Artificial intelligence to support clinical decision-making processes

García-Vidal, Carolina; Sanjuan, Gemma; Puerta‐Alcalde, Pedro; Moreno-García, Estela; Soriano, Álex

doi:10.1016/j.ebiom.2019.07.019

Cited by 99 publications

(61 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the 850 million pieces of data retrieved from our EHRs, we are able to identify a clinical problem through computer systems, collect data from EHRs and algorithm evaluations in optimal time, perform real-time predictions, and link such predictions to in-hospital clinical recommendations for improved clinical decision-making processes. Our innovative program has primarily focused on predicting the presence or absence of multidrug-resistant pathogens causing infections [11]. Such an approach to pneumonia management is currently being explored.…”

Section: Our Experience In Artificial Intelligence Supporting Clinicamentioning

confidence: 99%

Can Artificial Intelligence Improve the Management of Pneumonia

Chumbita

Cillóniz

Puerta‐Alcalde

et al. 2020

JCM

Self Cite

View full text Add to dashboard Cite

The use of artificial intelligence (AI) to support clinical medical decisions is a rather promising concept. There are two important factors that have driven these advances: the availability of data from electronic health records (EHR) and progress made in computational performance. These two concepts are interrelated with respect to complex mathematical functions such as machine learning (ML) or neural networks (NN). Indeed, some published articles have already demonstrated the potential of these approaches in medicine. When considering the diagnosis and management of pneumonia, the use of AI and chest X-ray (CXR) images primarily have been indicative of early diagnosis, prompt antimicrobial therapy, and ultimately, better prognosis. Coupled with this is the growing research involving empirical therapy and mortality prediction, too. Maximizing the power of NN, the majority of studies have reported high accuracy rates in their predictions. As AI can handle large amounts of data and execute mathematical functions such as machine learning and neural networks, AI can be revolutionary in supporting the clinical decision-making processes. In this review, we describe and discuss the most relevant studies of AI in pneumonia.

show abstract

Section: Our Experience In Artificial Intelligence Supporting Clinicamentioning

confidence: 99%

Can Artificial Intelligence Improve the Management of Pneumonia

Chumbita

Cillóniz

Puerta‐Alcalde

et al. 2020

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, physicians are still a long way from understanding how machine learning, neural networks or, most importantly, artificial intelligence (AI) tools can further current medical practice. Six studies have recently been published [4][5][6][7][8][9] using AI approaches to support pneumonia diagnosis and empirical antibiotic decision-making processes. Most of the research has been conducted in the field of pneumonia diagnosis through the study of chest radiographs.…”

Section: @Erspublicationsmentioning

confidence: 99%

“…We finish with a reflection on what machine learning can contribute to a single unconnected database when outputs are restricted to a limited set of values. Machine learning techniques try to predict the future given the past, and so a reinforcement learning giving feedback from updated data retrieved from a dynamic environment, for example data retrieved directly from electronic health records, seems an optimal methodology for applying AI algorithms in healthcare computer systems in order to support clinical decision-making processes around the clock [6].…”

Section: @Erspublicationsmentioning

confidence: 99%

Macrolide combination therapy for hospitalised CAP patients? An individualised approach supported by machine learning

2019

Self Cite

View full text Add to dashboard Cite

@ERSpublicationsThe article by König and co-workers paves the way for the selection of a subset of patients with CAP in whom combination initial therapy including macrolides could improve outcomes using a new and interesting mathematical approach http://bit.ly/2p8RdCDCite this article as: Garcia-Vidal C, Cillóniz C, Torres A. Macrolide combination therapy for hospitalised CAP patients? An individualised approach supported by machine learning. Eur Respir J 2019; 54: 1902111 [https://doi.org/10.1183/13993003.02111-2019.The use of macrolides in combination with betalactams to improve outcomes in patients with community-acquired pneumonia (CAP) remains a topic of controversy, mainly because most of the evidence comes from observational studies rather than from randomised clinical trials (RCTs). Some recent studies have suggested that macrolides are effective in patients with Streptococcus pneumoniae infection plus a high systemic inflammatory response [1]. However, macrolides can be harmful [2] and there is a clear need to identify CAP phenotypes that would benefit from macrolides without suffering negative effects. We are unlikely to solve this question using conventional study designs; rather, we need to explore new technologies, among them the use of models obtained with machine learning methodology.In an interesting paper, KÖNIG et al.[3] used new statistical tools, combining propensity matching score with tree decision models (not specified) using non-supervised machine learning (also not specified) to identify patients in whom macrolide use would be beneficial. They found that a simple decision tree of pneumonia patients' characteristics, comprising chronic cardiovascular and chronic respiratory co-morbidities and leukocyte counts in the respiratory secretion at admission, was able to identify the ones who would achieve better outcomes with the addition of macrolide treatment. The results are important and open up new perspectives for conducting optimised, randomised trials to demonstrate the beneficial role of macrolides in patients with CAP.But probably one of the most interesting features of this paper is the incorporation of new statistical tools in medical research. The machine learning approach involves the study of algorithms used by computer systems to perform a specific task, most of them associated with predictions, without using explicit instructions that rely on patterns. Machine learning builds a mathematical model based on training data in order to make predictions in a test dataset. It includes a heterogeneous range of approaches, such as

show abstract

“…These interventions are not yet scaled up, and although trials seem to confirm they are effective, they show some limitations that should be considered, such as the need for both a dermatologist available on demand and a stable and strong internet connection [ 15 ]. Artificial intelligence also holds promise in the diagnosis of skin conditions to a good degree of accuracy [ 16 ] and selecting the best treatment for a specific infectious disease [ 17 ]. However, these techniques are still under development and not yet available for implementation in the clinical management of sNTDs [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

Mobile Health Strategies to Tackle Skin Neglected Tropical Diseases With Recommendations From Innovative Experiences: Systematic Review

Carrión¹,

Robles²,

Solà-Morales³

et al. 2020

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

Background Neglected tropical diseases (NTDs) represent a diverse group of 20 communicable diseases that occur in tropical and subtropical areas in 149 countries, affecting over 1 billion people and costing developing economies billions of dollars every year. Within these diseases, those that present lesions on the skin surface are classified as skin NTDs (sNTDs). Mobile health interventions are currently being used worldwide to manage skin diseases and can be a good strategy in the epidemiological and clinical management of sNTDs. Objective We aimed to analyze existing evidence about mobile health interventions to control and manage sNTDs in low- and middle-income countries (LMICs) and make recommendations for what should be considered in future interventions. Methods A systematic review was conducted of the MEDLINE, Embase, and Scopus databases over 10 years up to April 30, 2020. All types of clinical studies were considered. Data were synthesized into evidence tables. Apps were selected through a comprehensive systematic search in the Google Play Store and Apple App Store conducted between March 20 and April 15, 2020. Results From 133 potentially relevant publications, 13 studies met our criteria (9.8%). These analyzed eight different interventions (three SMS text messaging interventions and five app interventions). Six of the 13 (46%) studies were community-based cross-sectional studies intended to epidemiologically map a specific disease, mainly lymphatic filariasis, but also cutaneous leishmaniasis, leprosy, and NTDs, as well as sNTDs in general. Most of the studies were considered to have a high (5/13, 39%) or moderate (4/13, 31%) risk of bias. Fifteen apps were identified in the Google Play Store, of which three were also in the Apple App Store. Most of the apps (11/15, 73%) were targeted at health care professionals, with only four targeted at patients. The apps focused on scabies (3/15, 20%), lymphatic filariasis (3/15, 20%), cutaneous leishmaniasis (1/15, 7%), leprosy (1/15, 7%), yaws and Buruli ulcer (1/15, 7%), tropical diseases including more than one sNTDs (3/15, 20%), and NTDs including sNTDs (2/15, 13%). Only 1 (7%) app focused on the clinical management of sNTDs. Conclusions All mobile health interventions that were identified face technological, legal, final user, and organizational issues. There was a remarkable heterogeneity among studies, and the majority had methodological limitations that leave considerable room for improvement. Based on existing evidence, eight recommendations have been made for future interventions.

show abstract

Artificial intelligence to support clinical decision-making processes

Cited by 99 publications

References 8 publications

Can Artificial Intelligence Improve the Management of Pneumonia

Can Artificial Intelligence Improve the Management of Pneumonia

Macrolide combination therapy for hospitalised CAP patients? An individualised approach supported by machine learning

Mobile Health Strategies to Tackle Skin Neglected Tropical Diseases With Recommendations From Innovative Experiences: Systematic Review

Contact Info

Product

Resources

About