Artificial intelligence and machine learning overview in pathology &amp; laboratory medicine: A general review of data preprocessing and basic supervised concepts

Albahra, Samer; Gorbett, Tom; Robertson, Scott; D'Aleo, Giana; Kumar, Sushasree Vasudevan Suseel; Ockunzzi, Samuel; Lallo, Daniel; Hu, Bo; Rashidi, Hooman H.

doi:10.1053/j.semdp.2023.02.002

Cited by 64 publications

(31 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data drift is a concept of input data gradually changing over time [36], for example, changes in stain appearance. This can result in differing performance of a deep learning model.…”

Section: Challenges In Implementation In Clinical Practicementioning

confidence: 99%

Deep learning applications for kidney histology analysis

Pilva,

Bülow,

Boor

2024

Current Opinion in Nephrology &Amp; Hypertension

View full text Add to dashboard Cite

Purpose of review Nephropathology is increasingly incorporating computational methods to enhance research and diagnostic accuracy. The widespread adoption of digital pathology, coupled with advancements in deep learning, will likely transform our pathology practices. Here, we discuss basic concepts of deep learning, recent applications in nephropathology, current challenges in implementation and future perspectives. Recent findings Deep learning models have been developed and tested in various areas of nephropathology, for example, predicting kidney disease progression or diagnosing diseases based on imaging and clinical data. Despite their promising potential, challenges remain that hinder a wider adoption, for example, the lack of prospective evidence and testing in real-world scenarios. Summary Deep learning offers great opportunities to improve quantitative and qualitative kidney histology analysis for research and clinical nephropathology diagnostics. Although exciting approaches already exist, the potential of deep learning in nephropathology is only at its beginning and we can expect much more to come.

show abstract

“…Data drift is a concept of input data gradually changing over time [36], for example, changes in stain appearance. This can result in differing performance of a deep learning model.…”

Section: Challenges In Implementation In Clinical Practicementioning

confidence: 99%

Deep learning applications for kidney histology analysis

Pilva,

Bülow,

Boor

2024

Current Opinion in Nephrology &Amp; Hypertension

View full text Add to dashboard Cite

show abstract

“…It is essential to gather representative data for training the model, adhering to the well-known principle of “garbage in, garbage out” [ 3 ]. Traditionally, many of these preprocessing tasks have been performed manually, but powerful data science applications have now emerged, accelerating these processes through automatization [ 4 ]. The development and validation of ML models involve a systematic approach using three distinct datasets.…”

Section: Machine Learningmentioning

confidence: 99%

“…These models operate by learning from labeled data, aiming to establish a robust relationship between input variables and a target outcome, such as classifying diagnoses [ 1 , 2 , 6 ]. In medical modeling, the generation of novel insightful features is more crucial than relying solely on existing predictors or advanced algorithms, as this is unlikely to lead to significant discoveries [ 2 , 4 ]. Unsupervised learning focuses on extracting structures and patterns from unlabeled datasets.…”

Section: Machine Learningmentioning

confidence: 99%

Application of Machine Learning in Chronic Kidney Disease: Current Status and Future Prospects

Delrue,

De Bruyne,

Speeckaert

2024

Biomedicines

View full text Add to dashboard Cite

The emergence of artificial intelligence and machine learning (ML) has revolutionized the landscape of clinical medicine, offering opportunities to improve medical practice and research. This narrative review explores the current status and prospects of applying ML to chronic kidney disease (CKD). ML, at the intersection of statistics and computer science, enables computers to derive insights from extensive datasets, thereby presenting an interesting landscape for constructing statistical models and improving data interpretation. The integration of ML into clinical algorithms aims to increase efficiency and promote its adoption as a standard approach to data interpretation in nephrology. As the field of ML continues to evolve, collaboration between clinicians and data scientists is essential for defining data-sharing and usage policies, ultimately contributing to the advancement of precision diagnostics and personalized medicine in the context of CKD.

show abstract

“…Pre‐processing refines the cleaned data to ensure it is optimal for model training. Feature scaling, such as normalization and standardization, 18 is performed to standardize the independent variables in the data set, ensure that they are contributing equally to model training and enhancing performance. Weighting strategies can be adopted to adjust feature influence.…”

Section: Fundamentals Of Using Ai/mlmentioning

confidence: 99%

Artificial Intelligence: From Buzzword to Useful Tool in Clinical Pharmacology

Shahin,

Barth,

Podichetty

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

The advent of artificial intelligence (AI) in clinical pharmacology and drug development is akin to the dawning of a new era. Previously dismissed as merely technological hype, these approaches have emerged as promising tools in different domains, including healthcare, demonstrating their potential to empower clinical pharmacology decision‐making, revolutionize the drug development landscape, and advance patient care. While challenges remain, the remarkable progress already made signals that the leap from hype to reality is well underway, and AI promises to offer clinical pharmacology new tools and possibilities for optimizing patient care is gradually coming to fruition. This review dives into the burgeoning world of AI and machine learning (ML), showcasing different applications of AI in clinical pharmacology and the impact of successful AI/ML implementation on drug development and/or regulatory decisions. This review also highlights recommendations for areas of opportunity in clinical pharmacology, including data analysis (e.g., handling large datasets, screening to identify important covariates, optimizing patient population) and efficiencies (e.g., automation, translation, literature curation, training). Realizing the benefits of AI in drug development and understanding its value will lead to the successful integration of AI tools in our clinical pharmacology and pharmacometrics armamentarium.

show abstract

Artificial intelligence and machine learning overview in pathology & laboratory medicine: A general review of data preprocessing and basic supervised concepts

Cited by 64 publications

References 30 publications

Deep learning applications for kidney histology analysis

Deep learning applications for kidney histology analysis

Application of Machine Learning in Chronic Kidney Disease: Current Status and Future Prospects

Artificial Intelligence: From Buzzword to Useful Tool in Clinical Pharmacology

Contact Info

Product

Resources

About