from November 16, 2015, to January 5, 2016. Results: The most common findings of POCEUS were performed and interpreted to have a first prediction of patients’ acute clinic problem by EPs were compatible with global systolic dysfunction (n = 16, 22.9%), pulmonary edema (n = 17, 23.3%), pulmonary embolus (n = 6, 8.2%), distributive/hypovolemic shock (n = 12, 16.4%), cardiac tamponade or pericardial effusion (n = 5, 6.8%), and pneumonia (n = 31, 42.5%) at presentation. The kappa correlation coefficient value of the POCEUS at presentation versus the final, traditional clinical diagnosis of the admitted ward, was 0.773 (95% CI, 0.747–0.892; p = 0.064, McNemar). Conclusions: POCEUS performed by an EP at presentation had a good agreement between in qualitative prediction of the first differential diagnosis in life-threatened patients and the last diagnosis obtained during hospitalization. Furthermore, this study showed the requirement of evidence in comparison of measurements to the qualitative manner and new descriptive processes in POCEUS for unexplained situations and questions.

P0262DIAGNOSIS OF PNEUMOCYSTIS PNEUMONIA BY METAGENOMIC NEXT-GENERATION SEQUENCING IN PERIPHERAL BLOOD OF PATIENTS WITH KIDNEY DISEASE

Abstract Background and Aims Pneumocystis jirovecii is an opportunistic infectious pathogen that can cause pneumocystis pneumonia in HIV patients. The kidney transplant recipients and patients with kidney diseases receive immunosuppressive therapy, PCP is not uncommon in such patients, but early etiological diagnosis is difficult. Metagenomic next-generation sequencing (mNGS) has higher sensitivity for pathogen identification in a variety of infections. In this study, mNGS was used to detect peripheral blood samples of patients with kidney disease complicated with PCP, and to evaluate the diagnostic value of mNGS in peripheral blood for the etiology of PCP. Method From August 2018 to December 2019, We collected 37 cases with kidney disease complicated with pulmonary infection and clinically diagnosed with PCP after receiving immunosuppressive therapy. mNGS was used to analyze the pathogen types and sequences in peripheral blood samples to evaluate the detection efficiency to PCP. To compare the efficacy of mNGS and traditional clinical diagnosis (fungal G combined with lactate dehydrogenase detection) of PCP. In addition, patients with Bacterial/fungal pneumonia or viral pneumonia were mNGS positive controls. Results 37 peripheral blood samples were collected from 37 patients, results for all samples were obtained within 72 hours. Pneumocystis jirovecii was detected by mNGS in 35 of the 37 samples, with a sensitivity of 94.59%, specificity of 100%. 31 patients had mixed infection. Cytomegalovirus (CMV) was detected in 19 of the 37 cases (51.4%), epstein-barr virus (EBV) was detected in 6 cases, herpes simplex virus (HSV) was detected in 5 cases, and Torquetenovirus was detected in 8 cases. There were 8 cases of bacterial infection, including 2 cases of staphylococcus, 2 cases of acinetobacter, 1 case of klebsiella pneumoniae, 1 case of escherichia coli, and 4 cases of other uncommon bacteria. There were 33 patients with positive fungal G test and elevated lactate dehydrogenase (BG/LDH), and 4 patients with multiple negative fungal G test .The sensitivity of BG/LDH was 89.19%, the specificity was 56.0%. Conclusion mNGS has obvious advantages over the traditional method of diagnosing PCP. It has the characteristics of accuracy, simplicity and noninvasiveness, and is of great value for the early diagnosis of PCP.

Implementing Telehealth in Practice: ACOG Committee Opinion Summary, Number 798.

The term "telemedicine" often is used to refer to traditional clinical diagnosis and monitoring that are delivered by technology. The term "telehealth" refers to the technology-enhanced health care framework that includes services such as virtual visits, remote patient monitoring, and mobile health care. Evidence suggests that telehealth provides comparable health outcomes when compared with traditional methods of health care delivery without compromising the patient-physician relationship, and it also has been shown to enhance patient satisfaction and improve patient engagement. Obstetrician-gynecologists and other physicians who provide telehealth should make certain that they have the necessary hardware, software, and a reliable, secure internet connection to ensure quality care and patient safety. To implement a telehealth program effectively, participating sites must undergo resource assessments to evaluate equipment readiness. Credentialing and privileging in telemedicine depend on the requirements of the facilities where the physician practices and the source of service payment or reimbursement. Obstetrician-gynecologists and other physicians who provide telehealth must meet many safeguards before delivering telehealth services, including federal, state, and local regulatory laws and licensure requirements. Insurance carriers should provide clear guidelines to physicians who provide telehealth to ensure appropriate health insurance coverage for tele-encounters. Telehealth has quickly become integrated into nearly every aspect of obstetrics and gynecology, and current trends in patient-generated data and big data analytics portend increased use. These technology-enhanced health care delivery opportunities enhance, not replace, the current standard of care.

Implementing Telehealth in Practice.

The term "telemedicine" often is used to refer to traditional clinical diagnosis and monitoring that are delivered by technology. The term "telehealth" refers to the technology-enhanced health care framework that includes services such as virtual visits, remote patient monitoring, and mobile health care. Evidence suggests that telehealth provides comparable health outcomes when compared with traditional methods of health care delivery without compromising the patient-physician relationship, and it also has been shown to enhance patient satisfaction and improve patient engagement. Obstetrician-gynecologists and other physicians who practice telehealth should make certain that they have the necessary hardware, software, and a reliable, secure internet connection to ensure quality care and patient safety. To implement a telehealth program effectively, participating sites must undergo resource assessments to evaluate equipment readiness. Credentialing and privileging in telemedicine depend on the requirements of the facilities where the physician practices and the source of service payment or reimbursement. Obstetrician-gynecologists and other physicians who provide telehealth must meet many safeguards before delivering telehealth services, including federal, state, and local regulatory laws and licensure requirements. Insurance carriers should provide clear guidelines to physicians who provide telehealth to ensure appropriate health insurance coverage for telehealth encounters. Telehealth has quickly become integrated into nearly every aspect of obstetrics and gynecology, and current trends in patient-generated data and big data analytics portend increased use. These technology-enhanced health care delivery opportunities enhance, not replace, the current standard of care.

AI-Enabled Diagnosis of Spontaneous Rupture of Ovarian Endometriomas: A PSO Enhanced Random Forest Approach

Spontaneous rupture of ovarian endometriomas (OEs) may cause serious injury to patients. However, in traditional clinical diagnosis, it is vulnerable to be ignored or misdiagnosed for the symptoms of the acute abdomen caused by it are quite similar to those of some common gynecological emergencies, which leads to serious complications to patients. In view of this, this study investigates the AI-enabled, early and accurate diagnosis of spontaneous rupture of OEs. Although artificial intelligence (AI) has been proved to be a powerful tool to help to make accurate clinical diagnosis, however, as far as we know, there is so far no report on AI-enabled diagnosis of spontaneous rupture of OEs yet. Specifically, this study proposes a particle swarm optimization (PSO) enhanced random forest (RF) classification model, called PSO-RF, to make diagnosis, where RF is used to rank feature importance and make diagnosis considering that an OE is ruptured or not is a typical 0-1 classification problem, and PSO is leveraged to fine-tune the essential parameters of RF. The performance of the proposed PSO-RF model is evaluated with practical data collected from a local hospital and fully benchmarked by comparing with eight other machine learning models whose key parameters are sufficiently optimized as well by grid search or PSO, for the sake of fairness. The experiment results show that the proposed PSO-RF model outperforms all the other models, with the accuracy of 97.47%, the area under the ROC curve (AUC) of 0.996, the sensitivity of 94.12% and the specificity of 98.39%. It can be concluded that the PSO-RF model is a highly effective AI-enabled tool for preoperatively diagnosing spontaneous rupture of OEs.

P.192The 100 meter timed test: responsiveness to change, predicting loss of ambulation, and data-driven phenotypes

The 100 meter timed test (100m) is a fixed distance ambulatory assessment used to quantify maximal ambulatory ability in persons with neuromuscular disorders. It has been validated in a cross-sectional cohort of boys with Duchenne muscular dystrophy (DMD) with comparison to typically-developing peers. The purpose of our study was to understand change in 100m performance over time to better interpret expected change as a result of natural history or treatment efficacy, as well as predict loss of ambulation (LOA). Additionally, we explored whether a data-driven phenotype matched traditional clinical diagnosis. We enrolled 231 patients with a dystrophinopathy (age range: 3–16 years), and 148 completed at least 1 follow up (range: 1-11 visits, 3-42 months). The 100m (time and % predicted) and 10 meter walk (10m) were completed at each study visit. The 100m and 10m were significantly better at baseline in boys exposed to steroids compared to steroid-naïve (P<0.01 and P<0.05 respectively) and boys initiating steroids at <4.5 years of age during our study demonstrated the largest improvement within the first 6 months post-initiation. Test-retest reliability was 0.95 and minimal detectable change using the standard error of measure was 4.5 seconds. In our cohort, a threshold of 39% predicted was optimal for predicting LOA. Predicting prognosis in new patients based on genetic results alone can be problematic. Exploratory analysis of our 100m data revealed 2 distinct phenotypic severity clusters (based on 100m time, age, height, and weight). The clusters suggest that 100m time greater than 73.6 seconds at any age defines a more severe phenotype. Clustering based on 100m speed has the potential to more stringently characterize disease severity leading to more accurate clinical counseling, as well as refined enrollment and interpretation of change in clinical trials. The 100m is reliable, responsive to change, and useful in predicting functional loss in dystrophinopathy.