-
The Reporting Quality of Machine Learning Studies on Pediatric Diabetes Mellitus: Systematic Review.Journal of Medical Internet Research Jan 2024Diabetes mellitus (DM) is a major health concern among children with the widespread adoption of advanced technologies. However, concerns are growing about the... (Review)
Review
BACKGROUND
Diabetes mellitus (DM) is a major health concern among children with the widespread adoption of advanced technologies. However, concerns are growing about the transparency, replicability, biasedness, and overall validity of artificial intelligence studies in medicine.
OBJECTIVE
We aimed to systematically review the reporting quality of machine learning (ML) studies of pediatric DM using the Minimum Information About Clinical Artificial Intelligence Modelling (MI-CLAIM) checklist, a general reporting guideline for medical artificial intelligence studies.
METHODS
We searched the PubMed and Web of Science databases from 2016 to 2020. Studies were included if the use of ML was reported in children with DM aged 2 to 18 years, including studies on complications, screening studies, and in silico samples. In studies following the ML workflow of training, validation, and testing of results, reporting quality was assessed via MI-CLAIM by consensus judgments of independent reviewer pairs. Positive answers to the 17 binary items regarding sufficient reporting were qualitatively summarized and counted as a proxy measure of reporting quality. The synthesis of results included testing the association of reporting quality with publication and data type, participants (human or in silico), research goals, level of code sharing, and the scientific field of publication (medical or engineering), as well as with expert judgments of clinical impact and reproducibility.
RESULTS
After screening 1043 records, 28 studies were included. The sample size of the training cohort ranged from 5 to 561. Six studies featured only in silico patients. The reporting quality was low, with great variation among the 21 studies assessed using MI-CLAIM. The number of items with sufficient reporting ranged from 4 to 12 (mean 7.43, SD 2.62). The items on research questions and data characterization were reported adequately most often, whereas items on patient characteristics and model examination were reported adequately least often. The representativeness of the training and test cohorts to real-world settings and the adequacy of model performance evaluation were the most difficult to judge. Reporting quality improved over time (r=0.50; P=.02); it was higher than average in prognostic biomarker and risk factor studies (P=.04) and lower in noninvasive hypoglycemia detection studies (P=.006), higher in studies published in medical versus engineering journals (P=.004), and higher in studies sharing any code of the ML pipeline versus not sharing (P=.003). The association between expert judgments and MI-CLAIM ratings was not significant.
CONCLUSIONS
The reporting quality of ML studies in the pediatric population with DM was generally low. Important details for clinicians, such as patient characteristics; comparison with the state-of-the-art solution; and model examination for valid, unbiased, and robust results, were often the weak points of reporting. To assess their clinical utility, the reporting standards of ML studies must evolve, and algorithms for this challenging population must become more transparent and replicable.
Topics: Humans; Child; Artificial Intelligence; Reproducibility of Results; Machine Learning; Diabetes Mellitus; Checklist
PubMed: 38241075
DOI: 10.2196/47430 -
Diagnostics (Basel, Switzerland) Jan 2024Artificial intelligence (AI) has emerged as a transformative force in various sectors, including medicine and healthcare. Large language models like ChatGPT showcase... (Review)
Review
Artificial intelligence (AI) has emerged as a transformative force in various sectors, including medicine and healthcare. Large language models like ChatGPT showcase AI's potential by generating human-like text through prompts. ChatGPT's adaptability holds promise for reshaping medical practices, improving patient care, and enhancing interactions among healthcare professionals, patients, and data. In pandemic management, ChatGPT rapidly disseminates vital information. It serves as a virtual assistant in surgical consultations, aids dental practices, simplifies medical education, and aids in disease diagnosis. A total of 82 papers were categorised into eight major areas, which are G1: treatment and medicine, G2: buildings and equipment, G3: parts of the human body and areas of the disease, G4: patients, G5: citizens, G6: cellular imaging, radiology, pulse and medical images, G7: doctors and nurses, and G8: tools, devices and administration. Balancing AI's role with human judgment remains a challenge. A systematic literature review using the PRISMA approach explored AI's transformative potential in healthcare, highlighting ChatGPT's versatile applications, limitations, motivation, and challenges. In conclusion, ChatGPT's diverse medical applications demonstrate its potential for innovation, serving as a valuable resource for students, academics, and researchers in healthcare. Additionally, this study serves as a guide, assisting students, academics, and researchers in the field of medicine and healthcare alike.
PubMed: 38201418
DOI: 10.3390/diagnostics14010109 -
Healthcare (Basel, Switzerland) Dec 2023Clinical reasoning (CR) is a holistic and recursive cognitive process. It allows nursing students to accurately perceive patients' situations and choose the best course... (Review)
Review
BACKGROUND
Clinical reasoning (CR) is a holistic and recursive cognitive process. It allows nursing students to accurately perceive patients' situations and choose the best course of action among the available alternatives. This study aimed to identify the randomised controlled trials studies in the literature that concern clinical reasoning in the context of nursing students.
METHODS
A comprehensive search of PubMed, Scopus, Embase, and the Cochrane Controlled Register of Trials (CENTRAL) was performed to identify relevant studies published up to October 2023. The following inclusion criteria were examined: (a) clinical reasoning, clinical judgment, and critical thinking in nursing students as a primary study aim; (b) articles published for the last eleven years; (c) research conducted between January 2012 and September 2023; (d) articles published only in English and Spanish; and (e) Randomised Clinical Trials. The Critical Appraisal Skills Programme tool was utilised to appraise all included studies.
RESULTS
Fifteen papers were analysed. Based on the teaching strategies used in the articles, two groups have been identified: simulation methods and learning programs. The studies focus on comparing different teaching methodologies.
CONCLUSIONS
This systematic review has detected different approaches to help nursing students improve their reasoning and decision-making skills. The use of mobile apps, digital simulations, and learning games has a positive impact on the clinical reasoning abilities of nursing students and their motivation. Incorporating new technologies into problem-solving-based learning and decision-making can also enhance nursing students' reasoning skills. Nursing schools should evaluate their current methods and consider integrating or modifying new technologies and methodologies that can help enhance students' learning and improve their clinical reasoning and cognitive skills.
PubMed: 38200996
DOI: 10.3390/healthcare12010090 -
Frontiers in Neurology 2023Chronic pain is common, disruptive, and often treatment-resistant. Hence, researchers and clinicians seek alternative therapies for chronic pain. Transcranial... (Review)
Review
BACKGROUND
Chronic pain is common, disruptive, and often treatment-resistant. Hence, researchers and clinicians seek alternative therapies for chronic pain. Transcranial alternating current stimulation (tACS) is an emerging neuromodulation technique that non-invasively modulates neural oscillations in the human brain. tACS induces pain relief by allowing the neural network to restore adequate synchronization. We reviewed studies on the effectiveness of tACS in controlling chronic pain.
METHODS
The PubMed, SCOPUS, Embase, and Cochrane Library databases were systematically searched for relevant studies published until December 6, 2023. The key search phrase for identifying potentially relevant articles was [(Transcranial Alternating Current Stimulation OR tACS) AND pain]. The following inclusion criteria were applied for article selection: (1) studies involving patients with chronic pain; (2) tACS was applied for controlling pain; and (3) follow-up evaluations were performed to assess the degree of pain reduction after the application of tACS.
RESULTS
We identified 2,330 potentially relevant articles. After reading the titles and abstracts and assessing eligibility based on the full-text articles, we included four articles in our review. Among the included studies, tACS was used for fibromyalgia in one study, low back pain (LBP) in two studies, and migraine in one study. In the study on fibromyalgia, it did not show a better pain-reducing effect of tACS compared with sham stimulation. Two studies on LBP showed conflicting results. In migraine, tACS showed a positive pain-reducing effect 24-48 h after its application.
CONCLUSION
There is insufficient research to draw a conclusive judgment on the effectiveness of tACS in controlling chronic pain. More studies across various chronic pain-related diseases are required for a definitive conclusion.
PubMed: 38192572
DOI: 10.3389/fneur.2023.1323520 -
Frontiers in Psychology 2023Previous research suggests that altered experiences of agency are an underlying vulnerability in both schizophrenia and autism. Here, we explore agency as a potential...
INTRODUCTION
Previous research suggests that altered experiences of agency are an underlying vulnerability in both schizophrenia and autism. Here, we explore agency as a potential transdiagnostic factor by conducting a systematic review of existing literature investigating agency in autism and schizophrenia individually and together.
METHODS
Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we conducted three systematic searches on PsycINFO, Embase, Medline, PubMed and Web of Science to identify studies that investigated (1) agency in schizophrenia, (2) agency in autism, and (3) agency in both schizophrenia and autism.
RESULTS
A total of 31 articles met eligibility criteria for inclusion and data extraction, with 24 measuring agency in schizophrenia, 7 investigating agency in autism, and no articles comparing the two. Results show that, compared to control populations, agency is significantly different in every identified schizophrenia study and generally not significantly different in autism.
DISCUSSION
Importantly, we identified a lack of studies using common tasks and a disproportionate number of studies investigating different dimensions of agency across the two conditions, resulting in limited grounds for valid comparison.
SYSTEMATIC REVIEW REGISTRATION
Prospero, CRD42021273373.
PubMed: 38187412
DOI: 10.3389/fpsyg.2023.1280622 -
European Review For Medical and... Dec 2023Self-consciousness is defined as a subject (I) then becomes the object (Me) associated with a present moment of self-experience in which one is aware of their experience...
OBJECTIVE
Self-consciousness is defined as a subject (I) then becomes the object (Me) associated with a present moment of self-experience in which one is aware of their experience without any reflexive judgment attached, a state commonly investigated in mindfulness studies. On the other hand, self-consciousness is viewed as a reflexive experience and, thus, as a synonym for self-reflection. Self-consciousness is an important determinant of behaviors. Expanding self-consciousness is important among adults with diabetes to optimize health prevention and compliance with diabetes self-management in the long term. The chronic complications of diabetes comprise heart disease, stroke, nephropathy, retinopathy, and neuropathy. This review aims to explain the relationship between self-consciousness and chronic diabetes complications.
MATERIALS AND METHODS
An electronic literature search was conducted in the English language in several databases. The Joanna-Briggs Institute was referenced for the quality assessment of case studies, cohort and cross-sectional studies, and qualitative studies, while systematic reviews were evaluated through PRISMA-S. Results were reported according to the PRISMA guidelines.
RESULTS
A total of 89 studies related to self-consciousness of diabetes chronic complications were not found. However, many findings related to chronic complications are based on a lack of knowledge of diabetes and long-term self-management. People with less education, multiple comorbidities, and cognitive dysfunction need lifestyle changes to prevent diabetes and chronic complications.
CONCLUSIONS
Future research should be oriented toward assessing the risk of chronic diabetes complications. Our findings suggest that research should expand self-consciousness and caring partnerships to improve self-consciousness and patients' obedience.
Topics: Adult; Humans; Cross-Sectional Studies; Diabetes Complications; Diabetes Mellitus; Health Status; Quality of Life; Health Literacy; Mindfulness
PubMed: 38164869
DOI: 10.26355/eurrev_202312_34805 -
Epidemiology and Health 2023Cancer is a major health burden in Korea, and dietary factors have been suggested as putative risk factors for cancer development at various sites. This study... (Meta-Analysis)
Meta-Analysis
Cancer is a major health burden in Korea, and dietary factors have been suggested as putative risk factors for cancer development at various sites. This study systematically reviewed the published literature investigating the associations between dietary factors and cancer incidence among Korean adults, following the Preferred Reporting Items for Systematic Reviews and Meta- Analyses guidelines. We focused on the 5 most studied cancer sites (stomach, colorectum, breast, thyroid, and cervix) as outcomes and dietary exposures with evidence levels greater than limited-suggestive according to the World Cancer Research Fund/American Institute for Cancer Research (WCRF/AICR) panel's judgment for any of the cancer sites. This resulted in the inclusion of 72 studies. Pooled estimates of the impact of dietary factors on cancer risk suggested protective associations of fruits and vegetables with risks for gastric cancer (GC), colorectal cancer (CRC), and breast cancer (BC) and dietary vitamin C with the risk of GC, as well as a harmful association between fermented soy products and the risk of GC. Despite the limited number of studies, we observed consistent protective associations of dietary fiber with GC and dietary fiber, coffee, and calcium with CRC. These findings are largely consistent with the WCRF/AICR expert report. However, pooled estimates for the associations of other salt-preserved foods with GC, meat with CRC, and dietary carotenoids and dairy products with BC did not reach statistical significance. Further studies with prospective designs, larger sample sizes, and diverse types of dietary factors and cancer sites are necessary.
Topics: Adult; Humans; Diet; Dietary Fiber; Eating; Incidence; Neoplasms; Republic of Korea; Risk Factors; Observational Studies as Topic
PubMed: 38037322
DOI: 10.4178/epih.e2023102 -
Frontiers in Veterinary Science 2023Cognitive approaches are increasingly used to assess animal welfare, but no systematic review has been conducted on pigs despite their cognitive capacities. Our aims...
Cognitive approaches are increasingly used to assess animal welfare, but no systematic review has been conducted on pigs despite their cognitive capacities. Our aims were two-fold: first, to assess the popularity and heterogeneity of this approach by quantifying the different cognitive tasks used and welfare interventions studied. The second was to assess how often results from cognitive tasks supported treatment effects. The search yielded 36 studies that met our criteria. Eleven different cognitive tasks were applied (three most common: judgment bias, learned approach/aversion, and holeboard). Welfare interventions investigated were also diverse: the impact of 19 other different events/conditions/states were reported (most common: housing enrichment). We defined "supportive" as the observation of a significant difference between treatment groups consistent with an author's expectation or hypothesis. Supportive findings were reported in 44% of papers. Interventions yielded no significant difference in 33% of studies. In another 21% of reports, outcomes were mixed and a single study refuted the author's predictions. When considering specific cognitive tasks, authors' predictions of welfare differences were supported most often when using learned approach/aversion (55% of these studies). Similar supportive results were observed less commonly (40% each) when using judgment bias and holeboard tests. Analysis of additional concomitant measures of welfare (health, physiology or behavior) revealed that behavioral measures were most frequently supportive of author's expectations (41%) as well as often matching the actual outcomes of these cognitive tasks (47%). This systematic review highlights the growing popularity of cognitive tasks as measures of pig welfare. However, overall rates of supportive results, i.e., changes in performance on cognitive tasks due to welfare interventions, have been limited so far, even for the most employed task, judgment bias. The numerous different combinations of experimental paradigms and welfare interventions reported in the literature creates challenges for a critical meta-analysis of the field especially in evaluating the efficiency of specific cognitive tasks in assessing animal welfare. This work also highlights important knowledge gaps in the use of cognitive tasks that will require both further validation as well as novel innovation to ensure that their potential is fully realized in the measurement of pig welfare.
PubMed: 38033647
DOI: 10.3389/fvets.2023.1251070 -
American Journal of Cardiovascular... Jan 2024Pulmonary arterial hypertension (PAH) is a progressive, cureless disease, characterized by increased pulmonary vascular resistance and remodeling, with subsequent... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Pulmonary arterial hypertension (PAH) is a progressive, cureless disease, characterized by increased pulmonary vascular resistance and remodeling, with subsequent ventricular dilatation and failure. New therapeutic targets are being investigated for their potential roles in improving PAH patients' symptoms and reversing pulmonary vascular pathology.
METHOD
We aimed to address the available knowledge from the published randomized controlled trials (RCTs) regarding the role of Rho-kinase (ROCK) inhibitors, bone morphogenetic protein 2 (BMP2) inhibitors, estrogen inhibitors, and AMP-activated protein kinase (AMPK) activators on the PAH evaluation parameters. This systematic review (SR) was registered in the International Prospective Register of Systematic Reviews (PROSPERO) database (CDR42022340658) and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.
RESULTS
Overall, 5092 records were screened from different database and registries; 8 RCTs that met our inclusion criteria were included. The marked difference in the study designs and the variability of the selected outcome measurement tools among the studies made performing a meta-analysis impossible. However, the main findings of this SR relate to the powerful potential of the AMPK activator and the imminent antidiabetic drug metformin, and the BMP2 inhibitor sotatercept as promising PAH-modifying therapies. There is a need for long-term studies to evaluate the effect of the ROCK inhibitor fasudil and the estrogen aromatase inhibitor anastrozole in PAH patients. The role of tacrolimus in PAH is questionable. The discrepancy in the hemodynamic and clinical parameters necessitates defining cut values to predict improvement. The differences in the PAH etiologies render the judgment of the therapeutic potential of the tested drugs challenging.
CONCLUSION
Metformin and sotatercept appear as promising therapeutic drugs for PAH.
CLINICAL TRIALS REGISTRATION
This work was registered in PROSPERO (CDR42022340658).
Topics: Humans; Pulmonary Arterial Hypertension; Hypertension, Pulmonary; AMP-Activated Protein Kinases; Familial Primary Pulmonary Hypertension; Estrogens; Metformin
PubMed: 37945977
DOI: 10.1007/s40256-023-00613-5 -
PloS One 2023Amputation is an irreversible, last-line treatment indicated for a multitude of medical problems. Delaying amputation in favor of limb-sparing treatment may lead to...
Amputation is an irreversible, last-line treatment indicated for a multitude of medical problems. Delaying amputation in favor of limb-sparing treatment may lead to increased risk of morbidity and mortality. This systematic review aims to synthesize the literature on how ML is being applied to predict amputation as an outcome. OVID Embase, OVID Medline, ACM Digital Library, Scopus, Web of Science, and IEEE Xplore were searched from inception to March 5, 2023. 1376 studies were screened; 15 articles were included. In the diabetic population, models ranged from sub-optimal to excellent performance (AUC: 0.6-0.94). In trauma patients, models had strong to excellent performance (AUC: 0.88-0.95). In patients who received amputation secondary to other etiologies (e.g.: burns and peripheral vascular disease), models had similar performance (AUC: 0.81-1.0). Many studies were found to have a high PROBAST risk of bias, most often due to small sample sizes. In conclusion, multiple machine learning models have been successfully developed that have the potential to be superior to traditional modeling techniques and prospective clinical judgment in predicting amputation. Further research is needed to overcome the limitations of current studies and to bring applicability to a clinical setting.
Topics: Humans; Prospective Studies; Amputation, Surgical; Peripheral Vascular Diseases; Machine Learning
PubMed: 37934767
DOI: 10.1371/journal.pone.0293684