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

Public Health Public Health

Rapid direct analysis of river water and machine learning assisted suspect screening of emerging contaminants in passive sampler extracts.

In Analytical methods : advancing methods and applications

A novel and rapid approach to characterise the occurrence of contaminants of emerging concern (CECs) in river water is presented using multi-residue targeted analysis and machine learning-assisted in silico suspect screening of passive sampler extracts. Passive samplers (Chemcatcher®) configured with hydrophilic-lipophilic balanced (HLB) sorbents were deployed in the Central London region of the tidal River Thames (UK) catchment in winter and summer campaigns in 2018 and 2019. Extracts were analysed by; (a) a rapid 5.5 min direct injection targeted liquid chromatography-tandem mass spectrometry (LC-MS/MS) method for 164 CECs and (b) a full-scan LC coupled to quadrupole time of flight mass spectrometry (QTOF-MS) method using data-independent acquisition over 15 min. From targeted analysis of grab water samples, a total of 33 pharmaceuticals, illicit drugs, drug metabolites, personal care products and pesticides (including several EU Watch-List chemicals) were identified, and mean concentrations determined at 40 ± 37 ng L-1. For targeted analysis of passive sampler extracts, 65 unique compounds were detected with differences observed between summer and winter campaigns. For suspect screening, 59 additional compounds were shortlisted based on mass spectral database matching, followed by machine learning-assisted retention time prediction. Many of these included additional pharmaceuticals and pesticides, but also new metabolites and industrial chemicals. The novelty in this approach lies in the convenience of using passive samplers together with machine learning-assisted chemical analysis methods for rapid, time-integrated catchment monitoring of CECs.

Richardson Alexandra K, Chadha Marcus, Rapp-Wright Helena, Mills Graham A, Fones Gary R, Gravell Anthony, Stürzenbaum Stephen, Cowan David A, Neep David J, Barron Leon P


Pathology Pathology

Prognostic mutation constellations in acute myeloid leukaemia and myelodysplastic syndrome.

In Current opinion in hematology

PURPOSE OF REVIEW : In the past decade, numerous studies analysing the genome and transcriptome of large cohorts of acute myeloid leukaemia (AML) and myelodysplastic syndrome (MDS) patients have substantially improved our knowledge of the genetic landscape of these diseases with the identification of heterogeneous constellations of germline and somatic mutations with prognostic and therapeutic relevance. However, inclusion of integrated genetic data into classification schema is still far from a reality. The purpose of this review is to summarize recent insights into the prevalence, pathogenic role, clonal architecture, prognostic impact and therapeutic management of genetic alterations across the spectrum of myeloid malignancies.

RECENT FINDINGS : Recent multiomic-studies, including analysis of genetic alterations at the single-cell resolution, have revealed a high heterogeneity of lesions in over 200 recurrently mutated genes affecting disease initiation, clonal evolution and clinical outcome. Artificial intelligence and specifically machine learning approaches have been applied to large cohorts of AML and MDS patients to define in an unbiased manner clinically meaningful disease patterns including, disease classification, prognostication and therapeutic vulnerability, paving the way for future use in clinical practice.

SUMMARY : Integration of genomic, transcriptomic, epigenomic and clinical data coupled to conventional and machine learning approaches will allow refined leukaemia classification and risk prognostication and will identify novel therapeutic targets for these still high-risk leukaemia subtypes.

Iacobucci Ilaria, Mullighan Charles G


Public Health Public Health

Automatic Subtyping of Individuals with Primary Progressive Aphasia.

In Journal of Alzheimer's disease : JAD

BACKGROUND : The classification of patients with primary progressive aphasia (PPA) into variants is time-consuming, costly, and requires combined expertise by clinical neurologists, neuropsychologists, speech pathologists, and radiologists.

OBJECTIVE : The aim of the present study is to determine whether acoustic and linguistic variables provide accurate classification of PPA patients into one of three variants: nonfluent PPA, semantic PPA, and logopenic PPA.

METHODS : In this paper, we present a machine learning model based on deep neural networks (DNN) for the subtyping of patients with PPA into three main variants, using combined acoustic and linguistic information elicited automatically via acoustic and linguistic analysis. The performance of the DNN was compared to the classification accuracy of Random Forests, Support Vector Machines, and Decision Trees, as well as to expert clinicians' classifications.

RESULTS : The DNN model outperformed the other machine learning models as well as expert clinicians' classifications with 80% classification accuracy. Importantly, 90% of patients with nfvPPA and 95% of patients with lvPPA was identified correctly, providing reliable subtyping of these patients into their corresponding PPA variants.

CONCLUSION : We show that the combined speech and language markers from connected speech productions can inform variant subtyping in patients with PPA. The end-to-end automated machine learning approach we present can enable clinicians and researchers to provide an easy, quick, and inexpensive classification of patients with PPA.

Themistocleous Charalambos, Ficek Bronte, Webster Kimberly, den Ouden Dirk-Bart, Hillis Argye E, Tsapkini Kyrana


Classification, machine learning, natural language processing, primary progressive aphasia

General General

Effect of grape seed proanthocyanidins on activity of HaCaT cells in mice based on deep learning image processing.

In Technology and health care : official journal of the European Society for Engineering and Medicine

BACKGROUND : Grape seed proanthocyanidin extract (GSPE) has a certain resistance to contrast light, which makes the boundary of the imaging image unclear.

OBJECTIVE : Because of this, an image processing algorithm is needed to process the contrast image to study the role of GSPE in the process of anti-ultraviolet.

METHODS : In this paper, the fuzzy edges of contrast images were processed by deep learning algorithm, and the changes of VEGF and PEDF expression in HaCaT cells before and after UVA irradiation and after GSPE intervention were studied.

RESULTS : The experiment results show that after processing, the edge and boundary of the image become clear and separable, which can be used to compare and analyze the test process. The image comparison results show that GSPE can down regulate the expression of VEGF gene and protein, and up regulate the expression of PEDF gene and protein. The synergistic effect of GSPE and GSPE can inhibit angiogenesis. It is confirmed that GSPE has the effect of anti-ultraviolet ray induced early angiogenesis.

Xu Feng, Huang Jia


HaCaT cells, SURF, binary image, deep learning

General General

A novel method for automatic classification of Parkinson gait severity using front-view video analysis.

In Technology and health care : official journal of the European Society for Engineering and Medicine

BACKGROUND : Gait impairment is an essential symptom of Parkinson's disease (PD).

OBJECTIVE : This paper introduces a novel computer-vision framework for automatic classification of the severity of gait impairment using front-view motion analysis.

METHODS : Four hundred and fifty-six videos were recorded from 19 PD patients using an RGB camera during clinical gait assessment. Gait performance in each video was rated by a neurologist using the unified Parkinson's disease rating scale for gait examination (UPDRS-gait). The proposed algorithm detects and tracks the silhouette of the test subject in the video to generate a height signal. Gait features were extracted from the height signal. Feature analysis was performed using the Kruskal-Wallis rank test. A support vector machine was trained using the features to classify the severity levels according to UPDRS-gait in 10-fold cross-validation.

RESULTS : Features significantly (p< 0.05) differentiated between median-ranks of UPDRS-gait levels. The SVM classified the levels with a promising area under the ROC of 80.88%.

CONCLUSION : Findings support the feasibility of this model for Parkinson's gait assessment in the home environment.

Khan Taha, Zeeshan Ali, Dougherty Mark


Parkinson’s disease, computervision, gait impairment, motion analysis

General General

Clinical Advice by Voice Assistants on Postpartum Depression: Cross-Sectional Investigation Using Apple Siri, Amazon Alexa, Google Assistant, and Microsoft Cortana.

In JMIR mHealth and uHealth

BACKGROUND : A voice assistant (VA) is inanimate audio-interfaced software augmented with artificial intelligence, capable of 2-way dialogue, and increasingly used to access health care advice. Postpartum depression (PPD) is a common perinatal mood disorder with an annual estimated cost of $14.2 billion. Only a small percentage of PPD patients seek care due to lack of screening and insufficient knowledge of the disease, and this is, therefore, a prime candidate for a VA-based digital health intervention.

OBJECTIVE : In order to understand the capability of VAs, our aim was to assess VA responses to PPD questions in terms of accuracy, verbal response, and clinically appropriate advice given.

METHODS : This cross-sectional study examined four VAs (Apple Siri, Amazon Alexa, Google Assistant, and Microsoft Cortana) installed on two mobile devices in early 2020. We posed 14 questions to each VA that were retrieved from the American College of Obstetricians and Gynecologists (ACOG) patient-focused Frequently Asked Questions (FAQ) on PPD. We scored the VA responses according to accuracy of speech recognition, presence of a verbal response, and clinically appropriate advice in accordance with ACOG FAQ, which were assessed by two board-certified physicians.

RESULTS : Accurate recognition of the query ranged from 79% to 100%. Verbal response ranged from 36% to 79%. If no verbal response was given, queries were treated like a web search between 33% and 89% of the time. Clinically appropriate advice given by VA ranged from 14% to 29%. We compared the category proportions using the Fisher exact test. No single VA statistically outperformed other VAs in the three performance categories. Additional observations showed that two VAs (Google Assistant and Microsoft Cortana) included advertisements in their responses.

CONCLUSIONS : While the best performing VA gave clinically appropriate advice to 29% of the PPD questions, all four VAs taken together achieved 64% clinically appropriate advice. All four VAs performed well in accurately recognizing a PPD query, but no VA achieved even a 30% threshold for providing clinically appropriate PPD information. Technology companies and clinical organizations should partner to improve guidance, screen patients for mental health disorders, and educate patients on potential treatment.

Yang Samuel, Lee Jennifer, Sezgin Emre, Bridge Jeffrey, Lin Simon


conversational agent, mental health, mobile health, postpartum depression, virtual assistant, voice assistant