A systematic review and meta-analysis of artificial intelligence diagnostic accuracy in prostate cancer histology identification and grading

Morozov, Andrey; Taratkin, Mark; Bazarkin, Andrey; Rivas, Juan Gómez; Puliatti, Stefano; Checcucci, Enrico; Belenchón, I. Rivero; Kowalewski, Karl‐Friedrich; Shpikina, Anastasia; Singla, Nirmish; Teoh, Jeremy Yuen‐Chun; Козлов, В. В.; Rodler, Severin; Piazza, Pietro; Fajković, Harun; Yakimov, Maxim; Abreu, André Luís de Castro; Cacciamani, Giovanni; Enikeev, Dmitry

doi:10.1038/s41391-023-00673-3

Cited by 18 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, our narrative synthesis showed that the performance of wearable AI in detecting students with stress (75.5%) is comparable with its performance in detecting students without stress (74.4%). We considered that the performance of wearable AI in detecting stress among students is suboptimal given that many previous reviews have shown a higher performance of AI in detecting other diseases or disorders, such as cancers [ 65 - 68 ], heart diseases [ 69 , 70 ], ear diseases [ 71 ], and ophthalmic disorders [ 72 , 73 ]. Moreover, relying solely on pooled mean accuracy is insufficient for drawing definitive conclusions regarding the performance of wearable AI; thus, we considered sensitivity and specificity when evaluating its performance, which were lower than the pooled accuracy.…”

Section: Discussionmentioning

confidence: 99%

The Performance of Wearable AI in Detecting Stress Among Students: Systematic Review and Meta-Analysis

Abd-alrazaq,

Alajlani,

Ahmad

et al. 2024

J Med Internet Res

View full text Add to dashboard Cite

Background Students usually encounter stress throughout their academic path. Ongoing stressors may lead to chronic stress, adversely affecting their physical and mental well-being. Thus, early detection and monitoring of stress among students are crucial. Wearable artificial intelligence (AI) has emerged as a valuable tool for this purpose. It offers an objective, noninvasive, nonobtrusive, automated approach to continuously monitor biomarkers in real time, thereby addressing the limitations of traditional approaches such as self-reported questionnaires. Objective This systematic review and meta-analysis aim to assess the performance of wearable AI in detecting and predicting stress among students. Methods Search sources in this review included 7 electronic databases (MEDLINE, Embase, PsycINFO, ACM Digital Library, Scopus, IEEE Xplore, and Google Scholar). We also checked the reference lists of the included studies and checked studies that cited the included studies. The search was conducted on June 12, 2023. This review included research articles centered on the creation or application of AI algorithms for the detection or prediction of stress among students using data from wearable devices. In total, 2 independent reviewers performed study selection, data extraction, and risk-of-bias assessment. The Quality Assessment of Diagnostic Accuracy Studies–Revised tool was adapted and used to examine the risk of bias in the included studies. Evidence synthesis was conducted using narrative and statistical techniques. Results This review included 5.8% (19/327) of the studies retrieved from the search sources. A meta-analysis of 37 accuracy estimates derived from 32% (6/19) of the studies revealed a pooled mean accuracy of 0.856 (95% CI 0.70-0.93). Subgroup analyses demonstrated that the accuracy of wearable AI was moderated by the number of stress classes (P=.02), type of wearable device (P=.049), location of the wearable device (P=.02), data set size (P=.009), and ground truth (P=.001). The average estimates of sensitivity, specificity, and F1-score were 0.755 (SD 0.181), 0.744 (SD 0.147), and 0.759 (SD 0.139), respectively. Conclusions Wearable AI shows promise in detecting student stress but currently has suboptimal performance. The results of the subgroup analyses should be carefully interpreted given that many of these findings may be due to other confounding factors rather than the underlying grouping characteristics. Thus, wearable AI should be used alongside other assessments (eg, clinical questionnaires) until further evidence is available. Future research should explore the ability of wearable AI to differentiate types of stress, distinguish stress from other mental health issues, predict future occurrences of stress, consider factors such as the placement of the wearable device and the methods used to assess the ground truth, and report detailed results to facilitate the conduct of meta-analyses. Trial Registration PROSPERO CRD42023435051; http://tinyurl.com/3fzb5rnp

show abstract

Section: Discussionmentioning

confidence: 99%

The Performance of Wearable AI in Detecting Stress Among Students: Systematic Review and Meta-Analysis

Abd-alrazaq,

Alajlani,

Ahmad

et al. 2024

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…Морозова и соавт. (2023), чувствительность ИИ в отношении выявления подозрительных очагов составляет 87 -100%, специфичность -68 -99%, общая точность 83,7 -98,3% (AUC достигает 0,99) [40]. По данным мета-анализа, общая чувствительность составляет 0,96 (I2 = 80,7%), а общая специфичность -0,95 (I2 = 86,1%).…”

Section: Discussionunclassified

Artificial intelligence in molecular and genomic prostate cancer diagnostics

Morozov,

Bazarkin,

Vovdenko

et al. 2024

Vestn. Urol.

Self Cite

View full text Add to dashboard Cite

Introduction. Many molecular genetic analyses have been proposed to predict the course of prostate cancer (PCa). They have the potential to develop artificial intelligence (AI) algorithms by processing large amounts of data and define connections between them.Objective. To evaluate the possibilities of using artificial intelligence in early diagnosis and prognosis of prostate cancer.Materials & methods. We conducted a systematic review of the literature on the Medline citation database. We have selected papers that provide data on the use of AI in vitro, in vivo and in silico systems to determine biological and genetic markers and/or their relationship to clinical data of PCa-patients from 2020 to 2023. The quantitative synthesis includes 16 articles.Results. AI can identify metabolic and genetic «signature» of PCa, the key elements of signal pathways, thus fulfilling complex tasks in the field of bioinformatics. AI analyses various biomaterials: prostate tissue, blood, and urine. When evaluating prostate tissue for aberrations, AI can help a pathologist. For example, AI can predict the histological status of genes, eliminating the need for IHC or tissue sequencing, significantly reducing the economic cost of predicting the severity of the disease. In most cases, prostate tissue sequencing provides information to the attending physician, allowing the start of optimal treatment, considering the molecular or genetic «signature» of PCa. AI can be used as an alternative to existing population screening tools and a predictive castration-resistant PCa. The use of AI capabilities is more appropriate for blood and urine analysis, procedures that do not require additional economic costs for biomaterial sampling. In theory, this may be more affordable for the patient and the medical institution. It is worth noting that a few studies were conducted in silico (based on the analysis of molecular genetic databases without validation on cell lines or on real patients) and are useful as background information. However, the results can serve as a robust basis for further research in molecular diagnostics and genomics.Conclusion. It is possible to use AI in the search for key metabolites and genes of the elements of signalling pathways, as well as the determination of metastasis potential, because molecular or genetic «signature» of PCa allows the physician to start optimal treatment.

show abstract

“…It is clear from this validation and the literature that AI algorithms can reach pathologist level accuracy. 5 , 6 , 7 The Galen™ Prostate AI algorithm was implemented in a second-read capacity at CorePlus driven by high sensitivity (96.1%) and NPV (99.1%) of reporting cancer vs benign.…”

Section: Discussionmentioning

confidence: 99%

“…These algorithms are particularly adept at recognizing intricate patterns including between benign and cancer as well as different Gleason grades, providing pathologists with invaluable support for more accurate and consistent diagnoses. 5 , 6 , 7 …”

Section: Introductionmentioning

confidence: 99%

Validation and three years of clinical experience in using an artificial intelligence algorithm as a second read system for prostate cancer diagnosis—real-world experience

Santa-Rosario,

Gustafson,

Sanabria Bellassai

et al. 2024

Journal of Pathology Informatics

View full text Add to dashboard Cite

A systematic review and meta-analysis of artificial intelligence diagnostic accuracy in prostate cancer histology identification and grading

Cited by 18 publications

References 53 publications

The Performance of Wearable AI in Detecting Stress Among Students: Systematic Review and Meta-Analysis

The Performance of Wearable AI in Detecting Stress Among Students: Systematic Review and Meta-Analysis

Artificial intelligence in molecular and genomic prostate cancer diagnostics

Validation and three years of clinical experience in using an artificial intelligence algorithm as a second read system for prostate cancer diagnosis—real-world experience

Contact Info

Product

Resources

About