-
The Lancet. Digital Health Dec 2023Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease... (Meta-Analysis)
Meta-Analysis
Machine learning and deep learning predictive models for long-term prognosis in patients with chronic obstructive pulmonary disease: a systematic review and meta-analysis.
BACKGROUND
Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease (COPD). We aimed to summarise the performance of such prognostic models for COPD, compare their relative performances, and identify key research gaps.
METHODS
We conducted a systematic review and meta-analysis to compare the performance of machine learning and deep learning prognostic models and identify pathways for future research. We searched PubMed, Embase, the Cochrane Library, ProQuest, Scopus, and Web of Science from database inception to April 6, 2023, for studies in English using machine learning or deep learning to predict patient outcomes at least 6 months after initial clinical presentation in those with COPD. We included studies comprising human adults aged 18-90 years and allowed for any input modalities. We reported area under the receiver operator characteristic curve (AUC) with 95% CI for predictions of mortality, exacerbation, and decline in forced expiratory volume in 1 s (FEV). We reported the degree of interstudy heterogeneity using Cochran's Q test (significant heterogeneity was defined as p≤0·10 or I>50%). Reporting quality was assessed using the TRIPOD checklist and a risk-of-bias assessment was done using the PROBAST checklist. This study was registered with PROSPERO (CRD42022323052).
FINDINGS
We identified 3620 studies in the initial search. 18 studies were eligible, and, of these, 12 used conventional machine learning and six used deep learning models. Seven models analysed exacerbation risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·69-0·85]) and there was significant heterogeneity (I 97%, p<0·0001). 11 models analysed mortality risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·74-0·80]) with significant degrees of heterogeneity (I 60%, p=0·027). Two studies assessed decline in lung function and were unable to be pooled. Machine learning and deep learning models did not show significant improvement over pre-existing disease severity scores in predicting exacerbations (p=0·24). Three studies directly compared machine learning models against pre-existing severity scores for predicting mortality and pooled performance did not differ (p=0·57). Of the five studies that performed external validation, performance was worse than or equal to regression models. Incorrect handling of missing data, not reporting model uncertainty, and use of datasets that were too small relative to the number of predictive features included provided the largest risks of bias.
INTERPRETATION
There is limited evidence that conventional machine learning and deep learning prognostic models demonstrate superior performance to pre-existing disease severity scores. More rigorous adherence to reporting guidelines would reduce the risk of bias in future studies and aid study reproducibility.
FUNDING
None.
Topics: Adult; Humans; Reproducibility of Results; Deep Learning; Quality of Life; Pulmonary Disease, Chronic Obstructive; Prognosis
PubMed: 38000872
DOI: 10.1016/S2589-7500(23)00177-2 -
Environmental Science and Pollution... Jul 2021Lead (Pb) is one of the most toxic and abundant elements in the earth's crust, which is pointed out that the intoxication caused by it may damage biological systems.... (Meta-Analysis)
Meta-Analysis Review
Lead (Pb) is one of the most toxic and abundant elements in the earth's crust, which is pointed out that the intoxication caused by it may damage biological systems. This systematic review with meta-analysis aimed to evaluate the association between Pb exposure and neurological damage. This work was executed according to PRISMA guidelines, and seven online databases were consulted. Based on the PECO strategy, studies presenting humans as participants (populations) exposed to Pb (exposure) compared to non-exposed to Pb (control) evaluating the neurological impairment (outcome) were included. The quality and risk of bias were verified by Fowkes and Fulton checklist. Two meta-analyses were conducted considering Digit Symbol and Profile Mood tests. The certainty of the evidence was evaluated with the GRADE tool. This review identified 2019 studies, of which 12 were eligible according to the inclusion criteria. Eight were considered with a low risk of bias. All the studies elected showed that exposure to Pb is associated with neurological damage, but the meta-analysis did not show any difference for the evaluated tests, and the certainty of the evidence was considered very low. Nevertheless, the included studies showed that Pb occupational exposure is associated with neurological damage, and the main parameters evaluated for possible neurological damage were related to mnemonic aspects, reaction time, intelligence, attention disorders, and mood changes. Thus, our results revealed that a definitive demonstration of an association of Pb and neurological changes in humans is still a pending issue. Future studies should take into consideration more confident methods to answer this question.
Topics: Humans; Lead; Occupational Exposure
PubMed: 34046839
DOI: 10.1007/s11356-021-13536-y -
The Lancet. Digital Health Mar 2023Digital health interventions are effective for hypertension self-management, but a comparison of the effectiveness and implementation of the different modes of... (Meta-Analysis)
Meta-Analysis
Effectiveness, reach, uptake, and feasibility of digital health interventions for adults with hypertension: a systematic review and meta-analysis of randomised controlled trials.
BACKGROUND
Digital health interventions are effective for hypertension self-management, but a comparison of the effectiveness and implementation of the different modes of interventions is not currently available. This study aimed to compare the effectiveness of SMS, smartphone application, and website interventions on improving blood pressure in adults with hypertension, and to report on their reach, uptake, and feasibility.
METHODS
In this systematic review and meta-analysis we searched CINAHL Complete, Cochrane Central Register of Controlled Trials, Ovid Embase, Ovid MEDLINE, and APA PsycInfo on May 25, 2022, for randomised controlled trials (RCTs) published in English from Jan 1, 2009, that examined the effectiveness of digital health interventions on reducing blood pressure in adults with hypertension. Screening was carried out using Covidence, and data were extracted following Cochrane's guidelines. The primary endpoint was change in the mean of systolic blood pressure. Risk of bias was assessed with Cochrane Risk of Bias 2. Data on systolic and diastolic blood pressure reduction were synthesised in a meta-analysis, and data on reach, uptake and feasibility were summarised narratively. Grading of Recommendations, Assessment, Development, and Evaluation criteria were used to evaluate the level of evidence. The study was registered with PROSPERO CRD42021247845.
FINDINGS
Of the 3235 records identified, 29 RCTs from 13 regions (n=7592 participants) were included in the systematic review, and 28 of these RCTs (n=7092 participants) were included in the meta-analysis. 11 studies used SMS as the primary mode of delivery of the digital health intervention, 13 used smartphone applications, and five used websites. Overall, digital health intervention group participants had a -3·62 mm Hg (95% CI -5·22 to -2·02) greater reduction in systolic blood pressure, and a -2·45 mm Hg (-3·83 to -1·07) greater reduction in diastolic blood pressure, compared with control group participants. No statistically significant differences between the three different modes of delivery were observed for both the systolic (p=0·73) and the diastolic blood pressure (p=0·80) outcomes. Smartphone application interventions had a statistically significant reduction in diastolic blood pressure (-2·45 mm Hg [-4·15 to -0·74]); however, there were no statistically significant reductions for SMS interventions (-1·80 mm Hg [-4·60 to 1·00]) or website interventions (-3·43 mm Hg [-7·24 to 0·38]). Due to the considerable heterogeneity between included studies and the high risk of bias in some, the level of evidence was assigned a low overall score. Interventions were more effective among people with greater severity of hypertension at baseline. SMS interventions reported higher reach and smartphone application studies reported higher uptake, but differences were not statistically significant.
INTERPRETATION
SMS, smartphone application, and website interventions were associated with statistically and clinically significant systolic and diastolic blood pressure reductions, compared with usual care, regardless of the mode of delivery of the intervention. This conclusion is tempered by the considerable heterogeneity of included studies and the high risk of bias in most. Future studies need to describe in detail the mediators and moderators of the effectiveness and implementation of these interventions, to both further improve their effectiveness as well as increase their reach, uptake, and feasibility.
FUNDING
European Union's Horizon 2020 Research and Innovation Programme.
Topics: Humans; Adult; Feasibility Studies; Hypertension; Blood Pressure; Randomized Controlled Trials as Topic
PubMed: 36828607
DOI: 10.1016/S2589-7500(23)00002-X -
Mayo Clinic Proceedings Nov 2013To evaluate the effect of statins on short-term cognitive function and the long-term incidence of dementia. (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
To evaluate the effect of statins on short-term cognitive function and the long-term incidence of dementia.
PATIENTS AND METHODS
A systematic search was performed of MEDLINE, EMBASE, and the Cochrane Central Register from their inception to April 25, 2013. Adults with no history of cognitive dysfunction treated with statins were included from high-quality randomized controlled trials and prospective cohort studies after formal bias assessment.
RESULTS
Sixteen studies were included in qualitative synthesis and 11 in quantitative synthesis. Short-term trials did not show a consistent effect of statin therapy on cognitive end points. Digit Symbol Substitution Testing (a well-validated measure of cognitive function) was the most common short-term end point, with no significant differences in the mean change from baseline to follow-up between the statin and placebo groups (mean change, 1.65; 95% CI, -0.03 to 3.32; 296 total exposures in 3 trials). Long-term cognition studies included 23,443 patients with a mean exposure duration of 3 to 24.9 years. Three studies found no association between statin use and incident dementia, and 5 found a favorable effect. Pooled results revealed a 29% reduction in incident dementia in statin-treated patients (hazard ratio, 0.71; 95% CI, 0.61-0.82).
CONCLUSION
In patients without baseline cognitive dysfunction, short-term data are most compatible with no adverse effect of statins on cognition, and long-term data may support a beneficial role for statins in the prevention of dementia.
Topics: Adult; Cognition; Cognition Disorders; Dementia; Humans; Hydroxymethylglutaryl-CoA Reductase Inhibitors; Incidence; Treatment Outcome
PubMed: 24095248
DOI: 10.1016/j.mayocp.2013.07.013 -
NPJ Digital Medicine Dec 2023Conversational artificial intelligence (AI), particularly AI-based conversational agents (CAs), is gaining traction in mental health care. Despite their growing usage,... (Review)
Review
Conversational artificial intelligence (AI), particularly AI-based conversational agents (CAs), is gaining traction in mental health care. Despite their growing usage, there is a scarcity of comprehensive evaluations of their impact on mental health and well-being. This systematic review and meta-analysis aims to fill this gap by synthesizing evidence on the effectiveness of AI-based CAs in improving mental health and factors influencing their effectiveness and user experience. Twelve databases were searched for experimental studies of AI-based CAs' effects on mental illnesses and psychological well-being published before May 26, 2023. Out of 7834 records, 35 eligible studies were identified for systematic review, out of which 15 randomized controlled trials were included for meta-analysis. The meta-analysis revealed that AI-based CAs significantly reduce symptoms of depression (Hedge's g 0.64 [95% CI 0.17-1.12]) and distress (Hedge's g 0.7 [95% CI 0.18-1.22]). These effects were more pronounced in CAs that are multimodal, generative AI-based, integrated with mobile/instant messaging apps, and targeting clinical/subclinical and elderly populations. However, CA-based interventions showed no significant improvement in overall psychological well-being (Hedge's g 0.32 [95% CI -0.13 to 0.78]). User experience with AI-based CAs was largely shaped by the quality of human-AI therapeutic relationships, content engagement, and effective communication. These findings underscore the potential of AI-based CAs in addressing mental health issues. Future research should investigate the underlying mechanisms of their effectiveness, assess long-term effects across various mental health outcomes, and evaluate the safe integration of large language models (LLMs) in mental health care.
PubMed: 38114588
DOI: 10.1038/s41746-023-00979-5 -
Digital Health 2023Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for... (Review)
Review
OBJECTIVE
Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for clinical diagnosis and health assessment. This systematic review aims to provide a comprehensive overview of the existing research that uses wearable sensors and features for the diagnosis of neurodegenerative diseases.
METHODS
A systematic review was conducted of studies published between 2015 and 2022 in major scientific databases such as Web of Science, Google Scholar, PubMed, and Scopes. The obtained studies were analyzed and organized into the process of diagnosis: wearable sensors, feature extraction, and feature selection.
RESULTS
The search led to 171 eligible studies included in this overview. Wearable sensors such as force sensors, inertial sensors, electromyography, electroencephalography, acoustic sensors, optical fiber sensors, and global positioning systems were employed to monitor and diagnose neurodegenerative diseases. Various features including physical features, statistical features, nonlinear features, and features from the network can be extracted from these wearable sensors, and the alteration of features toward neurodegenerative diseases was illustrated. Moreover, different kinds of feature selection methods such as filter, wrapper, and embedded methods help to find the distinctive indicator of the diseases and benefit to a better diagnosis performance.
CONCLUSIONS
This systematic review enables a comprehensive understanding of wearable sensors and features for the diagnosis of neurodegenerative diseases.
PubMed: 37214662
DOI: 10.1177/20552076231173569 -
Journal of Hand and Microsurgery Aug 2020There is a lack of consensus on what the critical outcomes in replantation are and how best to measure them. This review aims to identify all reported outcomes and... (Review)
Review
There is a lack of consensus on what the critical outcomes in replantation are and how best to measure them. This review aims to identify all reported outcomes and respective outcome measures used in digital replantation. Randomized controlled trials, cohort studies, and single-arm observational studies of adults undergoing replantation with at least one well-described outcome or outcome measure were identified. Primary outcomes were classified into six domains, and outcome measures were classified into eight domains. The clinimetric properties were identified and reported. A total of 56 observational studies met the inclusion criteria. In total, 29 continuous and 29 categorical outcomes were identified, and 87 scales and instruments were identified. The most frequently used outcomes were survival of replanted digit, sensation, and time in hospital. Outcomes and measures were most variable in domains of viability, quality of life, and motor function. Only eight measures used across these domains were validated and proven reliable. Lack of consensus creates an obstacle to reporting, understanding, and comparing the effectiveness of various replantation strategies.
PubMed: 33335363
DOI: 10.1055/s-0040-1701324 -
The Lancet. Digital Health Jul 2022Stratifying risk of postoperative pulmonary complications after major abdominal surgery allows clinicians to modify risk through targeted interventions and enhanced...
Evaluation of prognostic risk models for postoperative pulmonary complications in adult patients undergoing major abdominal surgery: a systematic review and international external validation cohort study.
BACKGROUND
Stratifying risk of postoperative pulmonary complications after major abdominal surgery allows clinicians to modify risk through targeted interventions and enhanced monitoring. In this study, we aimed to identify and validate prognostic models against a new consensus definition of postoperative pulmonary complications.
METHODS
We did a systematic review and international external validation cohort study. The systematic review was done in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We searched MEDLINE and Embase on March 1, 2020, for articles published in English that reported on risk prediction models for postoperative pulmonary complications following abdominal surgery. External validation of existing models was done within a prospective international cohort study of adult patients (≥18 years) undergoing major abdominal surgery. Data were collected between Jan 1, 2019, and April 30, 2019, in the UK, Ireland, and Australia. Discriminative ability and prognostic accuracy summary statistics were compared between models for the 30-day postoperative pulmonary complication rate as defined by the Standardised Endpoints in Perioperative Medicine Core Outcome Measures in Perioperative and Anaesthetic Care (StEP-COMPAC). Model performance was compared using the area under the receiver operating characteristic curve (AUROCC).
FINDINGS
In total, we identified 2903 records from our literature search; of which, 2514 (86·6%) unique records were screened, 121 (4·8%) of 2514 full texts were assessed for eligibility, and 29 unique prognostic models were identified. Nine (31·0%) of 29 models had score development reported only, 19 (65·5%) had undergone internal validation, and only four (13·8%) had been externally validated. Data to validate six eligible models were collected in the international external validation cohort study. Data from 11 591 patients were available, with an overall postoperative pulmonary complication rate of 7·8% (n=903). None of the six models showed good discrimination (defined as AUROCC ≥0·70) for identifying postoperative pulmonary complications, with the Assess Respiratory Risk in Surgical Patients in Catalonia score showing the best discrimination (AUROCC 0·700 [95% CI 0·683-0·717]).
INTERPRETATION
In the pre-COVID-19 pandemic data, variability in the risk of pulmonary complications (StEP-COMPAC definition) following major abdominal surgery was poorly described by existing prognostication tools. To improve surgical safety during the COVID-19 pandemic recovery and beyond, novel risk stratification tools are required.
FUNDING
British Journal of Surgery Society.
Topics: Adult; COVID-19; Cohort Studies; Humans; Pandemics; Postoperative Complications; Prognosis; Prospective Studies
PubMed: 35750401
DOI: 10.1016/S2589-7500(22)00069-3 -
NPJ Digital Medicine Dec 2023Motor Neuron Disease (MND) is a progressive and largely fatal neurodegeneritve disorder with a lifetime risk of approximately 1 in 300. At diagnosis, up to 25% of people... (Review)
Review
Motor Neuron Disease (MND) is a progressive and largely fatal neurodegeneritve disorder with a lifetime risk of approximately 1 in 300. At diagnosis, up to 25% of people with MND (pwMND) exhibit bulbar dysfunction. Currently, pwMND are assessed using clinical examination and diagnostic tools including the ALS Functional Rating Scale Revised (ALS-FRS(R)), a clinician-administered questionnaire with a single item on speech intelligibility. Here we report on the use of digital technologies to assess speech features as a marker of disease diagnosis and progression in pwMND. Google Scholar, PubMed, Medline and EMBASE were systematically searched. 40 studies were evaluated including 3670 participants; 1878 with a diagnosis of MND. 24 studies used microphones, 5 used smartphones, 6 used apps, 2 used tape recorders and 1 used the Multi-Dimensional Voice Programme (MDVP) to record speech samples. Data extraction and analysis methods varied but included traditional statistical analysis, CSpeech, MATLAB and machine learning (ML) algorithms. Speech features assessed also varied and included jitter, shimmer, fundamental frequency, intelligible speaking rate, pause duration and syllable repetition. Findings from this systematic review indicate that digital speech biomarkers can distinguish pwMND from healthy controls and can help identify bulbar involvement in pwMND. Preliminary evidence suggests digitally assessed acoustic features can identify more nuanced changes in those affected by voice dysfunction. No one digital speech biomarker alone is consistently able to diagnose or prognosticate MND. Further longitudinal studies involving larger samples are required to validate the use of these technologies as diagnostic tools or prognostic biomarkers.
PubMed: 38062079
DOI: 10.1038/s41746-023-00959-9 -
Disease Markers 2018Intrauterine sex hormone environment as indicated by the second to the fourth digit ratio (2D : 4D) can be associated with cancer risk. This systematic review and... (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
Intrauterine sex hormone environment as indicated by the second to the fourth digit ratio (2D : 4D) can be associated with cancer risk. This systematic review and meta-analysis aimed to evaluate the association of 2D : 4D with cancer diagnosis, malignancy, and age at presentation.
METHODS
Studies that evaluated the association of 2D : 4D with cancer risk were collected from Pubmed/MEDLINE and Clarivate Analytics databases. Nineteen studies were included in the qualitative analysis.
RESULTS
The 2D : 4D ratio was studied in prostate cancer, breast cancer, testicular cancer, gastric cancer, oral cancer, brain tumors, and cervical intraepithelial neoplasia. Low 2D : 4D was associated with prostate cancer, gastric cancer, and brain tumors, while high 2D : 4D, with breast cancer risk and cervical dysplasia. The 2D : 4D ratio was not associated with prostate, breast, and gastric cancer stage. Greater 2D : 4D ratio was associated with younger presentation of breast cancer and brain tumors. The meta-analyses demonstrated that testicular cancer was not associated with right-hand 2D : 4D ratio ( = 0.74) and gastric cancer was not associated with right-hand ( = 0.15) and left-hand ( = 0.95) 2D : 4D ratio.
CONCLUSIONS
Sex hormone environment during early development is associated with cancer risk later in life. Further studies exploring the link between intrauterine hormone environment and cancer risk are encouraged.
Topics: Biomarkers, Tumor; Brain Neoplasms; Breast Neoplasms; Case-Control Studies; Cross-Sectional Studies; Female; Fingers; Humans; Male; Mouth Neoplasms; Ovarian Neoplasms; Prognosis; Prostatic Neoplasms; Stomach Neoplasms; Testicular Neoplasms; Uterine Cervical Dysplasia
PubMed: 29581795
DOI: 10.1155/2018/7698193