RESUMEN
OBJECTIVES: Summarise the evidence of the performance of the machine learning algorithm in discriminating sacroiliitis features on MRI and compare it with the accuracy of human physicians. METHODS: MEDLINE, EMBASE, CIHNAL, Web of Science, IEEE, American College of Rheumatology and European Alliance of Associations for Rheumatology abstract archives were searched for studies published between 2008 and 4 June 2023. Two authors independently screened and extracted the variables, and the results are presented using tables and forest plots. RESULTS: Ten studies were selected from 2381. Over half of the studies used deep learning models, using Assessment of Spondyloarthritis International Society sacroiliitis criteria as the ground truth, and manually extracted the regions of interest. All studies reported the area under the curve as a performance index, ranging from 0.76 to 0.99. Sensitivity and specificity were the second-most commonly reported indices, with sensitivity ranging from 0.56 to 1.00 and specificity ranging from 0.67 to 1.00; these results are comparable to a radiologist's sensitivity of 0.67-1.00 and specificity of 0.78-1.00 in the same cohort. More than half of the studies showed a high risk of bias in the analysis domain of quality appraisal owing to the small sample size or overfitting issues. CONCLUSION: The performance of machine learning algorithms in discriminating sacroiliitis features on MRI varied owing to the high heterogeneity between studies and the small sample sizes, overfitting, and under-reporting issues of individual studies. Further well-designed and transparent studies are required.
Asunto(s)
Sacroileítis , Espondiloartritis , Humanos , Sacroileítis/diagnóstico por imagen , Imagen por Resonancia Magnética , Espondiloartritis/diagnóstico por imagen , Sensibilidad y Especificidad , Aprendizaje AutomáticoRESUMEN
The optimal timing of enteral nutrition (EN) in sepsis patients is controversial among societal guidelines. We aimed to evaluate the evidence of early EN's impact on critically ill sepsis patients' clinical outcomes. We searched the MEDLINE, Embase, CINAHL, Cochrane Library, ClinicalTrials.gov, and ICTRP databases on 10 March 2023. We included studies published after 2004 that compared early EN versus delayed EN in sepsis patients. We included randomized controlled trials (RCTs), non-RCTs, cohort studies, and case-control studies. Forest plots were used to summarize risk ratios (RRs), including mortality and mean difference (MD) of continuous variables such as intensive care unit (ICU) length of stay and ventilator-free days. We identified 11 eligible studies with sample sizes ranging from 31 to 2410. The RR of short-term mortality from three RCTs was insignificant, and the MD of ICU length of stay from two RCTs was -2.91 and -1.00 days (95% confidence interval [CI], -5.53 to -0.29 and -1.68 to -0.32). Although the RR of intestinal-related complications from one RCT was 3.82 (95% CI, 1.43 to 10.19), indicating a significantly higher risk for the early EN group than the control group, intestinal-related complications of EN reported in five studies were inconclusive. This systematic review did not find significant benefits of early EN on mortality in sepsis patients. Evidence, however, is weak due to inconsistent definitions, heterogeneity, risk of bias, and poor methodology in the existing studies.
Asunto(s)
Nutrición Enteral , Sepsis , Humanos , Nutrición Enteral/métodos , Enfermedad Crítica/terapia , Unidades de Cuidados Intensivos , Sepsis/terapia , Estudios de Casos y Controles , Tiempo de InternaciónRESUMEN
BACKGROUND: Exacerbation of inflammatory bowel disease (IBD) is common. Identification of the exacerbating factors could facilitate interventions for forecastable environmental factors through adjustment of the patient's daily routine. We assessed the effect of natural environmental factors on the exacerbation of IBD. METHODS: In this systematic review and meta-analysis, studies published from January 1, 1992 to November 3th, 2022 were searched in the MEDLINE, Embase, CINAHL Complete and Cochrane Library databases. We extracted data related to the impact of environmental variations on IBD exacerbation, and performed a meta-analysis of the individual studies' correlation coefficient χ2 converted into Cramér's V (φc) with 95% confidence intervals (CI). RESULTS: A total of 7,346 publications were searched, and 20 studies (sample size 248-84,000 cases) were selected. A meta-analysis with seven studies was performed, and the pooled estimate of the correlation (φc) between the seasonal variations and IBD exacerbations among 4806 cases of IBD exacerbation was 0.11 (95% CI 0.07-0.14; I2 = 39%; p = 0.13). When divided into subtypes of IBD, the pooled estimate of φc in ulcerative colitis (six studies, n = 2649) was 0.07 (95% CI 0.03-0.11; I2 = 3%; p = 0.40) and in Crohn's disease (three studies, n = 1597) was 0.12 (95% CI 0.07-0.18; I2 = 18%; p = 0.30). CONCLUSION: There was a significant correlation between IBD exacerbation and seasonal variations, however, it was difficult to synthesize pooled results of other environmental indicators due to the small number of studies and the various types of reported outcome measures. For clinical implications, additional evidence through well-designed follow-up studies is needed. PROTOCOL REGISTRATION NUMBER (PROSPERO): CRD42022304916.
Asunto(s)
Colitis Ulcerosa , Enfermedad de Crohn , Enfermedades Inflamatorias del Intestino , Humanos , Estaciones del Año , Temperatura , Enfermedades Inflamatorias del Intestino/epidemiología , Enfermedad de Crohn/epidemiologíaRESUMEN
BACKGROUND: According to DSM-5 criteria, Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by deficiencies in social communication and interaction along with the presence of restrictive and repetitive patterns of behavior. Few studies have explored the prevalence of behavioral addiction in individuals with ASD. Since addiction and ASD share common characteristics, individuals with ASD may be more vulnerable to addictive behaviors. Some typical behavioral addictions include internet, gaming, and gambling addiction. While most previous studies on ASD and addiction have looked at chemical addiction, behavioral addiction has not been thoroughly studied to date. AIMS: The objective of this study was to investigate the presence of behavioral addiction among individuals diagnosed with autism spectrum disorder. METHODS AND PROCEDURES: A systematic literature search of five databases was conducted in accordance with the PRISMA guidelines. Search results were reviewed for the predetermined inclusion criteria independently by two authors. OUTCOMES AND RESULTS: The search yielded 539 publications after the removal of duplicates. 61 met the inclusion criteria for title and abstract review. Full texts were reviewed resulting in an additional 31 being removed. The remaining 30 included 4 case reports and 26 original studies. Results included 27 studies that found a positive correlation (15 of significance, 12 of unknown significance) between a behavioral addiction and either ASD or Autistic traits, 1 found a significant negative correlation, 3 did not find a correlation. CONCLUSIONS AND IMPLICATIONS: This review is inconclusive about links between ASD and behavioral addictions. While a vast majority of studies show a positive correlation, many do not provide the statistical analysis to show if the correlations are significant. In addition, a positive correlation between ASD and behavioral addiction is observed in the presence of comorbid mental health conditions in many of the studies. Further research with proper controls and statistical analysis is needed to determine whether the development of behavioral addiction is directly influenced by ASD or if the presence of a comorbid mental health condition is the true cause.
Asunto(s)
Trastorno del Espectro Autista , Conducta Adictiva , Trastorno del Espectro Autista/epidemiología , Conducta Adictiva/epidemiología , Comunicación , Manual Diagnóstico y Estadístico de los Trastornos Mentales , Humanos , PrevalenciaRESUMEN
OBJECTIVE: The current study was performed to assess the evidence for effects of therapeutic intervention with mobile device applications (apps) for individuals with autism spectrum disorder (ASD). DESIGN: The main methodology of the current study was systematic review with meta-analysis. SETTING: Only randomised controlled trials (RCTs) for mobile device apps for individuals with ASD were considered for review in the current study. PATIENTS: The target population was individuals clinically diagnosed with ASD. INTERVENTIONS: Applications that are operable on a smart (mobile) device and interactive with users. MAIN OUTCOME MEASURES: The main outcomes were based on standardised mean differences in pretrial and post-trial scales in each control and intervention group. RESULTS: Out of a total of 1100 studies (after duplicate removal), 7 RCTs were selected for final analysis. Of the seven studies, two RCTs were further analysed for effects based on the visual and fine motor subscales of the Mullen Scales of Early Learning, which favoured the intervention groups (standardised mean difference (SMD)=0.41, 95% CI 0.03 to 0.80; SMD=0.41, 95% CI 0.03 to 0.80), without either having any heterogeneity (p>0.1) or publication bias. CONCLUSIONS: Although it is still early to draw a conclusion, available studies are showing promise for use of mobile device apps for treatment of individuals with ASD. More well-designed and large-scale studies focused on improving behavioural symptoms of ASD are warranted. PROSPERO REGISTRATION NUMBER: CRD42019128362.
Asunto(s)
Trastorno del Espectro Autista/terapia , Aplicaciones Móviles , Humanos , Ensayos Clínicos Controlados Aleatorios como Asunto , Resultado del TratamientoRESUMEN
BACKGROUND: In the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, their application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder (ASD). However, given their complexity and potential clinical implications, there is an ongoing need for further research on their accuracy. OBJECTIVE: This study aimed to perform a systematic review and meta-analysis to summarize the available evidence for the accuracy of machine learning algorithms in diagnosing ASD. METHODS: The following databases were searched on November 28, 2018: MEDLINE, EMBASE, CINAHL Complete (with Open Dissertations), PsycINFO, and Institute of Electrical and Electronics Engineers Xplore Digital Library. Studies that used a machine learning algorithm partially or fully for distinguishing individuals with ASD from control subjects and provided accuracy measures were included in our analysis. The bivariate random effects model was applied to the pooled data in a meta-analysis. A subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false-negative, and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw Summary Receiver Operating Characteristics curves, and obtain the area under the curve (AUC) and partial AUC (pAUC). RESULTS: A total of 43 studies were included for the final analysis, of which a meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural magnetic resonance imaging (sMRI) subgroup meta-analysis (12 samples with 1776 participants) showed a sensitivity of 0.83 (95% CI 0.76-0.89), a specificity of 0.84 (95% CI 0.74-0.91), and AUC/pAUC of 0.90/0.83. A functional magnetic resonance imaging/deep neural network subgroup meta-analysis (5 samples with 1345 participants) showed a sensitivity of 0.69 (95% CI 0.62-0.75), specificity of 0.66 (95% CI 0.61-0.70), and AUC/pAUC of 0.71/0.67. CONCLUSIONS: The accuracy of machine learning algorithms for diagnosis of ASD was considered acceptable by few accuracy measures only in cases of sMRI use; however, given the many limitations indicated in our study, further well-designed studies are warranted to extend the potential use of machine learning algorithms to clinical settings. TRIAL REGISTRATION: PROSPERO CRD42018117779; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=117779.
RESUMEN
AIM: To assess the accuracy of the Childhood Autism Rating Scale (CARS) through systematic review and meta-analysis. METHOD: Studies that provided quantitative values for the reliability and validity for all versions of CARS were searched through MEDLINE, CINAHL, PsycINFO, Embase, and OpenDissertations. RESULTS: A total of 24 studies with 4433 participants were included in our analysis. Meta-analysis showed that the summary Cronbach's alpha regarding a team of physicians and psychologists or others subgroup, derived from six studies (952 participants), was considered to be acceptable at 0.90 (95% confidence interval, 0.87-0.92) with moderate heterogeneity. Analysis of two 'low risk of bias' studies on the criterion validity for CARS with a cut-off of 30 and DSM-IV resulted in sensitivity of 0.86 and 0.71 and specificity of 0.79 and 0.75. INTERPRETATION: Through the results of the current systematic review and meta-analysis, the internal consistency can be considered to be acceptable for a team of physicians and psychologists or others subgroup. In terms of the criterion validity, the sensitivity was thought to be acceptable although the specificity was not, suggesting that CARS should be used along with other confirmatory tools. WHAT THIS PAPER ADDS: The Childhood Autism Rating Scale can be considered as a supplementary diagnostic tool for autism spectrum disorder.
EXACTITUD DE LA ESCALA DE CALIFICACIÓN DE AUTISMO INFANTIL (CARS): UNA REVISIÓN SISTEMÁTICA Y METAANÁLISIS: OBJETIVO: Se evalúa la exactitud de la Escala de Calificación de Autismo Infantil (CARS) a través de revisión sistemática y metaanálisis. MÉTODO: Los estudios que proporcionaron valores cuantitativos para la confiabilidad y validez de todas las versiones de CARS fueron buscados a través de MEDLINE, CINAHL, PsycINFO, Embase y Open Dissertations. RESULTADOS: En nuestro análisis se incluyeron un total de 24 estudios con 4433 participantes. El metaanálisis mostró el resumen del alfa de Cronbach basado en datos de equipos de médicos y psicólogos u otros subgrupos, derivado de seis estudios (952 participantes), fue considerado aceptable en 0,90 (intervalo de confianza del 95%, 0,87 - 0,92) con moderada heterogeneidad. El análisis de dos estudios de «bajo riesgo de sesgo¼ sobre los criterios de validez para CARS con un corte de 30 y criterios de DSM-IV, mostró una sensibilidad de 0,86 y 0,71 y especificidad de 0,79 y 0,75. INTERPRETACIÓN: Los resultados de la revisión sistemática actual y el metaanálisis demostró que la consistencia interna de CARS puede considerarse aceptable cuando es utilizado por equipos de médicos y psicólogos u otros subgrupos. En cuanto a la validez de criterio, se considero que la sensibilidad era aceptable, aunque la especificidad no lo es, sugiriendo que CARS debería utilizarse junto con otras herramientas confirmatorias.
ACURÁCIA DA ESCALA DE PONTUAÇÃO DO AUTISMO NA INFÂNCIA (CHILDHOOD AUTISM RATING SCALE -CARS): UMA REVISÃO SISTEMÁTICA E METANÁLISE: OBJETIVO: Avaliar a acurácia da Escala de Pontuação do Autismo na Infância (Childhood Autism Rating Scale -CARS) por meio de revisão sistemática e metanálise. MÉTODO: Estudos que forneceram valores de confiabilidade e validade de todas as versões da CARS foram pesquisados por meio das bases MEDLINE, CINAHL, PsycINFO, Embase, e OpenDissertations. RESULTADOS: Um total de 24 estudos com 4433 participantes foram incluídos em nossa análise. A metanálise mostrou que o resumo do alfa de Cronbach para uma equipe de médicos e psicólogos ou outros subgrupos, derivado de seis estudos (952 participantes), foi considerado aceitável a 0,90 (intervalo de confiança a 95%, 0,87-0,92) com heterogeneidade moderada. Análise de dois estudos com "baixo risco de viés" sobre a validade de critério da CARS com valor de corte de 30 e DSM-IV resultou em sensibilidade de 0,86 e 0,71 e especificidade de 0,79 and 0,75. INTERPRETAÇÃO: Por meio dos resultados da presente revisão sistemática e metanálise, a consistência interna pode ser considerada aceitável para uma equipe de médicos e psicólogos ou outros subgrupos. Em termos de validade de critério, a sensibilidade foi considerada aceitável, embora a especificidade não tenha sido, sugerindo que a CARS deva ser usada juntamente com outros instrumentos confirmatórios.
Asunto(s)
Trastorno del Espectro Autista/diagnóstico , Trastorno Autístico/diagnóstico , Niño , Humanos , Escalas de Valoración Psiquiátrica , Psicometría , Sensibilidad y EspecificidadRESUMEN
This article performs a systemic review of psychometric properties of Internet Addiction Test (IAT)-the most widely used tool for assessing Internet addiction in clinic and research field. Studies measuring psychometric properties of IAT (original version) were searched through MEDLINE, The Cumulative Index to Nursing and Allied Health Literature (CINAHL), PsycINFO, and Embase. A total of 25 studies including 18,421 subjects were reviewed in our study. Based on meta-analysis for internal consistency, the pooled Cronbach's alpha coefficient from college/university students with a single department subgroup was 0.90 (95percent confidence interval [CI], 0.89-0.91), and that from middle-/high-school students (older than 15 years) subgroup was 0.93 (95 percent CI, 0.92-0.93). According to test-retest analysis, the pooled Spearman's correlation coefficient from college/university students with a single department subgroup was high at 0.83 (95 percent CI, 0.81-0.85), along with low publication bias. Convergent validity showed correlation coefficients of 0.62-0.84, as compared with major tools. For construct validity, the number of factors is believed to be 1-2, only considering studies that followed the guidelines. IAT appears to have acceptable internal consistency, test-retest reliability, and convergent validity in specific groups. To verify these values, well-designed evidence-based studies assessing psychometric properties of IAT across diverse populations are warranted.
Asunto(s)
Conducta Adictiva , Internet/estadística & datos numéricos , Psicometría , Adolescente , Adulto , Conducta Adictiva/epidemiología , Conducta Adictiva/psicología , Humanos , Reproducibilidad de los Resultados , Instituciones Académicas , Estudiantes/psicología , Estudiantes/estadística & datos numéricos , Encuestas y Cuestionarios , Adulto JovenRESUMEN
[This corrects the article DOI: 10.1371/journal.pone.0187139.].
RESUMEN
BACKGROUND: This systematic review examined the reliability and validity of the Morisky Medication Adherence Scale-8 (MMAS-8), which has been widely used to assess patient medication adherence in clinical research and medical practice. METHODS: Of 418 studies identified through searching 4 electronic databases, we finally analyzed 28 studies meeting the selection criteria of this study regarding the reliability and validity of MMAS-8 including sensitivity and specificity. Meta-analysis for Cronbach's α, intraclass correlation coefficient (ICC), sensitivity and specificity to detect a patient with nonadherence to medication were performed. The pooled estimates for Cronbach's α and ICC were calculated using the random-effects weighted T transformation. A bivariate random-effects model was used to estimate pooled sensitivity and specificity. FINDINGS: The pooled Cronbach's α estimate for type 2 diabetes group in 7 studies and osteoporosis group in 3 studies were 0.67 (95% Confidence Interval(CI), 0.65 to 0.69) and 0.77 (95% CI, 0.72 to 0.83), respectively. With regard to test-retest, the pooled ICC for type 2 diabetes group in 3 studies and osteoporosis group in 2 studies were 0.81 (95% CI, 0.75 to 0.85) and 0.80 (95% CI, 0.74 to 0.85). For a cut-off value of 6, the pooled sensitivity and specificity in 12 studies were 0.43 (95% CI, 0.33 to 0.53) and 0.73 (95% CI, 0.68 to 0.78), respectively. CONCLUSIONS: The MMAS-8 had acceptable internal consistency and reproducibility in a few diseases like type 2 diabetes. Using the cut-off value of 6, criterion validity was not enough good to validly screen a patient with nonadherence to medication. However, this study did not calculated a pooled estimate for criterion validity using the higher values than 6 as a cut-off value since most of included individual studies did not report criterion validity based on those values.