-
Human Reproduction Open 2023What is the present performance of artificial intelligence (AI) decision support during embryo selection compared to the standard embryo selection by embryologists?
STUDY QUESTION
What is the present performance of artificial intelligence (AI) decision support during embryo selection compared to the standard embryo selection by embryologists?
SUMMARY ANSWER
AI consistently outperformed the clinical teams in all the studies focused on embryo morphology and clinical outcome prediction during embryo selection assessment.
WHAT IS KNOWN ALREADY
The ART success rate is ∼30%, with a worrying trend of increasing female age correlating with considerably worse results. As such, there have been ongoing efforts to address this low success rate through the development of new technologies. With the advent of AI, there is potential for machine learning to be applied in such a manner that areas limited by human subjectivity, such as embryo selection, can be enhanced through increased objectivity. Given the potential of AI to improve IVF success rates, it remains crucial to review the performance between AI and embryologists during embryo selection.
STUDY DESIGN SIZE DURATION
The search was done across PubMed, EMBASE, Ovid Medline, and IEEE Xplore from 1 June 2005 up to and including 7 January 2022. Included articles were also restricted to those written in English. Search terms utilized across all databases for the study were: ('Artificial intelligence' OR 'Machine Learning' OR 'Deep learning' OR 'Neural network') AND ('IVF' OR ' fertili*' OR 'assisted reproductive techn*' OR 'embryo'), where the character '*' refers the search engine to include any auto completion of the search term.
PARTICIPANTS/MATERIALS SETTING METHODS
A literature search was conducted for literature relating to AI applications to IVF. Primary outcomes of interest were accuracy, sensitivity, and specificity of the embryo morphology grade assessments and the likelihood of clinical outcomes, such as clinical pregnancy after IVF treatments. Risk of bias was assessed using the Modified Down and Black Checklist.
MAIN RESULTS AND THE ROLE OF CHANCE
Twenty articles were included in this review. There was no specific embryo assessment day across the studies-Day 1 until Day 5/6 of embryo development was investigated. The types of input for training AI algorithms were images and time-lapse (10/20), clinical information (6/20), and both images and clinical information (4/20). Each AI model demonstrated promise when compared to an embryologist's visual assessment. On average, the models predicted the likelihood of successful clinical pregnancy with greater accuracy than clinical embryologists, signifying greater reliability when compared to human prediction. The AI models performed at a median accuracy of 75.5% (range 59-94%) on predicting embryo morphology grade. The correct prediction (Ground Truth) was defined through the use of embryo images according to post embryologists' assessment following local respective guidelines. Using blind test datasets, the embryologists' accuracy prediction was 65.4% (range 47-75%) with the same ground truth provided by the original local respective assessment. Similarly, AI models had a median accuracy of 77.8% (range 68-90%) in predicting clinical pregnancy through the use of patient clinical treatment information compared to 64% (range 58-76%) when performed by embryologists. When both images/time-lapse and clinical information inputs were combined, the median accuracy by the AI models was higher at 81.5% (range 67-98%), while clinical embryologists had a median accuracy of 51% (range 43-59%).
LIMITATIONS REASONS FOR CAUTION
The findings of this review are based on studies that have not been prospectively evaluated in a clinical setting. Additionally, a fair comparison of all the studies were deemed unfeasible owing to the heterogeneity of the studies, development of the AI models, database employed and the study design and quality.
WIDER IMPLICATIONS OF THE FINDINGS
AI provides considerable promise to the IVF field and embryo selection. However, there needs to be a shift in developers' perception of the clinical outcome from successful implantation towards ongoing pregnancy or live birth. Additionally, existing models focus on locally generated databases and many lack external validation.
STUDY FUNDING/COMPETING INTERESTS
This study was funded by Monash Data Future Institute. All authors have no conflicts of interest to declare.
REGISTRATION NUMBER
CRD42021256333.
PubMed: 37588797
DOI: 10.1093/hropen/hoad031 -
European Journal of Medical Research Aug 2023A high maternal death rate is a result of maternal delays in seeking emergency obstetric care, particularly in countries with limited resources like Ethiopia. Utilizing... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
A high maternal death rate is a result of maternal delays in seeking emergency obstetric care, particularly in countries with limited resources like Ethiopia. Utilizing maternity waiting homes is a strategy to overcome geographical barriers and improve maternal and neonatal health outcomes. Pregnant women must intend to use this service in addition to it being available. Therefore, the goal of this study was to assess pregnant women's intentions to use maternity waiting homes and associated characteristics.
METHODS
PubMed, Google Scholar, Scopus, Science Direct, and online institutional repository homes were searched. Data were extracted using Microsoft Excel and analyzed using STATA statistical software (v. 14). Publication bias was checked by forest plot, Begg's, and Egger's tests. To look for heterogeneity, I was computed, and an overall estimated analysis was carried out. Subgroup analysis was done by study region, sample size, and publication. The pooled odds ratio for associated factors was also computed.
RESULTS
Out of 258 articles assessed, 8 studies with 4111 study participants met the criteria and were included in this study. The pooled prevalence of intention to use maternity waiting home was 52.25% (95% CI 45.88-58.66), I = 93.8%). Amhara region had a higher intention to use maternal waiting for home prevalence (63.5%), per subgroup analysis. In studies with sample sizes higher than 5000, the usage of maternity waiting homes was less prevalent (45.2%). Between published research (52.9%) and unpublished studies (51.3%), there was no appreciable difference in the intention to use a maternity waiting home. Experience of maternity waiting home (AOR = 3.337; 95% CI 2.038-5.463), direct subjective norm (AOR = 2.763; 95% CI 1.395-5.471), and direct perceived behavioral control (AOR = 23.147; 95% CI 2.341-4.231).
CONCLUSION
In Ethiopia, the intention to use maternity waiting was low. There was an intentional variation in to use of maternity waiting homes across regions of Ethiopia. Improving behavioral perception through intervention programs such as antenatal education should have been strengthened.
Topics: Infant, Newborn; Female; Pregnancy; Humans; Pregnant Women; Intention; Ethiopia
PubMed: 37550705
DOI: 10.1186/s40001-023-01248-7 -
Nursing Ethics Jul 2023Ethical climate refers to the shared perception of ethical norms and sets the scope for what is ethical and acceptable behaviour within teams. (Review)
Review
BACKGROUND
Ethical climate refers to the shared perception of ethical norms and sets the scope for what is ethical and acceptable behaviour within teams.
AIM
This paper sought to explore perceptions of ethical climate amongst healthcare workers as measured by the Ethical Climate Questionnaire (ECQ), the Hospital Ethical Climate Survey (HECS) and the Ethics Environment Questionnaire (EEQ).
METHODS
A systematic review and meta-analysis was utilised. PSYCINFO, CINAHL, WEB OF SCIENCE, MEDLINE and EMBASE were searched, and papers were included if they sampled healthcare workers and used the ECQ, HECS or EEQ.
ETHICAL CONSIDERATION
Ethical approval was not required.
RESULTS
The search returned 1020 results. After screening, 61 papers were included ( = 43 HECS, = 15 ECQ, = 3 EEQ). The overall sample size was over 17,000. The pooled mean score for the HECS was 3.60. Mean scores of individual studies ranged from 2.97 to 4.5. For the HECS studies, meta-regression was carried out. No relationship was found between the country of the studies, the study setting (ICU v non-ICU settings) or the mean years of experience that the sample had. For the ECQ, sub-scales had mean scores ranging from 3.41 (instrumental) to 4.34 (law) and were all observed to have significant and substantial heterogeneity. Three studies utilised the EEQ so further analysis was not carried out.
CONCLUSIONS
The above results provide insight into the variability of scores as measured by the HECS, ECQ and EEQ. To some extent, this variability is not surprising with studies carried out across 21 countries and in a range of healthcare systems. Results also suggest that it may be that more local and context specific factors are more important when it comes to predicting ethical climate.
PubMed: 37459590
DOI: 10.1177/09697330231177419 -
Frontiers in Pediatrics 2023The aim of this systematic review is to evaluate the perception of the patient, the chairside time, and the reliability and/or reproducibility of intraoral scanners for... (Review)
Review
PURPOSE
The aim of this systematic review is to evaluate the perception of the patient, the chairside time, and the reliability and/or reproducibility of intraoral scanners for full arch in pediatric patients.
METHODS
A data search was performed in four databases (Medline-Pubmed, Scopus, ProQuest and Web of Science) in accordance with the PRISMA 2020 statements. Studies were classified in three categories (patient perception, scanning or impression time and reliability and/or reproducibility). The resources, the data extraction and the quality assessment were carried out independently by two operators. The variables recorded were population characteristics, material and methods aspects and included country, study design and main conclusion. A quality assessment of the selected studies was performed with QUADAS-2 tool, and Kappa-Cohen Index was calculated to analyze examiner agreement.
RESULTS
The initial search obtained 681 publications, and finally four studies matching inclusion criteria were selected. The distribution of the studies in the categories was three for the analysis of the patient's perception and scanning or impression time; and two items to assess the reliability and/or reproducibility of intraoral scans. All included studies have a repeated measures-transversal design. The sample size ranged between 26 and 59 children with a mean age. The intraoral scanners evaluated were Lava C.O.S, Cerec Omnicam, TRIOS Classic, TRIOS 3-Cart and TRIOS Ortho. The quality assessment of the studies using QUADAS-2 tool revealed a low risk of bias while evaluating patient perception, but an unclear risk of bias in the analysis of accuracy or chairside time. In relation to the applicability concerns, the patient selection was of high risk of bias. All studies agreed that the patient perception and comfort is better with intraoral scanners in comparison with the conventional method. The accuracy or reliability of the digital procedure is not clear, being clinically acceptable. In relation with the chairside time, it depends on the intraoral scanner, with contradictory data in the different analyzed studies.
CONCLUSION
The use of intraoral scanners in children is a favorable option, finding a significantly higher patient perception and comfort with intraoral scanners compared to the conventional impression method. The evidence for reliability or reproducibility is not strong to date, however, the differences between the intraoral measurements and the digital models would be clinically acceptable.
PubMed: 37435173
DOI: 10.3389/fped.2023.1213072 -
Health and Quality of Life Outcomes Jun 2023The aims of this study were (1) to synthesize evidence of the general health-related quality of life in children with DCD compared to their typically developing peers,... (Review)
Review
The aims of this study were (1) to synthesize evidence of the general health-related quality of life in children with DCD compared to their typically developing peers, and (2) to verify which domains of HRQOL are more compromised in children with DCD. A systematic search was carried out to identify cross-sectional studies that evaluated self-perception and/or the parent's perception of the HRQOL in children with and without DCD as an outcome. The methodological quality of the studies was assessed, and the effect size calculated. Initial searches in the databases identified 1092 articles. Of these, six were included. Most of the articles (5/6) included noted that children with DCD show a significantly lower HRQOL than their typically developing peers. Regarding the most compromised HRQOL domains, the results are heterogeneous. Most studies (3/6) had moderate methodological quality, and two studies were classified as high methodological quality. Effect sizes ranged from low to high.
Topics: Humans; Child; Cross-Sectional Studies; Motor Skills Disorders; Quality of Life; Databases, Factual; Peer Group
PubMed: 37386629
DOI: 10.1186/s12955-023-02146-6 -
Journal of Parkinson's Disease 2023Stigma is an important social attitude affecting the quality of life (QoL) of people with Parkinson's disease (PwP, PD) as individuals within society.
BACKGROUND
Stigma is an important social attitude affecting the quality of life (QoL) of people with Parkinson's disease (PwP, PD) as individuals within society.
OBJECTIVE
This systematic review aimed to 1) identify the factors associated with stigma in PD and 2) demonstrate culture-based diversity in the stigmatization of PwP. We also reported data from the Turkish PwP, which is an underrepresented population.
METHODS
Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement, a literature search of the PubMed/Medline electronic database was performed covering the last 26 years. Articles on self-perceived stigma in PD with a sample size > 20 and quantitative results were included. Data were extracted by independent reviewers.
RESULTS
After screening 163 articles, 57 were eligible for review, most of which were from Europe or Asia. Only two studies have been conducted in South America. No study from Africa was found. Among the 61 factors associated with stigma, disease duration, sex, and age were most frequently studied. A comparison of the investigated factors across the world showed that, while the effect of motor impairment or treatment on stigma seems to be culture-free, the impact of sex, education, marriage, employment, cognitive impairment, and anxiety on stigma may depend on culture.
CONCLUSION
The majority of the world's PD population is underrepresented or unrepresented, and culture may influence the perception of stigma in PwP. More diverse data are urgently needed to understand and relieve the challenges of PwP within their society.
Topics: Humans; Parkinson Disease; Quality of Life; Cross-Cultural Comparison; Europe; Cognitive Dysfunction
PubMed: 37355913
DOI: 10.3233/JPD-230050 -
Nutrition Reviews Feb 2024Food labelling is a global strategy recommended to reduce noncommunicable diseases. Few reviews, however, have focused on food label use in sub-Saharan Africa (SSA). (Meta-Analysis)
Meta-Analysis
CONTEXT
Food labelling is a global strategy recommended to reduce noncommunicable diseases. Few reviews, however, have focused on food label use in sub-Saharan Africa (SSA).
OBJECTIVE
To determine the prevalence of food label use and describe determinants of food label use and purchasing decisions of adult consumers in SSA.
DATA SOURCE
PubMed (Medline), Web of Science, Cochrane Central, and Google Scholar databases.
DATA EXTRACTION
Search criteria included adults (aged ≥18 years), conducted in SSA, focusing on food label use or understanding and their determinants or determinants of food-purchasing decisions, and articles published in English.
STUDY QUALITY AND DATA ANALYSIS
Risk-of-bias assessment of included studies was done using the Joann Briggs Institute checklist for prevalence studies. Publication bias was assessed using funnel plots and Egger's test. Analysis included narrative synthesis and moderator and meta-analyses of food label use.
RESULTS
A total of 124 articles were found, of which 21 were included in the review. Of participants in the selected studies, 58% were female. About 80% reported food label use (either used sometimes or always) (70%-88%) (I2 = 97%; n = 6223), and regular use was estimated at 36% (28%-45%) (I2 = 97%; n = 5147). Food label use was influenced by level of income, education, employment status, and household size. Food-purchasing decisions were influenced by attributes such as expiry dates, price, and taste. Major recommendations reported were tailored education campaigns and reducing barriers to food label use.
CONCLUSION
Most (80%) of adults in SSA reported using food labels; however, only about one-third used them consistently. Demographic and situation factors determined patterns in food label use, whereas product attributes influenced food purchasing decisions. Complexity of these determinants requires adopting tailored, multisectoral, theory-driven programs to improve food label use.
SYSTEMATIC REVIEW REGISTRATION
Open Science Framework (https://osf.io/kc562).
Topics: Adult; Humans; Female; Adolescent; Male; Prevalence; Comprehension; Africa South of the Sahara; Food; Taste Perception
PubMed: 37330669
DOI: 10.1093/nutrit/nuad064 -
Systematic Reviews Jun 2023Shade determination is a critical step for the fabrication of a satisfactory restoration. Visual shade selection with conventional shade guides is subjective and... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Shade determination is a critical step for the fabrication of a satisfactory restoration. Visual shade selection with conventional shade guides is subjective and influenced by variables related to light, observer, and object. Shade selection devices have been introduced to provide subjective and quantitative shade values. This systematic review and meta-analysis aimed to compare the color difference for shade selection with visual and instrumental methods.
METHODS
An initial search was conducted on databases (MEDLINE via PubMed, Scopus, and Web of Science) in addition to a manual search through references of identified articles. Studies comparing the accuracy of visual and instrumental shade selection based on ΔΕ were included in data synthesis. Mean differences (MDs) and 95% confidence intervals (CIs) were calculated to estimate the effect size for global and subgroup meta-analysis using the inverse variance weighted method and random-effects model (P ˂ 0.05). Results were presented as forest plots.
RESULTS
The authors identified 1776 articles from the initial search. Seven in vivo studies were included in the qualitative analysis of which six studies were included in the meta-analysis. For the global meta-analysis, the pooled mean (95% CI) was - 1.10 (- 1.92, - 0.27). Test for overall effect showed that instrumental methods were significantly more accurate than visual methods with significantly less ΔΕ (P = 0.009). Test for subgroup difference showed that the type of instrumental shade selection method used had a significant effect on accuracy (P ˂ 0.001). Instrumental methods including spectrophotometer, digital camera, and smartphone showed significantly better accuracy compared with visual shade selection (P ˂ 0.05). The greatest mean difference was found between the smartphone and visual method with a mean (95% CI) of - 2.98 (- 3.37, - 2.59) with P ˂ 0.001 followed by digital camera and spectrophotometer. There was no significant difference in accuracy between IOS and visual shade selection (P = 1.00).
CONCLUSIONS
Instrumental shade selection with a spectrophotometer, digital camera, and smartphone showed significantly better shade matching compared with a conventional shade guide, whereas IOS did not improve the shade matching significantly compared with shade guides.
REVIEW REGISTRATION
PROSPERO CRD42022356545.
Topics: Humans; Color Perception; Prosthesis Coloring; Color; Spectrophotometry; Research Design
PubMed: 37291652
DOI: 10.1186/s13643-023-02263-9 -
German Medical Science : GMS E-journal 2023Damage to the central nervous system can occur in adulthood, for example, due to stroke, trauma, tumours, or chronic diseases. After damage to the central nervous... (Review)
Review
BACKGROUND
Damage to the central nervous system can occur in adulthood, for example, due to stroke, trauma, tumours, or chronic diseases. After damage to the central nervous system, cognitive impairments occur in addition to physical limitations. Occupational therapy is most often prescribed for neurological diagnoses, including stroke and traumatic brain injury.
METHODS
The health technology assessment (HTA) report this HTA article is based on investigates the clinical effectiveness, cost-effectiveness, and patient-related, social and ethical aspects of occupational therapy for patients with cognitive impairments compared to no occupational therapy. In addition, the effects of different occupational therapy interventions with and without cognitive components were compared in an explorative overview. Patients with moderate or severe dementia are excluded from the assessment. Systematic overviews, that is, systematic reviews of systematic reviews, were conducted.
RESULTS
For the evaluation of clinical effectiveness, a total of nine systematic reviews were included. No systematic review was identified for the assessment of costs or cost-effectiveness. Five systematic reviews were included for the assessment of patient and social aspects. For the assessment of clinical effectiveness compared with no occupational therapy, five systematic reviews comprising 20 randomised controlled trials with a total of 1,316 subjects reported small positive effects for the outcomes "global cognitive function" and "activities of daily living" as well as a non-quantified positive effect on the outcomes "health-related quality of life" and "behavioural control". No effect was found for individual components of cognition and measures of perception. The quality of the evidence for all outcomes is low due to a high risk of bias. In the supplementary presentations, no positive effects could be demonstrated on the basis of the available evidence. The quality of this evidence was not assessed. For the assessment of patient and social aspects, five systematic reviews on patients with a stroke or a traumatic brain injury - without specification regarding cognitive deficits or studies with their relatives - were included. It was reported that patients and family caregivers go through different phases of rehabilitation in which the discharge home is a decisive turning point. The discharge home represents a crucial breaking point. Regaining an active, self-determining role is a process that requires therapists to find the right level of support for patients and relatives. For the assessment of ethical aspects, nine documents were included. We identified ethical problem-solving models for occupational therapy and 16 ethical aspects in occupational therapy for cognitive deficits. The central theme of the analysis is the limited autonomy due to the consequences of the disease as well as the resulting tensions with those treating the patient.
CONCLUSIONS
Based on this systematic overview, it can neither be proven nor excluded with certainty that occupational therapy for cognitive impairment is an effective therapy for adult patients with central nervous system injuries compared to no occupational therapy. There is a lack of randomised trials with sufficient sample size, well-defined interventions, and comparable concomitant therapies in the control groups, but there is also a lack of well-designed observational studies in routine care and health economic studies. The identified systematic reviews on patient and social aspects provide information on the needs of patients after stroke or traumatic brain injury and their relatives, but there is a lack of studies on this aspect in German-speaking countries. For the ethical assessment, in addition to the identified theoretical models for solving ethical conflicts in occupational therapy, more empirical studies on ethical aspects with patients with cognitive deficits and their relatives as well as occupational therapists are needed.
Topics: Adult; Humans; Brain Injuries, Traumatic; Cognitive Dysfunction; Quality of Life; Stroke; Systematic Reviews as Topic
PubMed: 37260919
DOI: 10.3205/000316 -
Frontiers in Neuroscience 2023Neuroimaging studies have identified aberrant activity patterns in multiple brain regions in functional dyspepsia (FD) patients. However, due to the differences in study...
BACKGROUND
Neuroimaging studies have identified aberrant activity patterns in multiple brain regions in functional dyspepsia (FD) patients. However, due to the differences in study design, these previous findings are inconsistent, and the underlying neuropathological characteristics of FD remain unclear.
METHODS
Eight databases were systematically searched for literature from inception to October 2022 with the keywords "Functional dyspepsia" and "Neuroimaging." Thereafter, the anisotropic effect size signed the differential mapping (AES-SDM) approach that was applied to meta-analyze the aberrant brain activity pattern of FD patients.
RESULTS
A total of 11 articles with 260 FD patients and 202 healthy controls (HCs) were included. The AES-SDM meta-analysis demonstrated that FD patients manifested increased activity in the bilateral insula, left anterior cingulate gyrus, bilateral thalamus, right precentral gyrus, left supplementary motor area, right putamen, and left rectus gyrus and decreased functional activity in the right cerebellum compared to the HCs. Sensitivity analysis showed that all these above regions were highly reproducible, and no significant publication bias was detected.
CONCLUSION
The current study demonstrated that FD patients had significantly abnormal activity patterns in several brain regions involved in visceral sensation perception, pain modulation, and emotion regulation, which provided an integrated insight into the neuropathological characteristics of FD.
PubMed: 37250423
DOI: 10.3389/fnins.2023.1174287