Study retention prediction with AI
Ontology highlight
ABSTRACT: Introduction
Openness, conscientiousness, extroversion, agreeableness and neuroticism are dimensional personality traits known as the Big Five. Study attrition is a common but often hard to anticipate problem. Artificial intelligence (AI) could examine both fronts to mitigate the unpredictability of the latter. Objectives
To investigate whether AI could predict study attrition employing personality traits scores. Methods
Data from 2,697 questionnaires were analysed using an AI. The short form of the International Personality Item Pool was used to assess the Big Five personality traits on the first of three planned waves. The personality traits scores were employed to predict the missing of at least one wave. Overall attrition was 17.6%. The AI was conservatively tuned to minimize the negative likelihood ratio when confronting predicted and real attrition. The free and open source programming language R was used for all the analyses. Dataset source: Hansson, Isabelle; Berg, Anne Ingeborg; Thorvaldsson, Valgeir (2018), “Can personality predict longitudinal study attrition? Evidence from a population-based sample of older adults”, Mendeley Data, V1, doi: 10.17632/g3jx8zt2t9.1 Results
Predictions obtained a negative likelihood ratio of 0.333 and a negative predictive value of 0.933. The results were indicative of fair performance. Conclusions
AI might be useful to predict study retention. Furthermore, the results of this study might indicate a moderate effect of the Big Five on the probability of study retention. Finally, the AI used in this study is freely available, allowing anyone to experiment. Disclosure
No significant relationships.
SUBMITTER: Mereu A
PROVIDER: S-EPMC9471583 | biostudies-literature | 2021 Aug
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:A re-analysis of published data-dependent acquisition glycoproteomics datasets to demonstrate relative retention time prediction on glycopeptide identification and disambiguation of adduct states.
2020-04-01 | PXD018208 | Pride
Project description:VS94 gene expression at different time-points in SAPI medium in absence and presence of AI-2 was studied. Autoinducer-2 (AI-2) is produced by many species of bacteria, including various commensal bacteria and is involved in inter-species communication. Since, pathogens encounter AI-2 once they enter the human gastro-intestinal tract; we studied the effects of presence of AI-2 on various phenotypes associated with infection and colonization of enterohemorrhagic Escherichia coli (EHEC) namely, chemotaxis, motility and attachment to HeLa cells. AI-2 attracted EHEC when observed in agarose plug assays and also increased EHEC motility by 1.44-fold. AI-2 also increased EHEC attachment to HeLa cells by 1.6-fold; hence, suggesting that exposure to AI-2 inside the gastro-intestinal tract can play an important role in EHEC colonization. We then investigated the global effects of AI-2 on EHEC gene expression using DNA microarrays at various time-points. We found that AI-2 controls virulence gene expression and several other groups of genes (flagellar genes, iron related genes, biofilm genes etc.) associated with virulence in a time-dependent manner. Hence, through these studies we have shown that AI-2 may be a key component in EHEC infection of human gastro-intestinal tract. Keywords: Time course
2008-03-21 | GSE9388 | GEO
Project description:Background: Fatal coronary heart disease (FCHD) affects ~650,000 people yearly in the US. Electrocardiographic artificial intelligence (ECG-AI) models can predict adverse coronary events, yet their application to FCHD is understudied. Objectives: The study aimed to develop ECG-AI models predicting FCHD risk from ECGs. Methods (Retrospective): Data from 10 s 12-lead ECGs and demographic/clinical data from University of Tennessee Health Science Center (UTHSC) were used for model development. Of this dataset, 80% was used for training and 20% as holdout. Data from Atrium Health Wake Forest Baptist (AHWFB) were used for external validation. We developed two separate convolutional neural network models using 12-lead and Lead I ECGs as inputs, and time-dependent Cox proportional hazard models using demographic/clinical data with ECG-AI outputs. Correlation of the predictions from the 12- and 1-lead ECG-AI models was assessed. Results: The UTHSC cohort included data from 50,132 patients with a mean age (SD) of 62.50 (14.80) years, of whom 53.4% were males and 48.5% African American. The AHWFB cohort included data from 2305 patients with a mean age (SD) of 63.04 (16.89) years, of whom 51.0% were males and 18.8% African American. The 12-lead and Lead I ECG-AI models resulted in validation AUCs of 0.84 and 0.85, respectively. The best overall model was the Cox model using simple demographics with Lead I ECG-AI output (D1-ECG-AI-Cox), with the following results: AUC = 0.87 (0.85-0.89), accuracy = 83%, sensitivity = 69%, specificity = 89%, negative predicted value (NPV) = 92% and positive predicted value (PPV) = 55% on the AHWFB validation cohort. For this, the 2-year FCHD risk prediction accuracy was AUC = 0.91 (0.90-0.92). The 12-lead versus Lead I ECG FCHD risk prediction showed strong correlation (R = 0.74). Conclusions: The 2-year FCHD risk can be predicted with high accuracy from single-lead ECGs, further improving when combined with demographic information.
| S-EPMC11678222 | biostudies-literature
Project description:Introduction The dark triad is composed by the personality traits Machiavellianism, narcissism and psychopathy (MNP). Their complexity can make them difficult to interrelate. Artificial intelligence (AI) could help in this endeavour. Objectives To investigate whether AI could predict MNP from themselves. Methods Data from 210 questionnaires were analysed using an AI. The short Dark Triad questionnaire (SD3) was used to assess MNP. Two of the MNP scores were employed to predict the third one and the procedure was repeated for all of them alternatively. The AI was conservatively tuned to maximize the one-way random intraclass correlation coefficient (ICC) between predicted and real values. Pearson’s r was calculated too. The free and open source programming language R was used for all the analyses. Dataset source: Borráz-León, Javier I. (2020), “Dark triad, attractiveness, mate value, and sexual partners”, Mendeley Data, V1, doi: 10.17632/87vx6jfnrp.1 Results Machiavellianism, narcissism and psychopathy predictions obtained ICC of 0.593, 0.335, 0.505 and Pearson’s r of 0.608, 0.346, 0.548 respectively. The results were indicative of fair performance, mainly for Machiavellianism and psychopathy. Conclusions AI might be useful to predict MNP. This could be utile in many situations, such as dealing with missing data or deciding whether to formally test someone. Finally, the AI used in this study is freely available, allowing anyone to experiment. Disclosure No significant relationships.
| S-EPMC9471593 | biostudies-literature
Project description:Introduction SSRI-treated psychiatric disorders (STPD), such as general anxiety disorder and major depression disorder, are common psychiatric diagnoses. Serotonin-mediated effects of solar insolation are an active topic of research. Artificial intelligence (AI) could help to better examine that complex relation. Objectives To investigate whether AI could predict the STPD relying primarily on average ambient temperature and annual solar insolation. Methods Data of age, average ambient temperature and annual solar insolation were employed to predict STPD status in 7,587 subjects using an AI. To simplify the data analysis, only individuals with white ethnicity were assessed. SPTD prevalence was 17.1%. The AI was conservatively tuned to maximize the positive likelihood ratio considering predicted and real STPD statuses. The free and open source programming language R was used for all the analyses. Dataset source: Wortzel, Joshua; Kent, Shia; Avery, David; Al-Hamdan, Mohammad; Turner, Brandon; Norden, Justin; Norden, Michael; Haynor, David (2018), “Data for: Ambient temperature and solar insolation are associated with decreased prevalence of SSRI-treated psychiatric disorders”, Mendeley Data, V1, doi: 10.17632/trs43ybh92.1 Results Predictions obtained a positive likelihood ratio of 4.850. The results were indicative of fair performance. Conclusions AI might be useful to predict STPD. Furthermore, the results of this study might indicate a moderate effect of age, average ambient temperature and annual solar insolation on the probability of STPD occurrence. Finally, the AI used in this study is freely available, allowing anyone to experiment.
| S-EPMC9475708 | biostudies-literature
Project description:Introduction Openness, conscientiousness, extroversion, agreeableness and neuroticism are known as the Big Five personality traits (BFPT). They are theoretical building blocks of the personality and comprise wide and interconnected spectra. Artificial intelligence (AI) could help to grasp their complexity. Objectives To investigate whether AI could predict the BFPT from themselves. Methods Data from 2,697 questionnaires were analysed using an AI. The short form of the International Personality Item Pool was used to assess the BFPT. Four of the BFPT scores were employed to predict the fifth one and the procedure was repeated for all of them alternatively. The AI was conservatively tuned to maximize the one-way random intraclass correlation coefficient (ICC) between predicted and real values. Their Pearson’s r was calculated too. The free and open source programming language R was used for all the analyses. Dataset source: Hansson, Isabelle; Berg, Anne Ingeborg; Thorvaldsson, Valgeir (2018), “Can personality predict longitudinal study attrition? Evidence from a population-based sample of older adults”, Mendeley Data, V1, doi: 10.17632/g3jx8zt2t9.1 Results Openness, conscientiousness, extroversion, agreeableness and neuroticism predictions obtained ICC of 0.219, 0.146, 0.306, 0.354, 0.121 and Pearson’s r of 0.254, 0.149, 0.393, 0.446, 0.122 respectively. The results for extroversion and agreeableness were indicative of fair performance. Conclusions AI might be useful to predict personality traits, mainly extroversion and agreeableness. This could be utile in many situations, such as dealing with missing data or deciding whether to formally test someone. Finally, the AI used in this study is freely available, allowing anyone to experiment.
| S-EPMC9475767 | biostudies-literature
Project description:Drug-induced liver injury (DILI) is a common reason for the withdrawal of a drug from the market. Early assessment of DILI risk is an essential part of drug development, but it is rendered challenging prior to clinical trials by the complex factors that give rise to liver damage. Artificial intelligence (AI) approaches, particularly those building on machine learning, range from random forests to more recent techniques such as deep learning, and provide tools that can analyze chemical compounds and accurately predict some of their properties based purely on their structure. This article reviews existing AI approaches to predicting DILI and elaborates on the challenges that arise from the as yet limited availability of data. Future directions are discussed focusing on rich data modalities, such as 3D spheroids, and the slow but steady increase in drugs annotated with DILI risk labels.
| S-EPMC8080874 | biostudies-literature
Project description:Non-experts have long made important contributions to machine learning (ML) by contributing training data, and recent work has shown that non-experts can also help with feature engineering by suggesting novel predictive features. However, non-experts have only contributed features to prediction tasks already posed by experienced ML practitioners. Here we study how non-experts can design prediction tasks themselves, what types of tasks non-experts will design, and whether predictive models can be automatically trained on data sourced for their tasks. We use a crowdsourcing platform where non-experts design predictive tasks that are then categorized and ranked by the crowd. Crowdsourced data are collected for top-ranked tasks and predictive models are then trained and evaluated automatically using those data. We show that individuals without ML experience can collectively construct useful datasets and that predictive models can be learned on these datasets, but challenges remain. The prediction tasks designed by non-experts covered a broad range of domains, from politics and current events to health behavior, demographics, and more. Proper instructions are crucial for non-experts, so we also conducted a randomized trial to understand how different instructions may influence the types of prediction tasks being proposed. In general, understanding better how non-experts can contribute to ML can further leverage advances in Automatic machine learning and has important implications as ML continues to drive workplace automation.
| S-EPMC7924542 | biostudies-literature
Project description:The retention behavior in supercritical fluid chromatography (SFC) remains a complex and poorly understood phenomenon despite the development of various models to explain retention mechanisms. This study aims to deepen the understanding of retention by investigating three distinct stationary phases: high-strength silica octadecyl (HSS C18 SB), charged surface hybrid pentafluorophenyl (CSH PFP), and porous graphitic carbon (PGC) as a nonsilica-based phase. Three mobile phase compositions, i.e., CO2/methanol, CO2/methanol +10 mmol/L NH3, and CO2/methanol +2% H2O, were investigated using an extensive set of analytes characterized by over 200 molecular descriptors. Artificial neural networks were employed to analyze the influence of these descriptors on retention behavior, revealing the most significant molecular features that increase or decrease retention on each column with the three different mobile phases. This complex evaluation of the large set of experimental data enabled to link specific analyte properties to retention interactions in SFC, including the interaction of analytes with partial positive charge with silanol groups on the HSS C18 SB column when using methanol + H2O as the organic modifier. The flexibility of the alkyl chain in the HSS C18 SB column is also affected by the composition of the organic modifier, which alters retention mechanisms, especially when NH3 is used as an additive. This highlights the critical role of the mobile phase composition in modulating the behavior of nonpolar stationary phases. Completely different interaction mechanisms were observed for the PGC column when comparing methanol with and without additives, suggesting possible modifications to the planar structure and surface polarizability of the PGC phase. Statistical evaluation of data collected over a year of column usage demonstrated distinct long-term retention stability trends. The HSS C18 SB column exhibited the greatest stability with methanol + H2O, whereas significant retention decreases were observed with methanol + NH3 modifier, particularly for CSH PFP and, unexpectedly, also for PGC. These findings provide crucial insights into the long-term retention behavior and aging of SFC columns, with practical implications for optimizing SFC conditions and improving column lifetime.
| S-EPMC11800175 | biostudies-literature
Project description:Liquid Chromatography Time-of-Flight Mass Spectrometry (LC-TOF-MS) is widely used for profiling metabolite compounds. LC-TOF-MS is a chemical analysis technique that combines the physical separation capabilities of high-pressure liquid chromatography (HPLC) with the mass analysis capabilities of Time-of-Flight Mass Spectrometry (TOF-MS) which utilizes the difference in the flight time of ions due to difference in the mass-to-charge ratio. Since metabolite compounds have various chemical characteristics, their precise identification is a crucial problem of metabolomics research. Contemporaneously analyzed reference standards are commonly required for mass spectral matching and retention time matching, but there are far fewer reference standards than there are compounds in the organism. We therefore developed a retention time prediction method for HPLC to improve the accuracy of identification of metabolite compounds. This method uses a combination of Support Vector Regression and Multiple Linear Regression adaptively to the measured retention time. We achieved a strong correlation (correlation coefficient = 0.974) between measured and predicted retention times for our experimental data. We also demonstrated a successful identification of an E. coli metabolite compound that cannot be identified by precise mass alone.
| S-EPMC3055703 | biostudies-literature