Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Disrupting 3D printing of medicines with machine learning.

In Trends in pharmacological sciences ; h5-index 70.0

3D printing (3DP) is a progressive technology capable of transforming pharmaceutical development. However, despite its promising advantages, its transition into clinical settings remains slow. To make the vital leap to mainstream clinical practice and improve patient care, 3DP must harness modern technologies. Machine learning (ML), an influential branch of artificial intelligence, may be a key partner for 3DP. Together, 3DP and ML can utilise intelligence based on human learning to accelerate drug product development, ensure stringent quality control (QC), and inspire innovative dosage-form design. With ML's capabilities, streamlined 3DP drug delivery could mark the next era of personalised medicine. This review details how ML can be applied to elevate the 3DP of pharmaceuticals and importantly, how it can expedite 3DP's integration into mainstream healthcare.

Elbadawi Moe, McCoubrey Laura E, Gavins Francesca K H, Ong Jun J, Goyanes Alvaro, Gaisford Simon, Basit Abdul W


3D Printed drug products and formulations, Industry 4.0 and digital health, additive manufacturing, biomedical engineering and pharmaceutical sciences, personalized oral drug delivery systems and medical devices, translational pharmaceutics

Surgery Surgery

Automatically Delineating Key Anatomy in 3-D Ultrasound Volumes for Hip Dysplasia Screening.

In Ultrasound in medicine & biology ; h5-index 42.0

Developmental dysplasia of the hip (DDH) metrics based on 3-D ultrasound have proven more reliable than those based on 2-D images, but to date have been based mainly on hand-engineered features. Here, we test the performance of 3-D convolutional neural networks for automatically segmenting and delineating the key anatomical structures used to define DDH metrics: the pelvis bone surface and the femoral head. Our models are trained and tested on a data set of 136 volumes from 34 participants. For the pelvis, a 3D-U-Net achieves a Dice score of 85%, outperforming the confidence-weighted structured phase symmetry algorithm (Dice score = 19%). For the femoral head, the 3D-U-Net had centre and radius errors of 1.42 and 0.46 mm, respectively, outperforming the random forest classifier (3.90 and 2.01 mm). The improved segmentation may improve DDH measurement accuracy and reliability, which could reduce misdiagnosis.

El-Hariri Houssam, Hodgson Antony J, Mulpuri Kishore, Garbi Rafeef


Bone, Convolutional neural network, Deep learning, Hip dysplasia, Image processing, Machine learning, Orthopedics, Segmentation, Ultrasound

General General

Classification of environmental factors potentially motivating for dairy cows to access shade.

In The Journal of dairy research

The aim of this Research Communication was to apply the data mining technique to classify which environmental factors have the potential to motivate dairy cows to access natural shade. We defined two different areas at the silvopastoral system: shaded and sunny. Environmental factors and the frequency that dairy cows used each area were measured during four days, for 8 h each day. The shaded areas were the most used by dairy cows and presented the lowest mean values of all environmental factors. Solar radiation was the environmental factor with most potential to classify the dairy cow's decision to access shaded areas. Data mining is a machine learning technique with great potential to characterize the influence of the thermal environment in the cows' decision at the pasture.

Deniz Matheus, de Sousa Karolini Tenffen, Gomes Isabelle Cordova, Vale Marcos Martinez do, Dittrich João Ricardo


animal distribution, behavioural pattern, decision tree, pasture, precision livestock farming

General General

Identification and prediction of difficult-to-treat rheumatoid arthritis patients in structured and unstructured routine care data: results from a hackathon.

In Arthritis research & therapy ; h5-index 60.0

BACKGROUND : The new concept of difficult-to-treat rheumatoid arthritis (D2T RA) refers to RA patients who remain symptomatic after several lines of treatment, resulting in a high patient and economic burden. During a hackathon, we aimed to identify and predict D2T RA patients in structured and unstructured routine care data.

METHODS : Routine care data of 1873 RA patients were extracted from the Utrecht Patient Oriented Database. Data from a previous cross-sectional study, in which 152 RA patients were clinically classified as either D2T or non-D2T, served as a validation set. Machine learning techniques, text mining, and feature importance analyses were performed to identify and predict D2T RA patients based on structured and unstructured routine care data.

RESULTS : We identified 123 potentially new D2T RA patients by applying the D2T RA definition in structured and unstructured routine care data. Additionally, we developed a D2T RA identification model derived from a feature importance analysis of all available structured data (AUC-ROC 0.88 (95% CI 0.82-0.94)), and we demonstrated the potential of longitudinal hematological data to differentiate D2T from non-D2T RA patients using supervised dimension reduction. Lastly, using data up to the time of starting the first biological treatment, we predicted future development of D2TRA (AUC-ROC 0.73 (95% CI 0.71-0.75)).

CONCLUSIONS : During this hackathon, we have demonstrated the potential of different techniques for the identification and prediction of D2T RA patients in structured as well as unstructured routine care data. The results are promising and should be optimized and validated in future research.

Messelink Marianne A, Roodenrijs Nadia M T, van Es Bram, Hulsbergen-Veelken Cornelia A R, Jong Sebastiaan, Overmars L Malin, Reteig Leon C, Tan Sander C, Tauber Tjebbe, van Laar Jacob M, Welsing Paco M J, Haitjema Saskia


Applied data analytics in medicine, Difficult-to-treat rheumatoid arthritis, Machine learning, Routine care data

General General

Explaining multivariate molecular diagnostic tests via Shapley values.

In BMC medical informatics and decision making ; h5-index 38.0

BACKGROUND : Machine learning (ML) can be an effective tool to extract information from attribute-rich molecular datasets for the generation of molecular diagnostic tests. However, the way in which the resulting scores or classifications are produced from the input data may not be transparent. Algorithmic explainability or interpretability has become a focus of ML research. Shapley values, first introduced in game theory, can provide explanations of the result generated from a specific set of input data by a complex ML algorithm.

METHODS : For a multivariate molecular diagnostic test in clinical use (the VeriStrat® test), we calculate and discuss the interpretation of exact Shapley values. We also employ some standard approximation techniques for Shapley value computation (local interpretable model-agnostic explanation (LIME) and Shapley Additive Explanations (SHAP) based methods) and compare the results with exact Shapley values.

RESULTS : Exact Shapley values calculated for data collected from a cohort of 256 patients showed that the relative importance of attributes for test classification varied by sample. While all eight features used in the VeriStrat® test contributed equally to classification for some samples, other samples showed more complex patterns of attribute importance for classification generation. Exact Shapley values and Shapley-based interaction metrics were able to provide interpretable classification explanations at the sample or patient level, while patient subgroups could be defined by comparing Shapley value profiles between patients. LIME and SHAP approximation approaches, even those seeking to include correlations between attributes, produced results that were quantitatively and, in some cases qualitatively, different from the exact Shapley values.

CONCLUSIONS : Shapley values can be used to determine the relative importance of input attributes to the result generated by a multivariate molecular diagnostic test for an individual sample or patient. Patient subgroups defined by Shapley value profiles may motivate translational research. However, correlations inherent in molecular data and the typically small ML training sets available for molecular diagnostic test development may cause some approximation methods to produce approximate Shapley values that differ both qualitatively and quantitatively from exact Shapley values. Hence, caution is advised when using approximate methods to evaluate Shapley explanations of the results of molecular diagnostic tests.

Roder Joanna, Maguire Laura, Georgantas Robert, Roder Heinrich


Artificial intelligence, Explainability, Interpretability, Machine learning, Molecular diagnostic test, Shapley values

Ophthalmology Ophthalmology

Corneal pachymetry by AS-OCT after Descemet's membrane endothelial keratoplasty.

In Scientific reports ; h5-index 158.0

Corneal thickness (pachymetry) maps can be used to monitor restoration of corneal endothelial function, for example after Descemet's membrane endothelial keratoplasty (DMEK). Automated delineation of the corneal interfaces in anterior segment optical coherence tomography (AS-OCT) can be challenging for corneas that are irregularly shaped due to pathology, or as a consequence of surgery, leading to incorrect thickness measurements. In this research, deep learning is used to automatically delineate the corneal interfaces and measure corneal thickness with high accuracy in post-DMEK AS-OCT B-scans. Three different deep learning strategies were developed based on 960 B-scans from 50 patients. On an independent test set of 320 B-scans, corneal thickness could be measured with an error of 13.98 to 15.50 μm for the central 9 mm range, which is less than 3% of the average corneal thickness. The accurate thickness measurements were used to construct detailed pachymetry maps. Moreover, follow-up scans could be registered based on anatomical landmarks to obtain differential pachymetry maps. These maps may enable a more comprehensive understanding of the restoration of the endothelial function after DMEK, where thickness often varies throughout different regions of the cornea, and subsequently contribute to a standardized postoperative regime.

Heslinga Friso G, Lucassen Ruben T, van den Berg Myrthe A, van der Hoek Luuk, Pluim Josien P W, Cabrerizo Javier, Alberti Mark, Veta Mitko