scholarly journals Meta-analysis of the strength of exploratory suicide prediction models; from clinicians to computers

BJPsych Open ◽  
2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Michelle Corke ◽  
Katherine Mullin ◽  
Helena Angel-Scott ◽  
Shelley Xia ◽  
Matthew Large
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Odds Ratio ◽  
Suicide Risk ◽  
Prediction Models ◽  
Meta Analysis ◽  
Random Effect ◽  
Clinical Judgement ◽  
Suicide Prediction ◽  
Suicide Risk Factors

Background Suicide prediction models have been formulated in a variety of ways and are heterogeneous in the strength of their predictions. Machine learning has been a proposed as a way of improving suicide predictions by incorporating more suicide risk factors. Aims To determine whether machine learning and the number of suicide risk factors included in suicide prediction models are associated with the strength of the resulting predictions. Method Random-effect meta-analysis of exploratory suicide prediction models constructed by combining two or more suicide risk factors or using clinical judgement (Prospero Registration CRD42017059665). Studies were located by searching for papers indexed in PubMed before 15 August 2020 with the term suicid* in the title. Results In total, 86 papers reported 102 suicide prediction models and included 20 210 411 people and 106 902 suicides. The pooled odds ratio was 7.7 (95% CI 6.7–8.8) with high between-study heterogeneity (I2 = 99.5). Machine learning was associated with a non-significantly higher odds ratio of 11.6 (95% CI 6.0–22.3) and clinical judgement with a non-significantly lower odds ratio of 4.7 (95% CI 2.1–10.9). Models including a larger number of suicide risk factors had a higher odds ratio when machine-learning studies were included (P = 0.02). Among non-machine-learning studies, suicide prediction models including fewer risk factors performed just as well as those including more risk factors. Conclusions Machine learning might have the potential to improve the performance of suicide prediction models by increasing the number of included suicide risk factors but its superiority over other methods is unproven.

scholarly journals Summarising and synthesising regression coefficients through systematic review and meta-analysis for improving hypertension prediction using metamodelling: protocol

BMJ Open ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. e036388
Author(s):  
Mohammad Ziaul Islam Chowdhury ◽  
Iffat Naeem ◽  
Hude Quan ◽  
Alexander A Leung ◽  
Khokan C Sikdar ◽  
...  
Keyword(s):  
Risk Factors ◽  
Systematic Review ◽  
Risk Prediction ◽  
Prediction Models ◽  
Assessment Tool ◽  
Meta Analysis ◽  
Grey Literature ◽  
Random Effect ◽  
Regression Coefficients ◽  
Risk Prediction Models

IntroductionHypertension is one of the most common medical conditions and represents a major risk factor for heart attack, stroke, kidney disease and mortality. The risk of progression to hypertension depends on several factors, and combining these risk factors into a multivariable model for risk stratification would help to identify high-risk individuals who should be targeted for healthy behavioural changes and/or medical treatment to prevent the development of hypertension. The risk prediction models can be further improved in terms of accuracy by using a metamodel updating technique where existing hypertension prediction models can be updated by combining information available in existing models with new data. A systematic review and meta-analysis will be performed of hypertension prediction models in order to identify known risk factors for high blood pressure and to summarise the magnitude of their association with hypertension.Methods and analysisMEDLINE, Embase, Web of Science, Scopus and grey literature will be systematically searched for studies predicting the risk of hypertension among the general population. The search will be based on two key concepts: hypertension and risk prediction. The summary statistics from the individual studies will be the regression coefficients of the hypertension risk prediction models, and random-effect meta-analysis will be used to obtain pooled estimates. Heterogeneity and publication bias will be assessed, along with study quality, which will be assessed using the Prediction Model Risk of Bias Assessment Tool checklist.Ethics and disseminationEthics approval is not required for this systematic review and meta-analysis. We plan to disseminate the results of our review through journal publications and presentations at applicable platforms.

scholarly journals FAKTOR IBU, JANIN DAN RIWAYAT PENYAKIT SEBAGAI RISIKO PREEKLAMPSIA DI ASIA DAN AFRIKA: SUATU META-ANALISIS

2020 ◽  
Vol 10 (2) ◽  
pp. 127-139
Author(s):  
Miranda Ayunani ◽  
Annisa Nurrachmawati ◽  
Rahmi Susanti
Keyword(s):  
Risk Factors ◽  
Family History ◽  
Odds Ratio ◽  
Meta Analysis ◽  
Random Effect ◽  
Biomed Central ◽  
Chronic Hypertension ◽  
Maternal Factors ◽  
History Of ◽  
Review Manager

Abstract Background: Preeclampsia accounts for nearly 10 percent of maternal deaths in Asia and Africa. Therefore, it is important to detect signs and symptoms early on by knowing the factors that are at risk for a mother experiencing preeclampsia. Objective: To determine the risk factors for preeclampsia in Asia and Africa through the application of meta-analysis. Method: A systematic review was carried out on 26 case-control and cohort studies related to risk factors for preeclampsia from four databases (PubMed, BioMed Central, ProQuest, and Google Scholar). The pooled odds ratio was calculated with the fixed-effect and random-effect model using Review Manager 5.3. Result: A total of 20 studies consisting of 2,954,769 women were included in the meta-analysis. Risk factors for preeclampsia based on maternal factors were chronic hypertension=9.74(95% CI 1.69-56.04), gestational diabetes=9.28(95% CI 4, 49-19.19), pre-pregnancy body mass index=2.70(95% CI 2.08-3.50), maternal age during pregnancy=2.37(95% CI 2.29-2.46) and nulliparity=2.08(95% CI 1.44-3.01). The fetal factor was multiple pregnancy=4.24(95% CI 3.14-5.73). Four disease history factors were family history of preeclampsia=13.99(95% CI 6.91-28.33), history of chronic hypertension=8.28(95% CI 5.92- 11.59), history of preeclampsia=OR 6.90(95% CI 3.58-13.31) and family history of hypertension=2.81(95% CI 1.75-4.50). Conclusion: The results of a meta-analysis of 10 risk factors for preeclampsia could be used as a screening tool to determine the magnitude of risk and early diagnosis of preeclampsia that allows timely intervention. Key words: Maternal Factors, Chronic Hypertension, Preeclampsia, Meta-Analysis. Abstrak Latar belakang: Preeklampsia menyumbang hampir 10 persen dari kematian ibu di Asia dan Afrika. Oleh karena itu, penting untuk menemukan tanda dan gejala sejak dini dengan mengetahui faktor-faktor yang berisiko untuk seorang ibu mengalami preeklampsia. Tujuan: Mengetahui faktor risiko preeklampsia di Asia dan Afrika melalui penerapan meta-analisis. Metode: Tinjauan sistematis dilakukan pada 26 studi kasus kontrol dan kohort terkait faktor risiko preeklampsia di empat database, yaitu PubMed, BioMed Central, ProQuest, dan Google Scholar. Pooled Odds Ratio dihitung dengan model fixed-effect dan random effect menggunakan Review Manager 5.3. Hasil: Sebanyak 20 penelitian yang terdiri dari 2.954.769 wanita masuk dalam meta-analisis. Faktor risiko preeklampsia berdasarkan faktor ibu adalah hipertensi kronis=9,74(95% CI 1,69-56,04), diabetes gestasional=9,28(95% CI 4,49-19,19), indeks massa tubuh prakehamilan=2,70(95% CI 2,08-3,50), usia ibu saat kehamilan=2,37(95% CI 2,29-2,46) dan nuliparitas=2,08 (95% CI 1,44-3,01). Faktor janin yaitu kehamilan multipel=4,24(95% CI 3,14-5,73). Empat faktor riwayat penyakit yaitu riwayat keluarga preeklampsia=13,99(95% CI 6,91-28,33), riwayat hipertensi kronis=8,28(95% CI 5,92-11,59), riwayat preeklampsia= (95% CI 3,58-13,31) dan riwayat keluarga hipertensi=2,81(95% CI 1,75-4,50). Kesimpulan: Hasil meta-analisis dari 10 faktor risiko preeklampsia dapat digunakan sebagai alat skrining untuk mengetahui besarnya risiko dan diagnosis dini preeklampsia, yang memungkinkan intervensi tepat waktu.   Kata kunci: Faktor Ibu, Hipertensi Kronis, Preeklampsia, Meta-analisis

scholarly journals Prevalence and risk factors for antibiotic utilization in Chinese children

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Shasha Guo ◽  
Qiang Sun ◽  
Xinyang Zhao ◽  
Liyan Shen ◽  
Xuemei Zhen
Keyword(s):  
Risk Factors ◽  
Meta Analysis ◽  
Random Effect ◽  
Random Effect Model ◽  
Healthcare Research ◽  
Chinese Children ◽  
Rural Setting ◽  
Antibiotic Prescribing ◽  
Antibiotic Utilization ◽  
At Home

Abstract Background Antibiotic resistance poses a significant threat to public health globally. Irrational utilization of antibiotics being one of the main reasons of antibiotic resistant. Children as a special group, there's more chance of getting infected. Although most of the infection is viral in etiology, antibiotics still are the most frequently prescribed medications for children. Therefore, high use of antibiotics among children raises concern about the appropriateness of antibiotic prescribing. This systematic review aims to measuring prevalence and risk factors for antibiotic utilization in children in China. Methods English and Chinese databases were searched to identify relevant studies evaluating the prevalence and risk factors for antibiotic utilization in Chinese children (0-18 years), which were published between 2010 and July 2020. A Meta-analysis of prevalence was performed using random effect model. The Agency for Healthcare Research and Quality (AHRQ) and modified Jadad score was used to assess risk of bias of studies. In addition, we explored the risk factors of antibiotic utilization in Chinese children using qualitative analysis. Results Of 10,075 studies identified, 98 eligible studies were included after excluded duplicated studies. A total of 79 studies reported prevalence and 42 studies reported risk factors for antibiotic utilization in children. The overall prevalence of antibiotic utilization among outpatients and inpatients were 63.8% (35 studies, 95% confidence interval (CI): 55.1-72.4%), and 81.3% (41 studies, 95% CI: 77.3-85.2%), respectively. In addition, the overall prevalence of caregiver’s self-medicating of antibiotics for children at home was 37.8% (4 studies, 95% CI: 7.9-67.6%). The high prevalence of antibiotics was associated with multiple factors, while lacking of skills and knowledge in both physicians and caregivers was the most recognized risk factor, caregivers put pressure on physicians to get antibiotics and self-medicating with antibiotics at home for children also were the main factors attributed to this issue. Conclusion The prevalence of antibiotic utilization in Chinese children is heavy both in hospitals and home. It is important for government to develop more effective strategies to improve the irrational use of antibiotic, especially in rural setting.

Sign in / Sign up

Export Citation Format

Share Document