RESUMEN
Background: Extracorporeal shockwave therapy (ESWT) is a noninvasive treatment modality that is used in the treatment of chronic Achilles tendinopathy (AT). Purposes: To (1) retrospectively assess outcomes after ESWT for both noninsertional AT (NAT) and insertional AT (IAT) at >1-year follow-up and (2) identify potential predictors of outcomes. Study Design: Cohort study; Level of evidence, 3. Methods: Chart review was conducted to identify patients who underwent ESWT for AT with a minimum of 1-year follow-up. Data collected and assessed included patient demographic characteristics, pathological characteristics including the location of AT (NAT or IAT), presence of a Haglund deformity, and severity of tendon degeneration on magnetic resonance imaging (MRI), in addition to treatment characteristics including number of sessions and intensity of ESWT. The Victorian Institute of Sports Assessment-Achilles (VISA-A) and visual analog scale (VAS) pain scores were obtained before ESWT, 6 months after ESWT, and at final follow-up. Failures were also recorded, which were defined as no improvement in VISA-A or VAS scores or need for surgical intervention. Linear regression was performed to identify potential predictors of inferior subjective clinical outcomes and failures. Survival analysis was conducted using Kaplan-Meier curves. Results: The study included 52 patients with IAT and 34 patients with NAT. The mean follow-up in the NAT cohort was 22.3 ± 10.2 months and the mean follow-up in the IAT cohort was 26.8 ± 15.8 months. Improvements in VISA-A and VAS scores were observed in the NAT cohort at 6-month follow-up and at final follow-up (P < .05). Improvements in VISA-A and VAS scores were recorded in the IAT cohort at 6-month follow-up, which subsequently deteriorated at final follow-up. In the NAT cohort, the failure rate at 6-month follow-up was 11.8%, which increased to 29.4% at final follow-up. In the IAT cohort, the failure rate at 6-month follow-up was 32.7%, which increased to 59.6% at final follow-up. Predictors of inferior subjective clinical outcomes and failures in the NAT cohort included pre-ESWT subjective clinical score, male sex, presence of a cardiovascular risk factor, and more severe MRI grading of tendinopathy. Predictors of inferior subjective clinical outcomes and failures in the IAT cohort included pre-ESWT subjective clinical score and more severe MRI grading of tendinopathy. Conclusion: Superior subjective clinical outcomes together with a lower failure rate were maintained for >1 year in the NAT cohort compared with the IAT cohort, calling into question the long-term benefit of ESWT for patients with IAT.
RESUMEN
Background: Different machine learning (ML) technologies have been applied in healthcare systems with diverse applications. We aimed to determine the model feasibility and accuracy of predicting patient portal use among diabetic patients by using six different ML algorithms. In addition, we also compared model performance accuracy with the use of only essential variables. Methods: This was a single-center retrospective observational study. From March 1, 2019 to February 28, 2020, we included all diabetic patients from the study emergency department (ED). The primary outcome was the status of patient portal use. A total of 18 variables consisting of patient sociodemographic characteristics, ED and clinic information, and patient medical conditions were included to predict patient portal use. Six ML algorithms (logistic regression, random forest (RF), deep forest, decision tree, multilayer perception, and support vector machine) were used for such predictions. During the initial step, ML predictions were performed with all variables. Then, the essential variables were chosen via feature selection. Patient portal use predictions were repeated with only essential variables. The performance accuracies (overall accuracy, sensitivity, specificity, and area under receiver operating characteristic curve (AUC)) of patient portal predictions were compared. Results: A total of 77,977 unique patients were placed in our final analysis. Among them, 23.4% (18,223) patients were diabetic mellitus (DM). Patient portal use was found in 26.9% of DM patients. Overall, the accuracy of predicting patient portal use was above 80% among five out of six ML algorithms. The RF outperformed the others when all variables were used for patient portal predictions (accuracy 0.9876, sensitivity 0.9454, specificity 0.9969, and AUC 0.9712). When only eight essential variables were chosen, RF still outperformed the others (accuracy 0.9876, sensitivity 0.9374, specificity 0.9932, and AUC 0.9769). Conclusion: It is possible to predict patient portal use outcomes when different ML algorithms are used with fair performance accuracy. However, with similar prediction accuracies, the use of feature selection techniques can improve the interpretability of the model by addressing the most relevant features.
RESUMEN
INTRODUCTION: COVID19 has raised concerns for resource allocation across various sectors of healthcare. At the frontlines, emergency departments are required to triage a wide range of acuity and non-specific symptomology. METHODS: This retrospective study aimed to pave the way for more concrete detection and triage of patients by analyzing symptomology, physical findings, diagnostic testing and relevant hospital course of the 458 suspected cases that initially presented to an academic level one trauma center emergency department between March and August 2020. A total of 202 COVID positive cases were analyzed. RESULTS: The most common symptoms were cough (70.63%), fatigue (77%), and shortness of breath (59%). There was a significantly higher percentage of abnormal chest imaging in inpatient groups compared to the ED discharge group (42.86% vs 79%, p < 0.01). Laboratory studies, especially markers of inflammation (CRP, ESR), markers of tissue damage (lactic acid, troponin), and markers of infection were markedly higher and above normal reference ranges in complicated cases (p < 0.01). While there is limited data on the sensitivity and specificity of the current nasopharyngeal PCR test, there was no permutation of symptoms, physical findings, diagnostic testing that was more sensitive than that of the current PCR test calculated at 66.1% in our cohort. CONCLUSION: Laboratory studies that otherwise are more commonly conducted inpatient, including markers of inflammation, tissue damage, and infection, may be useful in disposition planning of ED patients in conjunction with clinical correlation of presentation and chest imaging.
Asunto(s)
COVID-19/complicaciones , COVID-19/diagnóstico , Servicio de Urgencia en Hospital , Adulto , Anciano , Biomarcadores/metabolismo , Proteína C-Reactiva/metabolismo , COVID-19/metabolismo , Prueba de COVID-19 , Femenino , Pruebas Hematológicas , Humanos , Masculino , Persona de Mediana Edad , New York , Estudios Retrospectivos , Sensibilidad y Especificidad , Evaluación de Síntomas , TriajeRESUMEN
Changes in the function and microbiome of the upper and lower gastrointestinal tract have been documented in Parkinson's disease (PD), although most studies have examined merely fecal microbiome profiles and patients with advanced disease states. In the present study we sought to identify sensitive and specific biomarkers of changes in the oral microbiome of early stage PD through shotgun metatranscriptomic profiling. We recruited 48 PD subjects and 36 age- and gender-matched healthy controls. Subjects completed detailed assessments of motor, cognitive, balance, autonomic and chemosensory (smell and taste) functions to determine their disease stage. We also obtained a saliva sample for profiling of microbial RNA and host mRNA using next generation sequencing. We found no differences in overall alpha and beta diversity between subject groups. However, changes in specific microbial taxa were observed, including primarily bacteria, but also yeast and phage. Nearly half of our findings were consistent with prior studies in the field obtained through profiling of fecal samples, with others representing highly novel candidates for detection of early stage PD. Testing of the diagnostic utility of the microbiome data revealed potentially robust performance with as few as 11 taxonomic features achieving a cross-validated area under the ROC curve of 0.90 and overall accuracy of 84.5%. Bioinformatic analysis of 167 different metabolic pathways supported shifts in a small set of distinct pathways involved in amino acid and energy metabolism among the organisms comprising the oral microbiome. In parallel with the microbial analysis, we also examined the evidence for changes in human salivary mRNAs in the same subjects. This revealed significant changes in a set of 9 host mRNAs, several of which mapped to various brain functions and showed correlations with some of the significantly changed microbial taxa. Unexpectedly, we also observed robust correlations between many of the microbiota and functional measures, including those reflecting cognition, balance, and disease duration. These results suggest that the oral microbiome may represent a highly-accessible and informative microenvironment that offers new insights in the pathophysiology of early stage PD.