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

Internal Medicine Internal Medicine

Effect of multimodal comprehensive communication skills training with video analysis by artificial intelligence for physicians on acute geriatric care: a mixed-methods study.

In BMJ open

OBJECTIVES : To quantitatively analyse by artificial intelligence (AI) the communication skills of physicians in an acute care hospital for geriatric care following a multimodal comprehensive care communication skills training programme and to qualitatively explore the educational benefits of this training programme.

DESIGN : A convergent mixed-methods study, including an intervention trial with a quasi-experimental design, was conducted to quantitatively analyse the communication skills of physicians. Qualitative data were collected via physicians' responses to an open-ended questionnaire administered after the training.

SETTING : An acute care hospital.

PARTICIPANTS : A total of 23 physicians.

INTERVENTIONS : In a 4-week multimodal comprehensive care communication skills training programme, including video lectures and bedside instruction, from May to October 2021, all the participants examined a simulated patient in the same scenario before and after their training. These examinations were video recorded by an eye-tracking camera and two fixed cameras. Then, the videos were analysed for communication skills by AI.

MAIN OUTCOME MEASURES : The primary outcomes were the physicians' eye contact, verbal expression, physical touch and multimodal communication skills with a simulated patient. The secondary outcomes were the physicians' empathy and burnout scores.

RESULTS : The proportion of the duration of the participants' single and multimodal types of communication significantly increased (p<0.001). The mean empathy scores and the personal accomplishment burnout scores also significantly increased after training. We developed a learning cycle model based on the six categories that changed after training from the physicians' perspective: multimodal comprehensive care communication skills training; increasing awareness of and sensitivity to changes to geriatric patients' condition; changes in clinical management; professionalism; team building and personal accomplishments.

CONCLUSIONS : Our study showed that multimodal comprehensive care communication skills training for physicians increased the proportions of time spent performing single and multimodal communication skills by video analysis through AI.

TRIAL REGISTRATION NUMBER : UMIN Clinical Trials Registry (UMIN000044288; https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000050586).

Kobayashi Masaki, Katayama Mitsuya, Hayashi Tomofumi, Hashiyama Takuhiro, Iyanagi Toshinori, Une Saki, Honda Miwako

2023-Mar-03

Dementia, GERIATRIC MEDICINE, INTERNAL MEDICINE, MEDICAL EDUCATION & TRAINING, QUALITATIVE RESEARCH

General General

Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.

In Computational intelligence and neuroscience

Malfunctions in the immune system cause multiple sclerosis (MS), which initiates mild to severe nerve damage. MS will disturb the signal communication between the brain and other body parts, and early diagnosis will help reduce the harshness of MS in humankind. Magnetic resonance imaging (MRI) supported MS detection is a standard clinical procedure in which the bio-image recorded with a chosen modality is considered to assess the severity of the disease. The proposed research aims to implement a convolutional neural network (CNN) supported scheme to detect MS lesions in the chosen brain MRI slices. The stages of this framework include (i) image collection and resizing, (ii) deep feature mining, (iii) hand-crafted feature mining, (iii) feature optimization with firefly algorithm, and (iv) serial feature integration and classification. In this work, five-fold cross-validation is executed, and the final result is considered for the assessment. The brain MRI slices with/without the skull section are examined separately, presenting the attained results. The experimental outcome of this study confirms that the VGG16 with random forest (RF) classifier offered a classification accuracy of >98% MRI with skull, and VGG16 with K-nearest neighbor (KNN) provided an accuracy of >98% without the skull.

Krishnamoorthy Sujatha, Zhang Yaxi, Kadry Seifedine, Khan Muhammad Attique, Alhaisoni Majed, Mustafa Nasser, Yu Weifeng, Alqahtani Abdullah

2023

oncology Oncology

Liquid biopsy-based protein biomarkers for risk prediction, early diagnosis and prognostication of cholangiocarcinoma.

In Journal of hepatology ; h5-index 119.0

BACKGROUND & AIMS : Cholangiocarcinoma (CCA), heterogeneous biliary tumors with dismal prognosis, lacks accurate early diagnostic methods, especially important for individuals at high-risk (i.e., primary sclerosing cholangitis (PSC)). Here, we searched for protein biomarkers in serum extracellular vesicles (EVs).

METHODS : EVs from patients with isolated PSC (n=45), concomitant PSC-CCA (n=44), PSC who developed CCA during follow-up (PSC to CCA; n=25), CCAs from non-PSC etiology (n=56), hepatocellular carcinoma (HCC; n=34) and healthy individuals (n=56) were characterized by mass-spectrometry. Diagnostic biomarkers for PSC-CCA, non-PSC CCA or CCAs regardless etiology (Pan-CCAs) were defined and validated by ELISA. Their expression was evaluated in CCA tumors at single-cell level. Prognostic EV-biomarkers for CCA were investigated.

RESULTS : High-throughput proteomics of EVs identified diagnostic biomarkers for PSC-CCA, non-PSC CCA or Pan-CCA, and for the differential diagnosis of intrahepatic CCA and HCC, that were cross-validated by ELISA using total serum. Machine learning-based algorithms disclosed CRP/FIBRINOGEN/FRIL for the diagnosis of PSC-CCA (local disease (LD)) vs isolated PSC (AUC=0.947;OR=36.9), and combined with CA19-9, overpowers CA19-9 alone. CRP/PIGR/VWF allowed the diagnosis of LD non-PSC CCAs vs healthy individuals (AUC=0.992;OR=387.5). Noteworthy, CRP/FRIL accurately diagnosed LD Pan-CCA (AUC=0.941;OR=89.4). Levels of CRP/FIBRINOGEN/FRIL/PIGR showed predictive capacity for CCA development in PSC before clinical evidences of malignancy. Multi-organ transcriptomic analysis revealed that serum EV-biomarkers were mostly expressed in hepatobiliary tissues, and scRNA-seq and immunofluorescence analysis of CCA tumors showed their presence mainly in malignant cholangiocytes. Multivariable analysis unveiled EV-prognostic biomarkers, with COMP/GNAI2/CFAI and ACTN1/MYCT1/PF4V associated negatively or positively to patients' survival, respectively.

CONCLUSIONS : Serum EVs contain protein biomarkers for the prediction, early diagnosis and prognosis estimation of CCA detectable using total serum, representing a tumor cell-derived liquid biopsy tool for personalized medicine.

IMPACT AND IMPLICATIONS : The accuracy of current imaging tests and circulating tumor biomarkers for cholangiocarcinoma (CCA) diagnosis is far from satisfactory. Most CCAs are considered sporadic, although up to 20% of patients with primary sclerosing cholangitis (PSC) develop CCA during their lifetime, constituting a major cause of PSC-related death. This international study has proposed protein-based and etiology-related logistic models with predictive, diagnostic or prognostic capacities by combining 2-4 circulating protein biomarkers, moving a step forward into personalized medicine. These novel liquid biopsy tools may allow the: i) easy and non-invasive diagnosis of sporadic CCAs, ii) identification of patients with PSC with higher risk for CCA development, iii) establishment of cost-effective surveillance programs for the early detection of CCA in high-risk populations (e.g., PSC), and iv) prognostic stratification of patients with CCA, which, altogether, may increase the number of cases eligible for potentially curative options or to receive more successful treatments, decreasing CCA-related mortality.

Lapitz Ainhoa, Azkargorta Mikel, Milkiewicz Piotr, Olaizola Paula, Zhuravleva Ekaterina, Grimsrud Marit M, Schramm Christoph, Arbelaiz Ander, O’Rourke Colm J, La Casta Adelaida, Milkiewicz Malgorzata, Pastor Tania, Vesterhus Mette, Jimenez-Agüero Raul, Dill Michael T, Lamarca Angela, Valle Juan W, Macias Rocio I R, Izquierdo-Sanchez Laura, Castaño Ylenia Pérez, Caballero-Camino Francisco Javier, Riaño Ioana, Krawczyk Marcin, Ibarra Cesar, Bustamante Javier, Nova-Camacho Luiz M, Falcon-Perez Juan M, Elortza Felix, Perugorria Maria J, Andersen Jesper B, Bujanda Luis, Karlsen Tom H, Folseraas Trine, Rodrigues Pedro M, Banales Jesus M

2023-Mar-01

Cholangiocarcinoma, extracellular vesicles, liquid biopsy, mass spectrometry, primary sclerosing cholangitis, protein biomarkers, single-cell RNA-sequencing

General General

In silico approaches for prediction of anti-CRISPR proteins.

In Journal of molecular biology ; h5-index 65.0

Numerous viruses infecting bacteria and archaea encode CRISPR-Cas system inhibitors, known as anti-CRISPR proteins (Acr). The Acrs typically are highly specific for particular CRISPR variants, resulting in remarkable sequence and structural diversity and complicating accurate prediction and identification of Acrs. In addition to their intrinsic interest for understanding the coevolution of defense and counter-defense systems in prokaryotes, Acrs could be natural, potent on-off switches for CRISPR-based biotechnological tools, so their discovery, characterization and application are of major importance. Here we discuss the computational approaches for Acr prediction. Due to the enormous diversity and likely multiple origins of the Acrs, sequence similarity searches are of limited use. However, multiple features of protein and gene organization have been successfully harnessed to this end including small protein size and distinct amino acid compositions of the Acrs, association of acr genes in virus genomes with genes encoding helix-turn-helix proteins that regulate Acr expression (Acr-associated proteins, Aca), and presence of self-targeting CRISPR spacers in bacterial and archaeal genomes containing Acr-encoding proviruses. Productive approaches for Acr prediction also involve genome comparison of closely related viruses, of which one is resistant and the other one is sensitive to a particular CRISPR variant, and "guilt by association" whereby genes adjacent to a homolog of a known Aca are identified as candidate Acrs. The distinctive features of Acrs are employed for Acr prediction both by developing dedicated search algorithms and through machine learning. New approaches will be needed to identify novel types of Acrs that are likely to exist.

Makarova Kira S, I Wolf Yuri, V Koonin Eugene

2023-Mar-01

anti-CRISPR proteins, comparative genomics, guilt-by-association, machine learning, self-targeting

oncology Oncology

Towards Artificial Intelligence to Multi-omics Characterization of Tumor Heterogeneity in Esophageal Cancer.

In Seminars in cancer biology

Esophageal cancer is a unique and complex heterogeneous malignancy, with substantial tumor heterogeneity: at the cellular levels, tumors are composed of tumor and stromal cellular components; at the genetic levels, they comprise genetically distinct tumor clones; at the phenotypic levels, cells in distinct microenvironmental niches acquire diverse phenotypic features. This heterogeneity affects almost every process of esophageal cancer progression from onset to metastases and recurrence, etc. Intertumoral and intratumoral heterogeneity are major obstacles in the treatment of esophageal cancer, but also offer the potential to manipulate the heterogeneity themselves as a new therapeutic strategy. The high-dimensional, multi-faceted characterization of genomics, epigenomics, transcriptomics, proteomics, metabonomics, etc. of esophageal cancer has opened novel horizons for dissecting tumor heterogeneity. Artificial intelligence especially machine learning and deep learning algorithms, are able to make decisive interpretations of data from multi-omics layers. To date, artificial intelligence has emerged as a promising computational tool for analyzing and dissecting esophageal patient-specific multi-omics data. This review provides a comprehensive review of tumor heterogeneity from a multi-omics perspective. Especially, we discuss the novel techniques single-cell sequencing and spatial transcriptomics, which have revolutionized our understanding of the cell compositions of esophageal cancer and allowed us to determine novel cell types. We focus on the latest advances in artificial intelligence in integrating multi-omics data of esophageal cancer. Artificial intelligence-based multi-omics data integration computational tools exert a key role in tumor heterogeneity assessment, which will potentially boost the development of precision oncology in esophageal cancer.

Li Junyu, Li Lin, You Peimeng, Wei Yiping, Xu Bin

2023-Mar-01

artificial intelligence, esophageal cancer, multi-omics, tumor heterogeneity, tumor microenvironment

Ophthalmology Ophthalmology

Differentiating Glaucomatous Optic Neuropathy from Non-Glaucomatous Optic Neuropathies Using Deep Learning Algorithms.

In American journal of ophthalmology ; h5-index 67.0

PURPOSE : A deep learning framework to differentiate glaucomatous optic disc changes (GON) from non-glaucomatous optic neuropathy-related disc changes (NGON).

DESIGN : Cross-sectional study.

METHOD : A deep-learning system was trained, validated, and externally tested to classify optic discs as normal, GON, or NGON using 2,183 digital color fundus photographs. A Single-Center data set of 1,822 images-660 images of NGON, 676 images of GON, and 486 images of normal optic discs-was used for training and validation, whereas 361 photographs from four different data sets were used for external testing. Our algorithm removed the redundant information from the images using an optic disc segmentation (OD-SEG) network, following which we performed transfer learning with various pre-trained networks. Finally, we calculated sensitivity, specificity, F1-score, and precision to show the performance of the discrimination network in the validation and independent external data set.

RESULTS : For classification, the algorithm with the best performance for the Single-Center data set was DenseNet121, with a sensitivity of 95.36%, precision of 95.35%, specificity of 92.19%, and F1 score of 95.40%. For the external validation data, the sensitivity and specificity of our network for differentiating GON from NGON were 85.53% and 89.02%, respectively. The glaucoma specialist who diagnosed those cases in masked fashion, had a sensitivity of 71.05% and a specificity of 82.21%.

CONCLUSIONS : The proposed algorithm for the differentiation of GON from NGON yields results that have a higher sensitivity than those of a glaucoma specialist, and its application for unseen data thus is extremely promising.

Vali Mahsa, Mohammadi Massoud, Zarei Nasim, Samadi Melika, Atapour-Abarghouei Amir, Supakontanasan Wasu, Suwan Yanin, Subramanian Prem S, Miller Neil R, Kafieh Rahele, Fard Masoud Aghsaei

2023-Mar-01