-
Archives of Physical Medicine and... Oct 2023To compare the efficacy of non-invasive brain stimulation (NiBS) such as transcranial direct current stimulation (tDCS), repetitive transcranial magnetic stimulation... (Meta-Analysis)
Meta-Analysis Review
Non-invasive Brain Stimulation Techniques for the Improvement of Upper Limb Motor Function and Performance in Activities of Daily Living After Stroke: A Systematic Review and Network Meta-analysis.
OBJECTIVE
To compare the efficacy of non-invasive brain stimulation (NiBS) such as transcranial direct current stimulation (tDCS), repetitive transcranial magnetic stimulation (rTMS), theta-burst stimulation (TBS), and transcutaneous vagus nerve stimulation (taVNS) in upper limb stroke rehabilitation.
DATA SOURCES
PubMed, Web of Science, and Cochrane databases were searched from January 2010 to June 2022.
DATA SELECTION
Randomized controlled trials (RCTs) assessing the effects of "tDCS", "rTMS", "TBS", or "taVNS" on upper limb motor function and performance in activities of daily livings (ADLs) after stroke.
DATA EXTRACTION
Data were extracted by 2 independent reviewers. Risk of bias was evaluated with the Cochrane Risk of Bias tool.
DATA SYNTHESIS
87 RCTs with 3750 participants were included. Pairwise meta-analysis showed that all NiBS except continuous TBS (cTBS) and cathodal tDCS were significantly more efficacious than sham stimulation for motor function (standardized mean difference [SMD] range 0.42-1.20), whereas taVNS, anodal tDCS, and both low and high frequency rTMS were significantly more efficacious than sham stimulation for ADLs (SMD range 0.54-0.99). NMA showed that taVNS was more effective than cTBS (SMD:1.00; 95% CI (0.02-2.02)), cathodal tDCS (SMD:1.07; 95% CI (0.21-1.92)), and Physical rehabilitation alone (SMD:1.46; 95% CI (0.59-2.33)) for improving motor function. P-score found that taVNS is best ranked treatment in improving motor function (SMD: 1.20; 95% CI (0.46-1.95)) and ADLs (SMD:1.20; 95% CI (0.45-1.94)) after stroke. After taVNS, excitatory stimulation protocols (intermittent TBS, anodal tDCS, and HF-rTMS) are most effective in improving motor function and ADLs after acute/sub-acute (SMD range 0.53-1.63) and chronic stroke (SMD range 0.39-1.16).
CONCLUSIONS
Evidence suggests that excitatory stimulation protocols are the most promising intervention in improving upper limb motor function and performance in ADLs. taVNS appeared to be a promising intervention for stroke patients, but further large RCTs are required to confirm its relative superiority.
Topics: Humans; Activities of Daily Living; Recovery of Function; Network Meta-Analysis; Stroke; Transcranial Direct Current Stimulation; Stroke Rehabilitation; Transcranial Magnetic Stimulation; Upper Extremity; Brain
PubMed: 37245690
DOI: 10.1016/j.apmr.2023.04.027 -
Systematic Reviews Oct 2023Since 1997, several meta-analyses (MAs) of placebo-controlled randomised efficacy trials of homoeopathy for any indication (PRETHAIs) have been published with different...
BACKGROUND AND OBJECTIVE
Since 1997, several meta-analyses (MAs) of placebo-controlled randomised efficacy trials of homoeopathy for any indication (PRETHAIs) have been published with different methods, results and conclusions. To date, a formal assessment of these MAs has not been performed. The main objective of this systematic review of MAs of PRETHAIs was to evaluate the efficacy of homoeopathic treatment.
METHODS
The inclusion criteria were as follows: MAs of PRETHAIs in humans; all ages, countries, settings, publication languages; and MAs published from 1 Jan. 1990 to 30 Apr. 2023. The exclusion criteria were as follows: systematic reviews without MAs; MAs restricted to age or gender groups, specific indications, or specific homoeopathic treatments; and MAs that did not assess efficacy. We searched 8 electronic databases up to 14 Dec. 2020, with an update search in 6 databases up to 30 April 2023. The primary outcome was the effect estimate for all included trials in each MA and after restricting the sample to trials with high methodological quality, according to predefined criteria. The risk of bias for each MA was assessed by the ROBIS (Risk Of Bias In Systematic reviews) tool. The quality of evidence was assessed by the GRADE framework. Statistical analyses were performed to determine the proportion of MAs showing a significant positive effect of homoeopathy vs. no significant difference.
RESULTS
Six MAs were included, covering individualised homoeopathy (I-HOM, n = 2), nonindividualised homoeopathy (NI-HOM, n = 1) and all homoeopathy types (ALL-HOM = I-HOM + NI-HOM, n = 3). The MAs comprised between 16 and 110 trials, and the included trials were published from 1943-2014. The median trial sample size ranged from 45 to 97 patients. The risk of bias (low/unclear/high) was rated as low for three MAs and high for three MAs. Effect estimates for all trials in each MA showed a significant positive effect of homoeopathy compared to placebo (5 of 5 MAs, no data in 1 MA). Sensitivity analyses with sample restriction to high-quality trials were available from 4 MAs; the effect remained significant in 3 of the MAs (2 MAs assessed ALL-HOM, 1 MA assessed I-HOM) and was no longer significant in 1 MA (which assessed NI-HOM).
DISCUSSION
The quality of evidence for positive effects of homoeopathy beyond placebo (high/moderate/low/very low) was high for I-HOM and moderate for ALL-HOM and NI-HOM. There was no support for the alternative hypothesis of no outcome difference between homoeopathy and placebo. The available MAs of PRETHAIs reveal significant positive effects of homoeopathy beyond placebo. This is in accordance with laboratory experiments showing partially replicable effects of homoeopathically potentised preparations in physico-chemical, in vitro, plant-based and animal-based test systems.
SYSTEMATIC REVIEW REGISTRATION
PROSPERO CRD42020209661. The protocol for this SR was finalised and submitted on 25 Nov. 2020 and registered on 26 Dec. 2020.
Topics: Humans; Bias; Homeopathy; Research Design; Meta-Analysis as Topic; Randomized Controlled Trials as Topic
PubMed: 37805577
DOI: 10.1186/s13643-023-02313-2 -
Journal of Orthopaedic Surgery and... Jun 2022This Bayesian network meta-analysis investigated the available randomized control trials (RCTs) to point out which acupuncture protocol is the most effective for chronic... (Meta-Analysis)
Meta-Analysis
BACKGROUND
This Bayesian network meta-analysis investigated the available randomized control trials (RCTs) to point out which acupuncture protocol is the most effective for chronic aspecific low back pain (LBP). Efficacy was measured in terms of pain (Visual Analogic Scale, VAS) and disability (Roland Morris Disability Questionnaire, RMQ), Transcutaneous Electrical Nerve Stimulation (TENS).
METHODS
PubMed, Google scholar, Embase, and Scopus were accessed in March 2022. All the RCTs comparing two or more acupuncture modalities for aspecific chronic LBP were accessed. Only studies which investigated the efficacy of acupuncture on patients with symptoms lasting a minimum of 1.5 months, or with at least three episodes in the previous 12 months, were considered eligible. The Review Manager Software (The Nordic Cochrane Collaboration, Copenhagen) was used for the methodological quality assessment. The STATA Software/MP, Version 14.1 (StataCorporation, College Station, Texas, USA), was used for the statistical analyses. The NMA was performed through the STATA routine for Bayesian hierarchical random-effects model analysis.
RESULTS
Data from 44 RCTs (8338 procedures) were retrieved. 56% of patients were women. The mean age of the patients was 48 ± 10.6 years. The mean BMI was 26.3 ± 2.2 kg/m. The individual group (95% confidence interval (CI) 2.02, 7.98) and the standard combined with TENS (95% CI 2.03, 7.97) demonstrated the highest improvement of the RMQ. The VAS score was lower in the standard combined with TENS group (95% CI 3.28, 4.56). Considering the standard acupuncture group, different studies used similar protocols and acupuncture points and the results could thus be compared. The equation for global linearity did not find any statistically significant inconsistency in any of the network comparison.
CONCLUSION
Verum acupuncture is more effective than sham treatment for the non-pharmacological management of LBP. Among the verum protocols, individualized acupuncture and standard acupuncture with TENS were the protocols that resulted in the highest improvement in pain and quality of life.
LEVEL OF EVIDENCE
Level I, Bayesian network meta-analysis of RCTs.
Topics: Acupuncture Therapy; Adult; Chronic Pain; Female; Humans; Low Back Pain; Male; Middle Aged; Network Meta-Analysis; Pain Measurement; Transcutaneous Electric Nerve Stimulation
PubMed: 35725480
DOI: 10.1186/s13018-022-03212-3 -
Medicine Oct 2023Biological agents are commonly used for the first-line treatment of ulcerative colitis (UC). However, small-molecule drugs and microbiome therapies are now being used as... (Meta-Analysis)
Meta-Analysis
Comparative of the effectiveness and safety of biological agents, small molecule drugs, and microbiome therapies in ulcerative colitis: Systematic review and network meta-analysis.
BACKGROUND
Biological agents are commonly used for the first-line treatment of ulcerative colitis (UC). However, small-molecule drugs and microbiome therapies are now being used as new treatments for ulcerative colitis. We aimed to compare the relative efficacy and safety of biologics, small-molecule drugs, and microbiome therapies for the treatment of patients with moderate-to-severe ulcerative colitis.
METHODS
We searched the Cochrane, Embase, and PubMed databases from their inception to December 2022. RCTs that recruited patients with moderate-to-severe ulcerative colitis treated with biological agents, small-molecule drugs, and microbiome therapies. Efficacy outcomes were induction of clinical remission and mucosal healing; safety outcomes were adverse events and serious adverse events. A network meta-analysis with multivariate consistency model random-effect meta-regression was done, with rankings based on surface under the cumulative ranking curve (SUCRA) values. Higher SUCRA scores correlate with better efficacy, whereas lower SUCRA scores correlate with better safety.
RESULTS
A total of 31 RCTs comprising 7933 UC patients were included in our studies. A risk of bias assessment showed a low risk of bias for most of the included studies. Upadacitinib ranked highest for induction of clinical remission (SUCRA, 0.83) and mucosal healing (SUCRA, 0.44). Moreover, no treatments were found to increase the occurrence of adverse events compared with placebos. Ustekinumab ranked lowest for adverse events (SUCRA 0.26) and probiotic ranked lowest for serious adverse events (0·21), whereas tofacitinib ranked highest for adverse events (0·43) and upadacitinib ranked highest for serious adverse events (0·43).
CONCLUSION
In this systematic review and network meta-analysis, we found upadacitinib to be ranked highest for the induction of clinical remission and mucosal healing, but the worst performing agent in terms of adverse events in UC patients. Probiotics were the best-performing agent for safety outcomes. More trials of direct comparisons are needed to inform clinical decision-making with greater confidence.
Topics: Humans; Biological Factors; Colitis, Ulcerative; Network Meta-Analysis; Ustekinumab; Biological Products
PubMed: 37904440
DOI: 10.1097/MD.0000000000035689 -
Brazilian Journal of Otorhinolaryngology 2023Oral H antihistamines are the first-line treatment for patients with allergic rhinitis, while it is uncertain which kind and dosage of the antihistamines are more... (Meta-Analysis)
Meta-Analysis Review
INTRODUCTION
Oral H antihistamines are the first-line treatment for patients with allergic rhinitis, while it is uncertain which kind and dosage of the antihistamines are more effective in improving symptoms of patients.
OBJECTIVE
To evaluate the efficacy of different oral H antihistamine treatments on patients with allergic rhinitis by performing a network meta-analysis.
METHODS
The search was executed in PubMed, Embase, OVID, the Cochrane Library and ClinicalTrials.gov for relevant studies. The network meta-analysis was performed by using Stata 16.0, and the outcome measures of the analysis were symptom score reductions of patients. Relative risks with 95% Confidence Intervals were used in the network meta-analysis to compare the clinical effect of treatments involved, and Surface Under the Cumulative Ranking Curves (SUCRAs) were also calculated to rank the treatments' efficacy.
RESULTS
18 eligible randomized controlled studies, involving a total of 9419 participants, were included in this meta-analysis. All the antihistamine treatments outperformed placebo in total symptom score reduction and each individual symptom score reduction. According to the results of SUCRA, rupatadine 20 mg and rupatadine 10 mg were ranked relatively high in reductions of total symptom score (SUCRA: 99.7%, 76.3%), nasal congestion score (SUCRA: 96.4%, 76.4%), rhinorrhea score (SUCRA: 96.6%, 74.6%) and ocular symptom score (SUCRA: 97.2%, 88.8%); rupatadine 20 mg and levocetirizine 5 mg were ranked relatively high in reductions of nasal itching score (SUCRA: 84.8%, 83.4%) and sneezing score (SUCRA: 87.3%, 95.4%); loratadine 10 mg was ranked the lowest in each symptom score reduction besides placebo.
CONCLUSION
This study suggests that rupatadine is the most effective in alleviating symptoms of patients with allergic rhinitis among different oral H antihistamine treatments involved, and rupatadine 20 mg performs better than rupatadine 10 mg. While loratadine 10 mg has inferior efficacy for patients to the other antihistamine treatments.
Topics: Humans; Loratadine; Network Meta-Analysis; Randomized Controlled Trials as Topic; Histamine H1 Antagonists; Histamine Antagonists; Rhinitis, Allergic; Treatment Outcome
PubMed: 37271114
DOI: 10.1016/j.bjorl.2023.03.009 -
Cephalalgia : An International Journal... Mar 2023We performed a random-effects network meta-analysis to study the efficacy and safety of newly developed drugs for the acute treatment of migraine attacks. (Meta-Analysis)
Meta-Analysis
Efficacy, safety and indirect comparisons of lasmiditan, rimegepant, and ubrogepant for the acute treatment of migraine: A systematic review and network meta-analysis of the literature.
BACKGROUND
We performed a random-effects network meta-analysis to study the efficacy and safety of newly developed drugs for the acute treatment of migraine attacks.
METHODS
MEDLINE via PubMed, Embase and The Cochrane Register of Controlled Trials were searched from inception to 11 February 2022. Phase 3 randomized controlled trials examining all formulations of lasmiditan, rimegepant and ubrogepant for the acute treatment of adults with migraine, were included. Data were extracted following the PRISMA guidelines.
RESULTS
Seven studies (SAMURAI, SPARTAN, CENTURION, Study 302, Study 303, ACHIEVE I and II) involving = 12,859 patients were included. All treatments were superior in efficacy to placebo. Lasmiditan 200 mg showed the highest two-hour pain freedom, while two-hour freedom from most bothersome symptom was equally achieved by the higher doses of lasmiditan (100 and 200 mg), rimegepant and the higher doses of ubrogepant (50 and 100 mg). The odds of treatment-emergent adverse events were greatest with all doses of lasmiditan.
CONCLUSION
Lasmiditan 200 mg was the most effective intervention in the treatment of migraine attacks, although it was associated with high degrees of dizziness, nausea and somnolence. Rimegepant showed slightly lower, but similar efficacy rates to lasmiditan. Ubrogepant had overall the best tolerability profile. These conclusions are limited by the absence of head-to-head comparisons, limitations of individual trials and of the meta-analysis methodology itself. CRD42022308224.
Topics: Adult; Humans; Network Meta-Analysis; Double-Blind Method; Migraine Disorders; Treatment Outcome
PubMed: 36786357
DOI: 10.1177/03331024231151419 -
The Lancet. Healthy Longevity Jun 2023Physical exercise is effective at attenuating ageing-related physical decline in general, but evidence of its benefits for older adults in residential care, who often... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Physical exercise is effective at attenuating ageing-related physical decline in general, but evidence of its benefits for older adults in residential care, who often have functional dependency, multimorbidity, and polypharmacy, is inconclusive. We aimed to establish the effects of exercise interventions on the physical function of this population.
METHODS
For this systematic review and network meta-analysis, we searched PubMed, Web of Science, Cochrane Library, Rehabilitation & Sports Medicine Source, and SPORTDiscus to identify randomised controlled trials assessing the effects of exercise interventions (vs usual care) on physical function (ie, functional independence, physical performance, and other related measures, such as muscle strength, balance, or flexibility) in adults aged 60 years or older living in residential care. Relevant studies published in English or Spanish up to Jan 12, 2023, were included in the systematic review. The quality of studies was assessed using the Tool for the Assessment of Study Quality and Reporting in Exercise (TESTEX) score. A network meta-analysis was performed for physical function-related outcomes reported in at least ten studies, with subanalyses for specific intervention (ie, exercise type, training volume, and study duration) and participant (eg, having cognitive impairment or dementia, pre-frail or frail status, and being functionally dependent) characteristics. The study protocol was registered on PROSPERO (CRD42021247809).
FINDINGS
147 studies (11 609 participants, with mean ages ranging from 67 years [SD 9] to 92 years [2]) were included in the systematic review, and were rated as having overall good quality (median TESTEX score 9 [range 3-14]). In the meta-analysis (including 105 studies, n=7759 participants), exercise interventions were associated with significantly improved overall physical function, with a standardised mean difference [SMD] of 0·13 (95% credible interval [CrI] 0·04-0·21), which was confirmed in all analysed subpopulations. The strongest association was observed with 110-225 min per week of exercise, and the greatest improvements were observed with 170 min per week (SMD 0·36 [95% CrI 0·20-0·52]). No significant differences were found between exercise types. Subanalyses showed significant improvements for almost all analysed physical function-related outcomes (Barthel index, five-times sit-to-stand test, 30-s sit-to-stand test, knee extension, hand grip strength, bicep curl strength, Short Physical Performance Battery, 6-min walking test, walking speed, Berg balance scale, and sit-and-reach test). Large heterogeneity was found between and within studies in terms of population and intervention characteristics.
INTERPRETATION
Exercise interventions are associated with improved physical function in older adults in residential care, and should, therefore, be routinely promoted in long-term care facilities.
FUNDING
None.
TRANSLATION
For the Spanish translation of the abstract see Supplementary Materials section.
Topics: Aged; Humans; Exercise; Exercise Therapy; Hand Strength; Muscle Strength; Network Meta-Analysis; Randomized Controlled Trials as Topic; Aged, 80 and over
PubMed: 37182530
DOI: 10.1016/S2666-7568(23)00057-0 -
JAMA Psychiatry Apr 2024Chronic insomnia disorder is highly prevalent, disabling, and costly. Cognitive behavioral therapy for insomnia (CBT-I), comprising various educational, cognitive, and... (Meta-Analysis)
Meta-Analysis
IMPORTANCE
Chronic insomnia disorder is highly prevalent, disabling, and costly. Cognitive behavioral therapy for insomnia (CBT-I), comprising various educational, cognitive, and behavioral strategies delivered in various formats, is the recommended first-line treatment, but the effect of each component and delivery method remains unclear.
OBJECTIVE
To examine the association of each component and delivery format of CBT-I with outcomes.
DATA SOURCES
PubMed, Cochrane Central Register of Controlled Trials, PsycInfo, and International Clinical Trials Registry Platform from database inception to July 21, 2023.
STUDY SELECTION
Published randomized clinical trials comparing any form of CBT-I against another or a control condition for chronic insomnia disorder in adults aged 18 years and older. Insomnia both with and without comorbidities was included. Concomitant treatments were allowed if equally distributed among arms.
DATA EXTRACTION AND SYNTHESIS
Two independent reviewers identified components, extracted data, and assessed trial quality. Random-effects component network meta-analyses were performed.
MAIN OUTCOMES AND MEASURES
The primary outcome was treatment efficacy (remission defined as reaching a satisfactory state) posttreatment. Secondary outcomes included all-cause dropout, self-reported sleep continuity, and long-term remission.
RESULTS
A total of 241 trials were identified including 31 452 participants (mean [SD] age, 45.4 [16.6] years; 21 048 of 31 452 [67%] women). Results suggested that critical components of CBT-I are cognitive restructuring (remission incremental odds ratio [iOR], 1.68; 95% CI, 1.28-2.20) third-wave components (iOR, 1.49; 95% CI, 1.10-2.03), sleep restriction (iOR, 1.49; 95% CI, 1.04-2.13), and stimulus control (iOR, 1.43; 95% CI, 1.00-2.05). Sleep hygiene education was not essential (iOR, 1.01; 95% CI, 0.77-1.32), and relaxation procedures were found to be potentially counterproductive(iOR, 0.81; 95% CI, 0.64-1.02). In-person therapist-led programs were most beneficial (iOR, 1.83; 95% CI, 1.19-2.81). Cognitive restructuring, third-wave components, and in-person delivery were mainly associated with improved subjective sleep quality. Sleep restriction was associated with improved subjective sleep quality, sleep efficiency, and wake after sleep onset, and stimulus control with improved subjective sleep quality, sleep efficiency, and sleep latency. The most efficacious combination-consisting of cognitive restructuring, third wave, sleep restriction, and stimulus control in the in-person format-compared with in-person psychoeducation, was associated with an increase in the remission rate by a risk difference of 0.33 (95% CI, 0.23-0.43) and a number needed to treat of 3.0 (95% CI, 2.3-4.3), given the median observed control event rate of 0.14.
CONCLUSIONS AND RELEVANCE
The findings suggest that beneficial CBT-I packages may include cognitive restructuring, third-wave components, sleep restriction, stimulus control, and in-person delivery but not relaxation. However, potential undetected interactions could undermine the conclusions. Further large-scale, well-designed trials are warranted to confirm the contribution of different treatment components in CBT-I.
Topics: Adult; Humans; Female; Middle Aged; Male; Sleep Initiation and Maintenance Disorders; Network Meta-Analysis; Cognitive Behavioral Therapy; Sleep; Treatment Outcome
PubMed: 38231522
DOI: 10.1001/jamapsychiatry.2023.5060 -
Canadian Association of Radiologists... Nov 2019The required training sample size for a particular machine learning (ML) model applied to medical imaging data is often unknown. The purpose of this study was to provide...
PURPOSE
The required training sample size for a particular machine learning (ML) model applied to medical imaging data is often unknown. The purpose of this study was to provide a descriptive review of current sample-size determination methodologies in ML applied to medical imaging and to propose recommendations for future work in the field.
METHODS
We conducted a systematic literature search of articles using Medline and Embase with keywords including "machine learning," "image," and "sample size." The search included articles published between 1946 and 2018. Data regarding the ML task, sample size, and train-test pipeline were collected.
RESULTS
A total of 167 articles were identified, of which 22 were included for qualitative analysis. There were only 4 studies that discussed sample-size determination methodologies, and 18 that tested the effect of sample size on model performance as part of an exploratory analysis. The observed methods could be categorized as pre hoc model-based approaches, which relied on features of the algorithm, or post hoc curve-fitting approaches requiring empirical testing to model and extrapolate algorithm performance as a function of sample size. Between studies, we observed great variability in performance testing procedures used for curve-fitting, model assessment methods, and reporting of confidence in sample sizes.
CONCLUSIONS
Our study highlights the scarcity of research in training set size determination methodologies applied to ML in medical imaging, emphasizes the need to standardize current reporting practices, and guides future work in development and streamlining of pre hoc and post hoc sample size approaches.
Topics: Biomedical Research; Diagnostic Imaging; Humans; Machine Learning; Sample Size
PubMed: 31522841
DOI: 10.1016/j.carj.2019.06.002 -
Advances in Therapy Aug 2023Several studies have emphasized the potential of artificial intelligence (AI) and its subfields, such as machine learning (ML), as emerging and feasible approaches to... (Meta-Analysis)
Meta-Analysis
INTRODUCTION
Several studies have emphasized the potential of artificial intelligence (AI) and its subfields, such as machine learning (ML), as emerging and feasible approaches to optimize patient care in oncology. As a result, clinicians and decision-makers are faced with a plethora of reviews regarding the state of the art of applications of AI for head and neck cancer (HNC) management. This article provides an analysis of systematic reviews on the current status, and of the limitations of the application of AI/ML as adjunctive decision-making tools in HNC management.
METHODS
Electronic databases (PubMed, Medline via Ovid, Scopus, and Web of Science) were searched from inception until November 30, 2022. The study selection, searching and screening processes, inclusion, and exclusion criteria followed the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. A risk of bias assessment was conducted using a tailored and modified version of the Assessment of Systematic Review (AMSTAR-2) tool and quality assessment using the Risk of Bias in Systematic Reviews (ROBIS) guidelines.
RESULTS
Of the 137 search hits retrieved, 17 fulfilled the inclusion criteria. This analysis of systematic reviews revealed that the application of AI/ML as a decision aid in HNC management can be thematized as follows: (1) detection of precancerous and cancerous lesions within histopathologic slides; (2) prediction of the histopathologic nature of a given lesion from various sources of medical imaging; (3) prognostication; (4) extraction of pathological findings from imaging; and (5) different applications in radiation oncology. In addition, the challenges in implementation of AI/ML models for clinical evaluations include the lack of standardized methodological guidelines for the collection of clinical images, development of these models, reporting of their performance, external validation procedures, and regulatory frameworks.
CONCLUSION
At present, there is a paucity of evidence to suggest the adoption of these models in clinical practice due to the aforementioned limitations. Therefore, this manuscript highlights the need for development of standardized guidelines to facilitate the adoption and implementation of these models in the daily clinical practice. In addition, adequately powered, prospective, randomized controlled trials are urgently needed to further assess the potential of AI/ML models in real-world clinical settings for the management of HNC.
Topics: Humans; Artificial Intelligence; Head and Neck Neoplasms; Machine Learning; Prospective Studies; Research Design
PubMed: 37291378
DOI: 10.1007/s12325-023-02527-9