| 1. |
- Oettl, Felix C., et al.
(författare)
-
A practical guide to the implementation of AI in orthopaedic research, Part 6: How to evaluate the performance of AI research?
- 2024
-
Ingår i: Journal of Experimental Orthopaedics. - 2197-1153. ; 11:3
-
Forskningsöversikt (refereegranskat)abstract
- Artificial intelligence's (AI) accelerating progress demands rigorous evaluation standards to ensure safe, effective integration into healthcare's high-stakes decisions. As AI increasingly enables prediction, analysis and judgement capabilities relevant to medicine, proper evaluation and interpretation are indispensable. Erroneous AI could endanger patients; thus, developing, validating and deploying medical AI demands adhering to strict, transparent standards centred on safety, ethics and responsible oversight. Core considerations include assessing performance on diverse real-world data, collaborating with domain experts, confirming model reliability and limitations, and advancing interpretability. Thoughtful selection of evaluation metrics suited to the clinical context along with testing on diverse data sets representing different populations improves generalisability. Partnering software engineers, data scientists and medical practitioners ground assessment in real needs. Journals must uphold reporting standards matching AI's societal impacts. With rigorous, holistic evaluation frameworks, AI can progress towards expanding healthcare access and quality. Level of Evidence: Level V.
|
|
| 2. |
- Zaharia, Oana P., et al.
(författare)
-
Risk of diabetes-associated diseases in subgroups of patients with recent-onset diabetes : a 5-year follow-up study
- 2019
-
Ingår i: The Lancet Diabetes and Endocrinology. - 2213-8587. ; 7:9, s. 684-694
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Cluster analyses have proposed different diabetes phenotypes using age, BMI, glycaemia, homoeostasis model estimates, and islet autoantibodies. We tested whether comprehensive phenotyping validates and further characterises these clusters at diagnosis and whether relevant diabetes-related complications differ among these clusters, during 5-years of follow-up. Methods: Patients with newly diagnosed type 1 or type 2 diabetes in the German Diabetes Study underwent comprehensive phenotyping and assessment of laboratory variables. Insulin sensitivity was assessed using hyperinsulinaemic-euglycaemic clamps, hepatocellular lipid content using magnetic resonance spectroscopy, hepatic fibrosis using non-invasive scores, and peripheral and autonomic neuropathy using functional and clinical criteria. Patients were reassessed after 5 years. The German Diabetes Study is registered with ClinicalTrials.gov, number NCT01055093, and is ongoing. Findings: 1105 patients were classified at baseline into five clusters, with 386 (35%) assigned to mild age-related diabetes (MARD), 323 (29%) to mild obesity-related diabetes (MOD), 247 (22%) to severe autoimmune diabetes (SAID), 121 (11%) to severe insulin-resistant diabetes (SIRD), and 28 (3%) to severe insulin-deficient diabetes (SIDD). At 5-year follow-up, 367 patients were reassessed, 128 (35%) with MARD, 106 (29%) with MOD, 88 (24%) with SAID, 35 (10%) with SIRD, and ten (3%) with SIDD. Whole-body insulin sensitivity was lowest in patients with SIRD at baseline (mean 4·3 mg/kg per min [SD 2·0]) compared with those with SAID (8·4 mg/kg per min [3·2]; p<0·0001), MARD (7·5 mg/kg per min [2·5]; p<0·0001), MOD (6·6 mg/kg per min [2·6]; p=0·0011), and SIDD (5·5 mg/kg per min [2·4]; p=0·0035). The fasting adipose-tissue insulin resistance index at baseline was highest in patients with SIRD (median 15·6 [IQR 9·3–20·9]) and MOD (11·6 [7·4–17·9]) compared with those with MARD (6·0 [3·9–10·3]; both p<0·0001) and SAID (6·0 [3·0–9·5]; both p<0·0001). In patients with newly diagnosed diabetes, hepatocellular lipid content was highest at baseline in patients assigned to the SIRD cluster (median 19% [IQR 11–22]) compared with all other clusters (7% [2–15] for MOD, p=0·00052; 5% [2–11] for MARD, p<0·0001; 2% [0–13] for SIDD, p=0·0083; and 1% [0–3] for SAID, p<0·0001), even after adjustments for baseline medication. Accordingly, hepatic fibrosis at 5-year follow-up was more prevalent in patients with SIRD (n=7 [26%]) than in patients with SAID (n=5 [7%], p=0·0011), MARD (n=12 [12%], p=0·012), MOD (n=13 [15%], p=0·050), and SIDD (n=0 [0%], p value not available). Confirmed diabetic sensorimotor polyneuropathy was more prevalent at baseline in patients with SIDD (n=9 [36%]) compared with patients with SAID (n=10 [5%], p<0·0001), MARD (n=39 [15%], p=0·00066), MOD (n=26 [11%], p<0·0001), and SIRD (n=10 [17%], p<0·0001). Interpretation: Cluster analysis can characterise cohorts with different degrees of whole-body and adipose-tissue insulin resistance. Specific diabetes clusters show different prevalence of diabetes complications at early stages of non-alcoholic fatty liver disease and diabetic neuropathy. These findings could help improve targeted prevention and treatment and enable precision medicine for diabetes and its comorbidities. Funding: German Diabetes Center, German Federal Ministry of Health, Ministry of Culture and Science of the state of North Rhine-Westphalia, German Federal Ministry of Education and Research, German Diabetes Association, German Center for Diabetes Research, Research Network SFB 1116 of the German Research Foundation, and Schmutzler Stiftung.
|
|
| 3. |
- Zsidai, Balint, 1993, et al.
(författare)
-
A practical guide to the implementation of AI in orthopaedic research – part 1: opportunities in clinical application and overcoming existing challenges
- 2023
-
Ingår i: Journal of Experimental Orthopaedics. - 2197-1153. ; 10:1
-
Forskningsöversikt (refereegranskat)abstract
- Artificial intelligence (AI) has the potential to transform medical research by improving disease diagnosis, clinical decision-making, and outcome prediction. Despite the rapid adoption of AI and machine learning (ML) in other domains and industry, deployment in medical research and clinical practice poses several challenges due to the inherent characteristics and barriers of the healthcare sector. Therefore, researchers aiming to perform AI-intensive studies require a fundamental understanding of the key concepts, biases, and clinical safety concerns associated with the use of AI. Through the analysis of large, multimodal datasets, AI has the potential to revolutionize orthopaedic research, with new insights regarding the optimal diagnosis and management of patients affected musculoskeletal injury and disease. The article is the first in a series introducing fundamental concepts and best practices to guide healthcare professionals and researcher interested in performing AI-intensive orthopaedic research studies. The vast potential of AI in orthopaedics is illustrated through examples involving disease- or injury-specific outcome prediction, medical image analysis, clinical decision support systems and digital twin technology. Furthermore, it is essential to address the role of human involvement in training unbiased, generalizable AI models, their explainability in high-risk clinical settings and the implementation of expert oversight and clinical safety measures for failure. In conclusion, the opportunities and challenges of AI in medicine are presented to ensure the safe and ethical deployment of AI models for orthopaedic research and clinical application. Level of evidence IV
|
|
| 4. |
- Zsidai, Bálint, et al.
(författare)
-
A practical guide to the implementation of artificial intelligence in orthopaedic research—Part 2: A technical introduction
- 2024
-
Ingår i: Journal of Experimental Orthopaedics. - 2197-1153. ; 11:3
-
Forskningsöversikt (refereegranskat)abstract
- Recent advances in artificial intelligence (AI) present a broad range of possibilities in medical research. However, orthopaedic researchers aiming to participate in research projects implementing AI-based techniques require a sound understanding of the technical fundamentals of this rapidly developing field. Initial sections of this technical primer provide an overview of the general and the more detailed taxonomy of AI methods. Researchers are presented with the technical basics of the most frequently performed machine learning (ML) tasks, such as classification, regression, clustering and dimensionality reduction. Additionally, the spectrum of supervision in ML including the domains of supervised, unsupervised, semisupervised and self-supervised learning will be explored. Recent advances in neural networks (NNs) and deep learning (DL) architectures have rendered them essential tools for the analysis of complex medical data, which warrants a rudimentary technical introduction to orthopaedic researchers. Furthermore, the capability of natural language processing (NLP) to interpret patterns in human language is discussed and may offer several potential applications in medical text classification, patient sentiment analysis and clinical decision support. The technical discussion concludes with the transformative potential of generative AI and large language models (LLMs) on AI research. Consequently, this second article of the series aims to equip orthopaedic researchers with the fundamental technical knowledge required to engage in interdisciplinary collaboration in AI-driven orthopaedic research. Level of Evidence: Level IV.
|
|
| 5. |
|
|
