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

General General

Artificial intelligence applications in solid waste management: A systematic research review.

In Waste management (New York, N.Y.)

The waste management processes typically involve numerous technical, climatic, environmental, demographic, socio-economic, and legislative parameters. Such complex nonlinear processes are challenging to model, predict and optimize using conventional methods. Recently, artificial intelligence (AI) techniques have gained momentum in offering alternative computational approaches to solve solid waste management (SWM) problems. AI has been efficient at tackling ill-defined problems, learning from experience, and handling uncertainty and incomplete data. Although significant research was carried out in this domain, very few review studies have assessed the potential of AI in solving the diverse SWM problems. This systematic literature review compiled 85 research studies, published between 2004 and 2019, analyzing the application of AI in various SWM fields, including forecasting of waste characteristics, waste bin level detection, process parameters prediction, vehicle routing, and SWM planning. This review provides comprehensive analysis of the different AI models and techniques applied in SWM, application domains and reported performance parameters, as well as the software platforms used to implement such models. The challenges and insights of applying AI techniques in SWM are also discussed.

Abdallah Mohamed, Abu Talib Manar, Feroz Sainab, Nasir Qassim, Abdalla Hadeer, Mahfood Bayan


Artificial intelligence, Deep learning, Machine learning, Modeling, Neural networks, Optimization

Surgery Surgery

Does the SORG Algorithm Generalize to a Contemporary Cohort of Patients with Spinal Metastases on External Validation?

In The spine journal : official journal of the North American Spine Society

BACKGROUND CONTEXT : The SORG machine learning (ML) algorithms were previously developed for preoperative prediction of overall survival in spinal metastatic disease. On sub-group analysis of a previous external validation, these algorithms were found to have diminished performance on patients treated after 2010.

PURPOSE : The purpose of this study was to assess the performance of these algorithms on a large contemporary cohort of consecutive spinal metastatic disease patients.

STUDY DESIGN/SETTING : Retrospective study performed at a tertiary care referral center.

PATIENT SAMPLE : Patients of 18 years and older treated with surgery for metastatic spinal disease between 2014 and 2016 OUTCOME MEASURES: Ninety-day and one-year mortality METHODS: Baseline patient and tumor characteristics of the validation cohort were compared to the development cohort using bivariate logistic regression. Performance of the SORG algorithms on external validation in the contemporary cohort was assessed with discrimination (c-statistic and receiver operating curve), calibration (calibration plot, intercept, and slope), overall performance (Brier score compared to the null-model Brier score), and decision curve analysis.

RESULTS : Overall, 200 patients were included with ninety-day and one-year mortality rates of 55 (27.6%) and 124 (62.9%), respectively. The contemporary external validation cohort and the developmental cohort differed significantly on primary tumor histology, presence of visceral metastases, ASIA impairment scale, and preoperative laboratory values. The SORG algorithms for ninety-day and one-year mortality retained good discriminative ability (c-statistic of 0.81 [95% CI, 0.74-0.87] and 0.84 [95% CI, 0.77-0.89]), overall performance, and decision curve analysis. The algorithm for ninety-day mortality showed almost perfect calibration reflected in an overall calibration intercept of -0.07 (95% CI: -0.50, 0.35). The one-year mortality algorithm underestimated mortality mainly for the lowest predicted probabilities with an overall intercept of 0.57 (95% CI: 0.18, 0.96) CONCLUSIONS: The SORG algorithms for survival in spinal metastatic disease generalized well to a contemporary cohort of consecutively treated patients from an external institutional. Further validation in international cohorts and large, prospective multi-institutional trials is required to confirm or refute the findings presented here. The open-access algorithms are available here:

Bongers M E R, Karhade A V, Villavieja J, Groot O Q, Bilsky M H, Laufer I, Schwab J H


external validation, machine learning, mortality, prediction, prognostication, spinal metastases

Surgery Surgery

What's new in IBD therapy: an "omics network" approach.

In Pharmacological research ; h5-index 58.0

The industrial revolution that began in the late 1800's has resulted in dramatic changes in the environment, human lifestyle, dietary habits, social structure, and so on. Almost certainly because this rapid evolution has outpaced the ability of the body to adapt to a number of environmental and behavioral changes, there has been a parallel emergence of several chronic inflammatory diseases, among which are inflammatory bowel diseases (IBD), primarily ulcerative colitis and Crohn's disease. The ability to treat these conditions has progressively improved in the last 50 years, particularly in the last couple of decades with the introduction of biological therapy targeting primarily soluble mediators produced by inflammatory cells. A large number of biologics are now available, but all of them induce similarly unsatisfactory (<50%,) rates of clinical response and remission, and most of them lose efficacy over time, requiring dose escalation or switching from one biologic to another. So, treatment of IBD still needs improvement that will occur only if different approaches are taken. A reason why even the most recent forms of IBD therapy are unsatisfactory is because they target only selected components of an exceedingly complex pathophysiological process, a reality that must be honestly considered if better IBD therapies are to be achieved. Brand new approaches must integrate all relevant factors in their totality - the "omes" - and identify the key controllers of biological responses. This can be accomplished by using systems biology-based approaches and advanced bioinformatics tools, which together represent the essence of network medicine. This review looks at the past and the present of IBD pathogenesis and therapy, and discusses how to develop new therapies based on a network medicine approach.

Fiocchi Claudio, Iliopoulos Dimitrios


artificial intelligence, deep learning, inflammatory bowel disease, network medicine, omics, systems biology

General General

A self-administered, artificial intelligence (AI) platform for cognitive assessment in multiple sclerosis (MS).

In BMC neurology

BACKGROUND : Cognitive impairment is common in patients with multiple sclerosis (MS). Accurate and repeatable measures of cognition have the potential to be used as markers of disease activity.

METHODS : We developed a 5-min computerized test to measure cognitive dysfunction in patients with MS. The proposed test - named the Integrated Cognitive Assessment (ICA) - is self-administered and language-independent. Ninety-one MS patients and 83 healthy controls (HC) took part in Substudy 1, in which each participant took the ICA test and the Brief International Cognitive Assessment for MS (BICAMS). We assessed ICA's test-retest reliability, its correlation with BICAMS, its sensitivity to discriminate patients with MS from the HC group, and its accuracy in detecting cognitive dysfunction. In Substudy 2, we recruited 48 MS patients, 38 of which had received an 8-week physical and cognitive rehabilitation programme and 10 MS patients who did not. We examined the association between the level of serum neurofilament light (NfL) in these patients and their ICA scores and Symbol Digit Modalities Test (SDMT) scores pre- and post-rehabilitation.

RESULTS : The ICA demonstrated excellent test-retest reliability (r = 0.94), with no learning bias, and showed a high level of convergent validity with BICAMS. The ICA was sensitive in discriminating the MS patients from the HC group, and demonstrated high accuracy (AUC = 95%) in discriminating cognitively normal from cognitively impaired participants. Additionally, we found a strong association (r = - 0.79) between ICA score and the level of NfL in MS patients before and after rehabilitation.

CONCLUSIONS : The ICA has the potential to be used as a digital marker of cognitive impairment and to monitor response to therapeutic interventions. In comparison to standard cognitive tools for MS, the ICA is shorter in duration, does not show a learning bias, and is independent of language.

Khaligh-Razavi Seyed-Mahdi, Sadeghi Maryam, Khanbagi Mahdiyeh, Kalafatis Chris, Nabavi Seyed Massood


Artificial intelligence (AI), BICAMS, Digital biomarkers, Integrated cognitive assessment (ICA), Language-independent, Multiple sclerosis

General General

Digital Translucence: Adapting Telemedicine Delivery Post-COVID-19.

In Telemedicine journal and e-health : the official journal of the American Telemedicine Association

In nearly 1 month, with a rapidly expanding corona virus disease 2019 (COVID-19), telemedicine has been transformed into an essential service for delivering routine clinical care. This transformation occurred as a crisis management response-driven by the need to provide care for patients with physical distancing measures in place. However, the current rapid adoption of telemedicine presents a transitional state between one that existed before the pandemic and one that could potentially be better aligned with the delivery of a personalized model of care. Using the conceptual framework of digital translucence-situating virtual encounters with more nuanced information regarding patients-we describe the role of integrated remote monitoring and virtual care tools aligned with the patient's electronic health record for adapting telemedicine delivery post-COVID-19.

Kannampallil Thomas, Ma Jun


artificial intelligence, electronic health records, m-health, pandemic, telemedicine

Public Health Public Health

Machine learning on drug-specific data to predict small molecule teratogenicity.

In Reproductive toxicology (Elmsford, N.Y.)

Pregnant women are an especially vulnerable population, given the sensitivity of a developing fetus to chemical exposures. However, prescribing behavior for the gravid patient is guided on limited human data and conflicting cases of adverse outcomes due to the exclusion of pregnant populations from randomized, controlled trials. These factors increase risk for adverse drug outcomes and reduce quality of care for pregnant populations. Herein, we propose the application of artificial intelligence to systematically predict the teratogenicity of a prescriptible small molecule from information inherent to the drug. Using unsupervised and supervised machine learning, our model probes all small molecules with known structure and teratogenicity data published in research-amenable formats to identify patterns among structural, meta-structural, and in vitro bioactivity data for each drug and its teratogenicity score. With this workflow, we discovered three chemical functionalities that predispose a drug towards increased teratogenicity and two moieties with potentially protective effects. Our models predict three clinically-relevant classes of teratogenicity with AUC = 0.8 and nearly double the predictive accuracy of a blind control for the same task, suggesting successful modeling. We also present extensive barriers to translational research that restrict data-driven studies in pregnancy and therapeutically "orphan" pregnant populations. Collectively, this work represents a first-in-kind platform for the application of computing to study and predict teratogenicity.

Challa Anup P, Beam Andrew L, Shen Min, Peryea Tyler, Lavieri Robert R, Lippmann Ethan S, Aronoff David M


chemical structure, drug development, drug exposure, high-throughput screening, informatics, machine learning, teratogenicity, translational medicine