GC-CDSS: Personalized gastric cancer treatment recommendations system based on knowledge graph

BACKGROUND

Gastric cancer (GC) is one of the most common malignant tumors in the world, posing a serious threat to human health. Currently, gastric cancer treatment strategies emphasize a multidisciplinary team (MDT) consultation approach. However, there are numerous treatment guidelines and insights from clinical trials. The application of AI-based Clinical Decision Support System (CDSS) in tumor diagnosis and screening is increasing rapidly.

OBJECTIVE

The purpose of this study is to (1) summarize the treatment decision process for GC according to the treatment guidelines in China, and then create a knowledge graph (KG) for GC, (2) based on aforementioned KG, built a CDSS and conducted an initial feasibility evaluation for the current system.

METHODS

Firstly, we summarized the decision-making process for treatment of GC. Then, we extracted relevant decision nodes and relationships and utilized Neo4j to create the KG. After obtaining the initial node features for building the graph embedding model, graph embedding algorithm, such as Node2Vec and GraphSAGE, were used to construct the GC-CDSS. At last, a retrospective cohort study was used to compare the consistency between GC-CDSS and MDT in treatment decision making.

RESULTS

In current study, we introduce a GC-CDSS, which is constructed based on Chinese GC treatment guidelines knowledge graph (KG). In the KG, we define four types of nodes and four types of relationships, and it comprise a total of 207 nodes and 300 relationships. Regarding GC-CDSS, the system is capable of providing dynamic and personalized diagnostic and treatment recommendations based on the patient's condition. Furthermore, a retrospective cohort study is conducted to compare GC-CDSS recommendations with those of the MDT group, the overall consistency rate of treatment recommendations between the auxiliary decision system and MDT team is 92.96%.

CONCLUSIONS

We construct a GC treatment support system, GC-CDSS, based on KG. The GC-CDSS may help oncologists make treatment decisions more efficient and promote standardization in primary healthcare settings.

ANTIFON-CLIC®, a new clinical decision support system for the treatment of invasive aspergillosis: is it clinically relevant?

BACKGROUND

Invasive aspergillosis (IA) is increasing especially in new groups of patients. Despite advances in management, morbidity and mortality related to IA remain high. Thus, Clinical Decision Support System (CDSS) dedicated to IA are needed to promote the optimal antifungal for each group of patients.

PATIENTS AND METHODS

This was a retrospective multicenter cohort study involving intensive care units and medical units. Adult patients who received caspofungin, isavuconazole, itraconazole, liposomal amphotericin B, posaconazole, or voriconazole, for the treatment of IA were eligible for enrollment. The primary objective was the concordance between the clinician's prescription and the prescription recommended by the CDSS. The secondary objective was the concordance according to different hospitals, departments, and indications.

RESULTS

Eighty-eight patients (n=88) from three medical hospitals were included. The overall concordance was 97% (85/88) including 100% (41/41) for center A, 92% (23/25) for center B, and 95% (21/22) for center C. There was no significant difference in concordance among the hospitals (P=0.973), the departments (P=1.000), and the indications (P=0.799). The concordance was 70% (7/10) for isavuconazole due to its use as an empirical treatment and 100% (78/78) for the other antifungals.

DISCUSSION

The concordance rate was high whatever the hospital, the department, and the indication. The only discrepancy was attributed to the use of isavuconazole as an empirical treatment which is a therapeutic option not included in the CDSS.

CONCLUSIONS

This new CDSS dedicated to IA is meeting the clinical practice. Its implementation in routine will help to support antifungal stewardship.

Acceptance and use of a clinical decision support system in musculoskeletal pain disorders - the SupportPrim project

BACKGROUND

We have developed a clinical decision support system (CDSS) based on methods from artificial intelligence to support physiotherapists and patients in the decision-making process of managing musculoskeletal (MSK) pain disorders in primary care. The CDSS finds the most similar successful patients from the past to give treatment recommendations for a new patient. Using previous similar patients with successful outcomes to advise treatment moves management of MSK pain patients from one-size fits all recommendations to more individually tailored treatment. This study aimed to summarise the development and explore the acceptance and use of the CDSS for MSK pain patients.

METHODS

This qualitative study was carried out in the Norwegian physiotherapy primary healthcare sector between October and November 2020, ahead of a randomised controlled trial. We included four physiotherapists and three of their patients, in total 12 patients, with musculoskeletal pain in the neck, shoulder, back, hip, knee or complex pain. We conducted semi-structured telephone interviews with all participants. The interviews were analysed using the Framework Method.

RESULTS

Overall, both the physiotherapists and patients found the system acceptable and usable. Important findings from the analysis of the interviews were that the CDSS was valued as a preparatory and exploratory tool, facilitating the therapeutic relationship. However, the physiotherapists used the system mainly to support their previous and current practice rather than involving patients to a greater extent in decisions and learning from previous successful patients.

CONCLUSIONS

The CDSS was acceptable and usable to both the patients and physiotherapists. However, the system appeared not to considerably influence the physiotherapists' clinical reasoning and choice of treatment based on information from most similar successful patients. This could be due to a smaller than optimal number of previous patients in the CDSS or insufficient clinical implementation. Extensive training of physiotherapists should not be underestimated to build understanding and trust in CDSSs.

Named Entity Recognition in Electronic Health Records: A Methodological Review

OBJECTIVES

A substantial portion of the data contained in Electronic Health Records (EHR) is unstructured, often appearing as free text. This format restricts its potential utility in clinical decision-making. Named entity recognition (NER) methods address the challenge of extracting pertinent information from unstructured text. The aim of this study was to outline the current NER methods and trace their evolution from 2011 to 2022.

METHODS

We conducted a methodological literature review of NER methods, with a focus on distinguishing the classification models, the types of tagging systems, and the languages employed in various corpora.

RESULTS

Several methods have been documented for automatically extracting relevant information from EHRs using natural language processing techniques such as NER and relation extraction (RE). These methods can automatically extract concepts, events, attributes, and other data, as well as the relationships between them. Most NER studies conducted thus far have utilized corpora in English or Chinese. Additionally, the bidirectional encoder representation from transformers using the BIO tagging system architecture is the most frequently reported classification scheme. We discovered a limited number of papers on the implementation of NER or RE tasks in EHRs within a specific clinical domain.

CONCLUSIONS

EHRs play a pivotal role in gathering clinical information and could serve as the primary source for automated clinical decision support systems. However, the creation of new corpora from EHRs in specific clinical domains is essential to facilitate the swift development of NER and RE models applied to EHRs for use in clinical practice.

Design, development, implementation, and evaluation of a severe drug-drug interaction alert system in the ICU: An analysis of acceptance and override rates

BACKGROUND AND OBJECTIVE

The override rate of Drug-Drug Interaction Alerts (DDIA) in Intensive Care Units (ICUs) is very high. Therefore, this study aimed to design, develop, implement, and evaluate a severe Drug-Drug Alert System (DDIAS) in a system of ICUs and measure the override rate of this system.

METHODS

This is a cross-sectional study that details the design, development, implementation, and evaluation of a DDIAS for severe interactions into a Computerized Provider Order Entry (CPOE) system in the ICUs of Nemazee general teaching hospitals in 2021. The patients exposed to the volume of DDIAS, acceptance and overridden of DDIAS, and usability of DDIAS have been collected. The study was approved by the local Institutional Review Board (IRB) and; the ethics committee of Shiraz University of Medical Science on date: 2019-11-23 (Approval ID: IR.SUMS.REC.1398.1046).

RESULTS

The knowledge base of the DDIAS contains 9,809 severe potential drug-drug interactions (pDDIs). A total of 2672 medications were prescribed in the population study. The volume and acceptance rate for the DDIAS were 81 % and 97.5 %, respectively. The override rate was 2.5 %. The mean System Usability Scale (SUS) score of the DDIAS was 75.

CONCLUSION

This study demonstrates that implementing high-risk DDIAS at the point of prescribing in ICUs improves adherence to alerts. In addition, the usability of the DDIAS was reasonable. Further studies are needed to investigate the establishment of severe DDIAS and measure the prescribers' response to DDIAS on a larger scale.

Machine Learning Approach for Predicting Systemic Lupus Erythematosus in an Oman-Based Cohort

Objectives

This study aimed to design a machine learning-based prediction framework to predict the presence or absence of systemic lupus erythematosus (SLE) in a cohort of Omani patients.

Methods

Data of 219 patients from 2006 to 2019 were extracted from Sultan Qaboos University Hospital's electronic records. Among these, 138 patients had SLE, while the remaining 81 had other rheumatologic diseases. Clinical and demographic features were analysed to focus on the early stages of the disease. Recursive feature selection was implemented to choose the most informative features. The CatBoost classification algorithm was utilised to predict SLE, and the SHAP explainer algorithm was applied on top of the CatBoost model to provide individual prediction reasoning, which was then validated by rheumatologists.

Results

CatBoost achieved an area under the receiver operating characteristic curve score of 0.95 and a sensitivity of 92%. The SHAP algorithm identified four clinical features (alopecia, renal disorders, acute cutaneous lupus and haemolytic anaemia) and the patient's age as having the greatest contribution to the prediction.

Conclusion

An explainable framework to predict SLE in patients and provide reasoning for its prediction was designed and validated. This framework enables clinicians to implement early interventions that will lead to positive healthcare outcomes.

Keyphrase Identification Using Minimal Labeled Data with Hierarchical Context and Transfer Learning

Interoperable clinical decision support system (CDSS) rules provide a pathway to interoperability, a well-recognized challenge in health information technology. Building an ontology facilitates creating interoperable CDSS rules, which can be achieved by identifying the keyphrases (KP) from the existing literature. However, KP identification for data labeling requires human expertise, consensus, and contextual understanding. This paper aims to present a semi-supervised KP identification framework using minimal labeled data based on hierarchical attention over the documents and domain adaptation. Our method outperforms the prior neural architectures by learning through synthetic labels for initial training, document-level contextual learning, language modeling, and fine-tuning with limited gold standard label data. To the best of our knowledge, this is the first functional framework for the CDSS sub-domain to identify KPs, which is trained on limited labeled data. It contributes to the general natural language processing (NLP) architectures in areas such as clinical NLP, where manual data labeling is challenging, and light-weighted deep learning models play a role in real-time KP identification as a complementary approach to human experts' effort.

The Effect of Physicians' Acknowledgement of Clinical Decision Support Systems Generated Alerts on Patient Diabetes Management in a Primary Care Setting

The purpose of the study is to evaluate whether clinician's acknowledgement and adherence to Clinical Best Practice Advisories (BPA) system's alerts improves the outcome of patients with chronic diabetes. We used deidentified clinical data of elderly (65 or older) diabetes patients with hemoglobin A1C (HbA1C) >= 6.5 that were extracted from the clinical database of a multi-specialty outpatient clinic that also provides primary care services. We performed paired ttest to evaluate whether clinician's acknowledgement and adherence to BPA system's alert has any impact on patients' HbA1C management. Our findings showed that the average HbA1C values improved for patients whose alerts were acknowledged by their clinicians. For the group of patients whose BPA alerts were ignored by their clinicians, we found clinicians' acknowledgement and adherence to BPA alerts for chronic diabetes patient management did not have a significant negative effect on improvement in patient outcome.

A drug recommender system for the treatment of hypertension

BACKGROUND

One third (20% to 30%) of patients suffering from hypertension show increased blood pressure resistant to treatment. This resistance often has multifactorial causes, like therapeutic inertia and inappropriate medication but also poor patient adherence. Evidence-based guidelines aim to support appropriate health care decisions. However, (i) research and appraisal of clinical guidelines is often not practicable in daily routine care and (ii) guidelines alone are often insufficient to make suitable and personalized treatment decisions. Shared decision-making (SDM) can significantly improve patient adherence, but is also difficult to implement in routine care due to time constraints.

METHODS

Clinical Decision Support Systems (CDSSs), designed to support clinical decision-making by providing explainable and personalized treatment recommendations, are expected to remedy the aforementioned issues. In this work we describe a digital recommendation system for the pharmaceutical treatment of hypertension and compare its recommendations with clinical experts. The proposed therapy recommender algorithm combines external evidence (knowledge-based) - derived from clinical guidelines and drugs' professional information - with information stored in routine care data (data-based) - derived from 298 medical records and 900 doctor-patient contacts from 7 general practitioners practices. The developed Graphical User Interface (GUI) visualizes recommendations along with personalized treatment information and intents to support SDM. The CDSS was evaluated on 23 artificial test patients (case vignettes), by comparing its output with recommendations from five specialized physicians.

RESULTS

The results show that the proposed algorithm provides personalized treatment recommendations with large agreement with clinical experts. This is true for agreement with all experts (agree_all), with any expert (agree_any), and with the majority vote of all experts (agree_majority). The performance of a solely data-based approach can be additionally improved by applying evidence-based rules (external evidence). When comparing the achieved results (agree_all) with the inter-rater agreement among experts, the CDSS's recommendations partly agree more often with the experts than the experts among each other.

CONCLUSION

Overall, the feasibility and performance of medication recommendation systems for the treatment of hypertension could be shown. The major challenges when developing such a CDSS arise from (i) the availability of sufficient and appropriate training and evaluation data and (ii) the absence of standardized medical knowledge such as computerized guidelines. If these challenges are solved, such treatment recommender systems can support physicians with exploiting knowledge stored in routine care data, help to comply with the best available clinical evidence and increase the adherence of the patient by reducing site-effects and individualizing therapies.

Early identification of chronic kidney disease: it is time to enhance patient and population-based informatics tools for general practitioners

Chronic kidney disease (CKD) is a global public health issue that can lead to several complications such as, kidney failure, cerebro/cardiovascular disease, and death.There is a well-documented "awareness gap" among general practitioners (GPs) to recognize CKD. As shown by estimates stemming from the Health Search Database (HSD) of the Italian College of General Practitioners and Primary Care (SIMG), no substantial changes were observed in terms of the incident rate of CKD over the last 10 years. Namely, 10.3 to 9.5 per 1,000 new cases of CKD were estimated in 2012 and 2021, respectively. Thus, strategies to reduce under-recognized cases are needed. Early identification of CKD might improve patient's quality of life and clinical outcomes. In this context, patient- and population-based informatic tools may support both opportunistic and systematic screening of patients at greater risk of CKD. As such, the new effective pharmacotherapies for CKD would be proficiently administered. To this aim, these two complimentary tools have been developed and will be further implemented by GPs.The effectiveness of these instruments in identifying the condition at an early stage and reducing the burden of CKD on the national health system needs to be verified according to the new regulations on medical device (MDR: (EU) 2017/745).

Putting undergraduate medical students in AI-CDSS designers' shoes: An innovative teaching method to develop digital health critical thinking

INTRODUCTION

Digital health programs are urgently needed to accelerate the adoption of Artificial Intelligence and Clinical Decision Support Systems (AI-CDSS) in clinical settings. However, such programs are still lacking for undergraduate medical students, and new approaches are required to prepare them for the arrival of new and unknown technologies. At University Paris Cité medical school, we designed an innovative program to develop the digital health critical thinking of undergraduate medical students that consisted of putting medical students in AI-CDSS designers' shoes.

METHODS

We followed the six steps of Kern's approach for curriculum development: identification of needs, definition of objectives, design of an educational strategy, implementation, development of an assessment and design of program evaluation.

RESULTS

A stand-alone and elective AI-CDSS program was implemented for fourth-year medical students. Each session was designed from an AI-CDSS designer viewpoint, with theoretical and practical teaching and brainstorming time on a project that consisted of designing an AI-CDSS in small groups. From 2021 to 2022, 15 students were enrolled: they rated the program 4.4/5, and 80% recommended it. Seventy-four percent considered that they had acquired new skills useful for clinical practice, and 66% felt more confident with technologies. The AI-CDSS program aroused great enthusiasm and strong engagement of students: 8 designed an AI-CDSS and wrote two scientific 5-page articles presented at the Medical Informatics Europe conference; 4 students were involved in a CDSS research project; 2 students asked for a hospital internship in digital health; and 1 decided to pursue PhD training.

DISCUSSION

Putting students in AI-CDSS designers' shoes seemed to be a fruitful and innovative strategy to develop digital health skills and critical thinking toward AI technologies. We expect that such programs could help future doctors work in rapidly evolving digitalized environments and position themselves as key leaders in digital health.

Improving Adherence to the Mediterranean Diet in Early Pregnancy Using a Clinical Decision Support System; A Randomised Controlled Clinical Trial

Prenatal health is important for both mother and child. Additionally, the offspring’s development is affected by the mother’s diet. The aim of this study was to assess whether a Clinical Decision Support System (CDSS) can improve adherence to the Mediterranean diet in early pregnancy and whether this change is accompanied by changes in nutritional status and psychological parameters. We designed a three month randomised controlled clinical trial which was applied to 40 healthy pregnant women (20 in the CDSS and 20 in the control group). Medical history, biochemical, anthropometric measurements, dietary, and a psychological distress assessment were applied before and at the end of the intervention. Pregnant women in the CDSS group experienced a greater increase in adherence to the Mediterranean diet, as assessed via MedDietScore, in the first trimester of their pregnancy compared to women in the control group (p < 0.01). Furthermore, an improved nutritional status was observed in pregnant women who were supported by CDSS. Anxiety and depression levels showed a greater reduction in the CDSS group compared to the control group (p = 0.048). In conclusion, support by a CDSS during the first trimester of pregnancy may be beneficial for the nutritional status of the mother, as well as for her anxiety and depression status.

Healthcare Professionals' Expectations of Medical Artificial Intelligence and Strategies for its Clinical Implementation: A Qualitative Study

OBJECTIVES

Although medical artificial intelligence (AI) systems that assist healthcare professionals in critical care settings are expected to improve healthcare, skepticism exists regarding whether their potential has been fully actualized. Therefore, we aimed to conduct a qualitative study with physicians and nurses to understand their needs, expectations, and concerns regarding medical AI; explore their expected responses to recommendations by medical AI that contradicted their judgments; and derive strategies to implement medical AI in practice successfully.

METHODS

Semi-structured interviews were conducted with 15 healthcare professionals working in the emergency room and intensive care unit in a tertiary teaching hospital in Seoul. The data were interpreted using summative content analysis. In total, 26 medical AI topics were extracted from the interviews. Eight were related to treatment recommendation, seven were related to diagnosis prediction, and seven were related to process improvement.

RESULTS

While the participants expressed expectations that medical AI could enhance their patients' outcomes, increase work efficiency, and reduce hospital operating costs, they also mentioned concerns regarding distortions in the workflow, deskilling, alert fatigue, and unsophisticated algorithms. If medical AI decisions contradicted their judgment, most participants would consult other medical staff and thereafter reconsider their initial judgment.

CONCLUSIONS

Healthcare professionals wanted to use medical AI in practice and emphasized that artificial intelligence systems should be trustworthy from the standpoint of healthcare professionals. They also highlighted the importance of alert fatigue management and the integration of AI systems into the workflow.

HIV retention in care: results and lessons learned from the Positive Pathways Implementation Trial

BACKGROUND

Sustained, routine care is vital to the health of people with HIV (PWH) and decreasing transmission of HIV. We evaluated whether the identification of PWH at-risk of falling out of care and prompts for outreach were effective in retaining PWH in care in the United States.

METHODS

In this cluster randomized controlled trial, 20 AIDS Healthcare Foundation Healthcare Centers (HCCs) were randomized to the intervention (n = 10) or control (n = 10) arm; all maintained existing retention efforts. The intervention included daily automated flags in CHORUS™, a mobile app and web-based reporting solution utilizing electronic health record data, that identified PWH at-risk of falling out of care to clinic staff. Among flagged PWH, the association between the intervention and visits after a flag was assessed using logistic regression models fit with generalized estimating equations (independent correlation structure) to account for clustering. To adjust for differences between HCCs, models included geographic region, number of PWH at HCC, and proportions of PWH who self-identified as Hispanic or had the Ryan White Program as a payer.

RESULTS

Of 15,875 PWH in care, 56% were flagged; 76% (intervention) and 75% (control) resulted in a visit, of which 76% were within 2 months of the flag. In adjusted analyses, flags had higher odds of being followed by a visit (odds ratio [OR]: 1.08, 95% confidence interval [CI]: 0.97, 1.21) or a visit within 2 months (OR: 1.07, 95% CI: 0.97, 1.17) at intervention than control HCCs. Among at-risk PWH with viral loads at baseline and study end, the proportion with < 50 copies/mL increased in both study arms, but more so at intervention (65% to 74%) than control (62% to 67%) HCCs.

CONCLUSION

Despite challenges of the COVID-19 pandemic, adding an intervention to existing retention efforts, and the reality that behavior change takes time, PWH flagged as at-risk of falling out of care were marginally more likely to return for care at intervention than control HCCs and a greater proportion achieved undetectability. Sustained use of the retention module in CHORUS™ has the potential to streamline retention efforts, retain more PWH in care, and ultimately decrease transmission of HIV.

TRIAL REGISTRATION

The study was first registered at Clinical Trials.gov (NCT04147832, https://clinicaltrials.gov/show/NCT04147832 ) on 01/11/2019.

CAREPATH: Developing Digital Integrated Care Solutions for Multimorbid Patients with Dementia

CAREPATH project is focusing on providing an integrated solution for sustainable care for multimorbid elderly patients with dementia or mild cognitive impairment. The project has a digitally enhanced integrated patient-centered care approach clinical decision and associated intelligent tools with the aim to increase patients' independence, quality of life and intrinsic capacity. In this paper, the conceptual aspects of the CAREPATH project, in terms of technical and clinical requirements and considerations, are presented.

Automatic Wound Type Classification with Convolutional Neural Networks

Chronic wounds are ulcerations of the skin that fail to heal because of an underlying condition such as diabetes mellitus or venous insufficiency. The timely identification of this condition is crucial for healing. However, this identification requires expert knowledge unavailable in some care situations. Here, artificial intelligence technology may support clinicians. In this study, we explore the performance of a deep convolutional neural network to classify diabetic foot and venous leg ulcers using wound images. We trained a convolutional neural network on 863 cropped wound images. Using a hold-out test set with 80 images, the model yielded an F1-score of 0.85 on the cropped and 0.70 on the full images. This study shows promising results. However, the model must be extended in terms of wound images and wound types for application in clinical practice.

Design of an Ontology-Based Triage System for Patients with Chronic Pain

OBJECTIVE

Waiting time for a consultation for chronic pain is a widespread health problem. This paper presents the design of an ontology use to assess patients referred to a consultation for chronic pain.

METHODS

We designed OntoDol, an ontology of pain domain for patient triage based on priority degrees. Terms were extracted from clinical practice guidelines and mapped to SNOMED-CT concepts through the Python module Owlready2. Selected SNOMED-CT concepts, relationships, and the TIME ontology, were implemented in the ontology using Protégé. Decision rules were implemented with SWRL. We evaluated OntoDol on 5 virtual cases.

RESULTS

OntoDol contains 762 classes, 92 object properties and 18 SWRL rules to assign patients to 4 categories of priority. OntoDol was able to assert every case and classify them in the right category of priority.

CONCLUSION

Further works will extend OntoDol to other diseases and assess OntoDol with real world data from the hospital.

An Interactive Interface for Displaying Recommendations on Emergency Phone Triage in Pediatrics

Emergency phone triage aims at identifying quickly patients with critical emergencies. Patient triage is not an easy task, especially in situations involving children, mostly due to the lack of training and the lack of clinical guidelines for children. To overcome these issues, we aim at designing and assessing an interactive interface for displaying recommendations on emergency phone triage in pediatrics. Four medical students formalized local guidelines written by the SAMU of Paris, into a decision tree and designed an interface according to usability principles. The navigation within the interface was designed to allow the identification of critical emergencies at the beginning of the decision process, and thus ensuring a quick response in case of critical emergencies. The interface was assessed by 10 medical doctors: they appreciated the ergonomics (e.g., intuitive colors), and found easy to navigate through the interface. Nine of them would like to use this interface during phone call triage. In the future, this interface will be improved and implemented in emergency call centers.

Towards a Clinical Decision Support System for Helping Medical Students in Emergency Call Centers

In critical situations such as pandemic, medical students are often called to help in emergency call centers. However, they may encounter difficulties in phone triage because of a lack of medical skills. Here, we aim at developing a Clinical Decision Support System for helping medical students in phone call triage of pediatric patients. The system is based on the PAT (Pediatric Assessment Triangle) and local guidelines. It is composed of two interfaces. The first allows a quick assessment of severity signs, and the second provides recommendations and additional elements such as "elements to keep in mind" or "medical advice to give to patient". The system was evaluated by 20 medical students, with two fictive clinical cases. 75% of them found the content useful and clear, and the navigation easy. 65% would feel more reassured to have this system in emergency call centers. Further works are planned to improve the system before implementation in real-life.

An Image Based Object Recognition System for Wound Detection and Classification of Diabetic Foot and Venous Leg Ulcers

Venous leg ulcers and diabetic foot ulcers are the most common chronic wounds. Their prevalence has been increasing significantly over the last years, consuming scarce care resources. This study aimed to explore the performance of detection and classification algorithms for these types of wounds in images. To this end, algorithms of the YoloV5 family of pre-trained models were applied to 885 images containing at least one of the two wound types. The YoloV5m6 model provided the highest precision (0.942) and a high recall value (0.837). Its mAP_0.5:0.95 was 0.642. While the latter value is comparable to the ones reported in the literature, precision and recall were considerably higher. In conclusion, our results on good wound detection and classification may reveal a path towards (semi-) automated entry of wound information in patient records. To strengthen the trust of clinicians, we are currently incorporating a dashboard where clinicians can check the validity of the predictions against their expertise.

Improving care for hypertension and diabetes in india by addition of clinical decision support system and task shifting in the national NCD program: I-TREC model of care

Background

The growing burden of hypertension and diabetes is one of the major public health challenges being faced by the health system in India. Clinical Decision Support Systems (CDSS) that assist with tailoring evidence-based management approaches combined with task-shifting from more specialized to less specialized providers may together enhance the impact of a program. We sought to integrate a technology “CDSS” and a strategy “Task-shifting” within the Government of India’s (GoI) Non-Communicable Diseases (NCD) System under the Comprehensive Primary Health Care (CPHC) initiative to enhance the program’s impact to address the growing burden of hypertension and diabetes in India.

Methods

We developed a model of care “I-TREC” entirely calibrated for implementation within the current health system across all facility types (Primary Health Centre, Community Health Centre, and District Hospital) in a block in Shaheed Bhagat Singh (SBS) Nagar district of Punjab, India. We undertook an academic-community partnership to incorporate the combination of a CDSS with task-shifting into the GoI CPHC-NCD system, a platform that assists healthcare providers to record patient information for routine NCD care. Academic partners developed clinical algorithms, a revised clinic workflow, and provider training modules with iterative collaboration and consultation with government and technology partners to incorporate CDSS within the existing system.

Discussion

The CDSS-enabled GoI CPHC-NCD system provides evidence-based recommendations for hypertension and diabetes; threshold-based prompts to assure referral mechanism across health facilities; integrated patient database, and care coordination through workflow management and dashboard alerts. To enable efficient implementation, modifications were made in the patient workflow and the fulcrum of the use of technology shifted from physician to nurse.

Conclusion

Designed to be applicable nationwide, the I-TREC model of care is being piloted in a block in the state of Punjab, India. Learnings from I-TREC will provide a roadmap to other public health experts to integrate and adapt their interventions at the national level.

Trial registration

CTRI/2020/01/022723.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-022-08025-y.

Communication and Decision Support Tool for an In-Hospital 3D Printing Service

BACKGROUND

Effective communication is a key factor in healthcare, essential for improving process efficiency and quality of care. This is particularly true in new services, e.g., the 3D printing service inside the hospital.

OBJECTIVES

A web platform, called 3DSCT, has been developed to act as an interface between the three categories of operators involved in 3D printing: physicians, radiologists and engineers.

METHODS

The 3DSCT platform has been designed using Microsoft Visual Studio Code, enclosing .js scripts and HTML pages with the relative CSS formats.

RESULTS

When applied to a real 3D printing service, the 3DSCT platform provided an effective solution that streamlined the process of designing and manufacturing 3D-printed artifacts, from physician's request through development to printing.

CONCLUSION

By incorporating the platform into the hospital management system, it will be possible to reduce the overall lead time and decrease the waste of time for the operators involved in 3D printing inside the hospital.

Ensemble Deep-Learning-Enabled Clinical Decision Support System for Breast Cancer Diagnosis and Classification on Ultrasound Images

Simple Summary

In the literature, there exist plenty of research works focused on the detection and classification of breast cancer. However, only a few works have focused on the classification of breast cancer using ultrasound scan images. Although deep transfer learning models are useful in breast cancer classification, owing to their outstanding performance in a number of applications, image pre-processing and segmentation techniques are essential. In this context, the current study developed a new Ensemble Deep-Learning-Enabled Clinical Decision Support System for the diagnosis and classification of breast cancer using ultrasound images. In the study, an optimal multi-level thresholding-based image segmentation technique was designed to identify the tumor-affected regions. The study also developed an ensemble of three deep learning models for feature extraction and an optimal machine learning classifier for breast cancer detection. The study offers a means of assisting radiologists and healthcare professionals in the breast cancer classification process.

Abstract

Clinical Decision Support Systems (CDSS) provide an efficient way to diagnose the presence of diseases such as breast cancer using ultrasound images (USIs). Globally, breast cancer is one of the major causes of increased mortality rates among women. Computer-Aided Diagnosis (CAD) models are widely employed in the detection and classification of tumors in USIs. The CAD systems are designed in such a way that they provide recommendations to help radiologists in diagnosing breast tumors and, furthermore, in disease prognosis. The accuracy of the classification process is decided by the quality of images and the radiologist’s experience. The design of Deep Learning (DL) models is found to be effective in the classification of breast cancer. In the current study, an Ensemble Deep-Learning-Enabled Clinical Decision Support System for Breast Cancer Diagnosis and Classification (EDLCDS-BCDC) technique was developed using USIs. The proposed EDLCDS-BCDC technique was intended to identify the existence of breast cancer using USIs. In this technique, USIs initially undergo pre-processing through two stages, namely wiener filtering and contrast enhancement. Furthermore, Chaotic Krill Herd Algorithm (CKHA) is applied with Kapur’s entropy (KE) for the image segmentation process. In addition, an ensemble of three deep learning models, VGG-16, VGG-19, and SqueezeNet, is used for feature extraction. Finally, Cat Swarm Optimization (CSO) with the Multilayer Perceptron (MLP) model is utilized to classify the images based on whether breast cancer exists or not. A wide range of simulations were carried out on benchmark databases and the extensive results highlight the better outcomes of the proposed EDLCDS-BCDC technique over recent methods.

Development and Evaluation of a Bayesian Risk Stratification Method for Major Amputations in Patients with Diabetic Foot Ulcers

The diabetic foot ulcer, which 2% - 6% of diabetes patients experience, is a severe health threat. It is closely linked to the risk of lower extremity amputation (LEA). When a DFU is present, the chief imperative is to initiate tertiary preventive actions to avoid amputation. In this light, clinical decision support systems (CDSS) can guide clinicians to identify DFU patients early. In this study, the PEDIS classification and a Bayesian logistic regression model are utilised to develop and evaluate a decision method for patient stratification. Therefore, we conducted a Bayesian cutpoint analysis. The CDSS revealed an optimal cutpoint for the amputation risk of 0.28. Sensitivity and specificity were 0.83 and 0.66. These results show that although the specificity is low, the decision method includes most actual patients at risk, which is a desirable feature in monitoring patients at risk for major amputation. This study shows that the PEDIS classification promises to provide a valid basis for a DFU risk stratification in CDSS.

Development of a Clinical Decision Support System for Smart Algorithms in Emergency Medicine

The development of clinical decision support systems (CDSS) is complex and requires user-centered planning of assistive interventions. Especially in the setting of emergency care requiring time-critical decisions and interventions, it is important to adapt a CDSS to the needs of the user in terms of acceptance, usability and utility. In the so-called ENSURE project, a user-centered approach was applied to develop the CDSS intervention. In the context of this paper, we present a path to the first mockup development for a CDSS interface by addressing Campbell's Five Rights within the CDSS workflow.

Automatic Classification of Diabetic Foot Ulcer Images - A Transfer-Learning Approach to Detect Wound Maceration

Diabetic foot ulcer (DFU) is a chronic wound and a common diabetic complication as 2% - 6% of diabetic patients witness the onset thereof. The DFU can lead to severe health threats such as infection and lower leg amputations, Coordination of interdisciplinary wound care requires well-written but time-consuming wound documentation. Artificial intelligence (AI) systems lend themselves to be tested to extract information from wound images, e.g. maceration, to fill the wound documentation. A convolutional neural network was therefore trained on 326 augmented DFU images to distinguish macerated from unmacerated wounds. The system was validated on 108 unaugmented images. The classification system achieved a recall of 0.69 and a precision of 0.67. The overall accuracy was 0.69. The results show that AI systems can classify DFU images for macerations and that those systems could support clinicians with data entry. However, the validation statistics should be further improved for use in real clinical settings. In summary, this paper can contribute to the development of methods to automatic wound documentation.

A COVID-19 Decision Support System for Phone Call Triage, Designed by and for Medical Students

During spring 2020, SARS-CoV-2 pandemic induced shortage of medical equipment, hospital capacity and staff. To tackle this issue, medical students have been strongly involved in early patient triage through medical phone call regulation. Here, we present an intelligent web-based decision support system for COVID-19 phone call regulation, developed by and for, medical students to help them during this difficult but crucial task. The system is divided into 5 tabs. The first tab displays administrative information, clinical data related to life-threatening emergency, and personalized recommendations for patient management. The second tab displays a PDF report summarizing the clinical situation; the third tab displays the guidelines used for establishing the recommendations, and the fourth tab displays the overall algorithm in the form of a decision tree. The fifth tab provided a short user guide. The system was assessed by 21 medical staff. More than 90% of them appreciated the navigation and the interface, and found the content relevant. 90,5% of them would like to use it during the medical regulation. In the future, we plan to use this system during simulation-based medical learning for the initial medical training of medical students.

Evaluation of a Clinical Decision Support System in the Domain of Chronic Wound Management

The PosiThera project focuses on the management of chronic wounds, which is multi-professional and multi-disciplinary. For this context, a software prototype was developed in the project, which is intended to support medical and nursing staff with the assistance of artificial intelligence. In accordance with the user-centred design, national workshops were held at the beginning of the project with the involvement of domain experts in wound care in order to identify requirements and use cases of IT systems in wound care, with a focus on AI. In this study, the focus was on involving nursing and nursing science staff in testing the software prototype to gain insights into its functionality and usability. The overarching goal of the iterative testing and adaptation process is to further develop the prototype in a way that is close to care.

Integrating a brief alcohol intervention with tobacco addiction treatment in primary care: qualitative study of health care practitioner perceptions

BACKGROUND

Randomized trials of complex interventions are increasingly including qualitative components to further understand factors that contribute to their success. In this paper, we explore the experiences of health care practitioners in a province wide smoking cessation program (the Smoking Treatment for Ontario Patients program) who participated in the COMBAT trial. This trial examined if the addition of an electronic prompt embedded in a Clinical Decision Support System (CDSS)-designed to prompt practitioners to Screen, provide a Brief intervention and Referral to Treatment (SBIRT) to patients who drank alcohol above the amounts recommended by the Canadian Cancer Society guidelines-influenced the proportion of practitioners delivering a brief intervention to their eligible patients. We wanted to understand the factors influencing implementation and acceptability of delivering a brief alcohol intervention for treatment-seeking smokers for health care providers who had access to the CDSS (intervention arm) and those who did not (control arm).

METHODS

Twenty-three health care practitioners were selected for a qualitative interview using stratified purposeful sampling (12 from the control arm and 11 from the intervention arm). Interviews were 45 to 90 min in length and conducted by phone using an interview guide that was informed by the National Implementation Research Network's Hexagon tool. Interview recordings were transcribed and coded iteratively between three researchers to achieve consensus on emerging themes. The preliminary coding structure was developed using the National Implementation Research Network's Hexagon Tool framework and data was analyzed using the framework analysis approach.

RESULTS

Seventy eight percent (18/23) of the health care practitioners interviewed recognized the need to simultaneously address alcohol and tobacco use. Seventy four percent (17/23), were knowledgeable about the evidence of health risks associated with dual alcohol and tobacco use but 57% (13/23) expressed concerns with using the Canadian Cancer Society guidelines to screen for alcohol use. Practitioners acknowledged the value of adding a validated screening tool to the STOP program's baseline questionnaire (19/23); however, following through with a brief intervention and referral to treatment proved challenging due to lack of training, limited time, and fear of stigmatizing patients. Practitioners in the intervention arm (5/11; 45%) might not follow the recommendations from CDSS if these recommendations are not perceived as beneficial to the patients.

CONCLUSIONS

The results of the study show that practitioners' beliefs were reflective of the current social norms around alcohol use and this influenced their decision to offer a brief alcohol intervention. Future interventions need to emphasize both organizational and sociocultural factors as part of the design. The results of this study point to the need to change social norms regarding alcohol in order to effectively implement interventions that target both alcohol and tobacco use in primary care clinics. Trial registration ClinicalTrials.gov NCT03108144. Retrospectively registered 11 April 2017, https://www.clinicaltrials.gov/ct2/show/NCT03108144.

Emerging Concepts and Applied Machine Learning Research in Patients with Drug-Induced Repolarization Disorders

The paper presents a review of current research to develop predictive models for automated detection of drug-induced repolarization disorders and shows a feasibility study for developing machine learning tools trained on massive multimodal datasets of narrative, textual and electrocardiographic records. The goal is to reduce drug-induced long QT and associated complications (Torsades-de-Pointes, sudden cardiac death), by identifying prescription patterns with pro-arrhythmic propensity using a validated electronic application for the detection of adverse drug events with data mining and natural language processing; and to compute individual-based predictive scores in order to further identify clinical conditions, concomitant diseases, or other variables that correlate with higher risk of pro-arrhythmic situations.

A Domain-Independent Semantically Validated Authoring Tool for Formalizing Clinical Practice Guidelines

Clinical Practice Guidelines (CPGs) are promoted as a powerful tool for standardization of the medical care quality and improvement of patients' outcomes. However, CPGs need to be formalized in a computer interpretable format (i.e. as Computer Interpretable Guidelines or CIGs) for their implementation within Clinical Decision Support Systems (CDSS). But, maintaining the reliability of these guidelines when deploying them in different clinical settings is still a challenge. On the one hand, the complexity of the medical language complicates the adoption of the guidelines in different clinical institutions. On the other hand, the continuous discovery of new evidence needs to be included within CPGs, updating their contents and providing tools for evidence assessment. Furthermore, although nowadays' clinical decision-making tends towards a personalized process, guidelines are designed for a general population. In this paper, we present an Authoring Tool (AT) that allows clinicians to take an active role in the process of CPG formalization. This AT enables them to introduce new clinical knowledge and create personalized CIGs for their local application, which best fits their clinical needs. The proposed system also allows the use of ontologies to facilitate the standardization and interoperability of the created guidelines. Finally, the content included in the CIGs can be evaluated using standard systems for grading clinical evidence.

Are Clinical Decision Support Systems Compatible with Patient-Centred Care?

Few, if any, of the Clinical Decision Support Systems developed and reported within the informatics literature incorporate patient preferences in the formal and quantitatively analytic way adopted for evidence. Preferences are assumed to be 'taken into account' by the clinician in the associated clinical encounter. Many CDSS produce management recommendations on the basis of embedded algorithms or expert rules. These are often focused on a single criterion, and the preference trade-offs involved have no empirical basis outside an expert panel. After illustrating these points with the Osteoporosis Adviser CDSS from Iceland, we review an ambitious attempt to address both the monocriterial bias and lack of empirical preference-sensitivity, in the context of Early Rheumatoid Arthritis. It brings together the preference data from a Discrete Choice Experiment and the best available evidence data, to arrive at the percentage of patients who would prefer particular treatments from those in the listed options. It is suggested that these percentages could assist a GRADE panel determine whether to produce a strong or weak recommendation. However, any such group average preference-based recommendations are arguably in breach of both the reasonable patient legal standard for informed consent and simple ethical principles. The answer is not to localise, but personalise, decisions through the use of preference-sensitive multi-criteria decision support tools engaged with at the point of care.

Early temporal prediction of Type 2 Diabetes Risk Condition from a General Practitioner Electronic Health Record: A Multiple Instance Boosting Approach

Early prediction of target patients at high risk of developing Type 2 diabetes (T2D) plays a significant role in preventing the onset of overt disease and its associated comorbidities. Although fundamental in early phases of T2D natural history, insulin resistance is not usually quantified by General Practitioners (GPs). Triglyceride-glucose (TyG) index has been proven useful in clinical studies for quantifying insulin resistance and for the early identification of individuals at T2D risk but still not applied by GPs for diagnostic purposes. The aim of this study is to propose a multiple instance learning boosting algorithm (MIL-Boost) for creating a predictive model capable of early prediction of worsening insulin resistance (low vs high T2D risk) in terms of TyG index. The MIL-Boost is applied to past electronic health record (EHR) patients' information stored by a single GP. The proposed MIL-Boost algorithm proved to be effective in dealing with this task, by performing better than the other state-of-the-art ML competitors (Recall from 0.70 and up to 0.83). The proposed MIL-based approach is able to extract hidden patterns from past EHR temporal data, even not directly exploiting triglycerides and glucose measurements. The major advantages of our method can be found in its ability to model the temporal evolution of longitudinal EHR data while dealing with small sample size and variability in the observations (e.g., a small variable number of prescriptions for non-hospitalized patients). The proposed algorithm may represent the main core of a clinical decision support system.

Development of an Guideline-Based Decision Support System for Effective Diagnostic Workflow for Oncologic Pathologists

Accurate and rapid differential diagnosis are required for personalized cancer treatment. However, owing to the numerous molecular tests used for establishing a diagnosis, pathologists need time to investigate and confirm necessary test items. We present a guideline-based decision support system for effective workflow with regards to the molecular tests for pathological differential diagnosis.

Development and Assessment of RecosDoc-MTeV to Improve the Quality of Direct Oral Anticoagulant Prescription for Venous Thromboembolic Disease

Potentially inappropriate prescribing of direct oral anticoagulants is frequent with the most common errors being dosage, administration, and duration of therapy. We developed RecosDoc-MTeV, a documentary-based clinical decision support system (CDSS) for the management of direct oral anticoagulant prescription to prevent and treat venous thromboembolism. Simultaneously, the network of Parisian public hospitals (AP-HP, France) developed narrative clinical practice guidelines (CPGs) and a companion smartphone application to enhance medication and patient safety related to direct oral anticoagulant prescription. To assess the effectiveness of these CDS tools, we performed a retrospective review of 274 random patients hospitalized in 2017, which were either at risk of venous thromboembolism or actually treated for the disease. Consistency between the two CDS tools was measured at 96.7%. Administered treatments were compliant in 67.2% and 72.3% of the cases, with AP-HP CPGs and RecosDoc-MTeV, respectively. These results support that implementing CDSSs for the prescription of direct oral anticoagulants may ensure safe prescribing of high-risk medications.

Medication in older patients reviewed multiple ways (MORE) study

Background Polypharmacy in older patients can lead to potentially inappropriate prescribing. The risk of the latter calls for effective medication review to ensure proper medication usage and safety. Objective Provide insight on the similarities and differences of medication review done in multiple ways that may lead to future possibilities to optimize medication review. Setting This study was conducted in Zuyderland Medical Centre, the second largest teaching hospital in the Netherlands. Method This descriptive study compares the quantity and content of remarks identified by medication review performed by a geriatrician, outpatient pharmacist, and Clinical Decision Support System. The content of remarks is categorized in seven categories of possible pharmacotherapeutic problems: ‘indication without medication’, ‘medication without indication’, ‘contra-indication/interaction/side-effect’, ‘dosage problem’, ‘double medication’, ‘incorrect medication’ and ‘therapeutic drug monitoring’. Main outcome measure Number and content of remarks on medication review. Results The Clinical Decision Support System (1.8 ± 0.8 vs. 0.9 ± 0.9, p < 0.001) and outpatient pharmacist (1.8 ± 0.8 vs. 0.9 ± 0.9, p = 0.045) both noted remarks in significantly more categories than the geriatricians. The Clinical Decision Support System provided more remarks on ‘double medication’, ‘dosage problem’ and ‘contraindication/interaction/side effects’ than the geriatrician (p < 0.050), while the geriatrician did on ‘medication without indication’ (p < 0.001). The Clinical Decision Support System noted significantly more remarks on ‘contraindication/interaction/side effects’ and ‘therapeutic drug monitoring’ than the outpatient pharmacist, whereas the outpatient pharmacist reported more on ‘indication without medication’ and ‘medication without indication’ than the Clinical Decision Support System (p ≤ 0.007). Conclusion Medication review performed by a geriatrician, outpatient pharmacist, and Clinical Decision Support System provides different insights and should be combined to create a more comprehensive report on medication profiles.

Implementing an Oncology Decision Support System: The Case of the Brazilian National Cancer Institute

Brazil has a complex situation in cancer treatment services. The incidence rates have reached around 600.000 new cases each year. The development of an Oncology Decision Support System (ODSS) that support cancer treatment is amongst the priorities in the cancer control program. The purpose of this article is to study the ODSS deployment at the Brazilian National Cancer Institute. The implementation of this Clinical Decision Support System employed on the management, processing, and analysis of Brazilian cancer clinical data can be considered a disruptive innovation which changes the clinical decision-making process radically.

The ALMANACH Project: Preliminary results and potentiality from Afghanistan

INTRODUCTION

ALMANACH (ALgorithms for the MANagement of Acute CHildhood illnesses) is an electronic version of IMCI (Integrated Management of Childhood Illness) running on tablets. ALMANACH enhances its concept, it integrates well into health staff's daily consultation work and facilitates diagnosis and treatment. ALMANACH informs when to refer a child or to perform a rapid diagnostic test (RDT), recommends the right treatment dosage and synchronizes collected data real time with a Health Management Information System (DHIS2) for epidemiological evaluation and decision making.

OBJECTIVES

Since May 2016, ALMANACH is under investigational deployment in three primary health care facilities in Afghanistan with the goal to improve the quality of care provided to children between 2 months and 5 years old.

METHODS

IMCI's algorithms were updated in considering latest scientific publications, national guidelines, innovations in RDTs, the target population's epidemiological profile and the local resources available. Before the implementation of the project, a direct observation of 599 consultations was carried out to assess the daily performance at three selected health facilities in Kabul.

RESULTS

The baseline survey showed that nutritional screening, vitamin A supplementation and deworming were not systematically performed: few patients were diagnosed for malnutrition (1.8%), received vitamin A (2.7%) or deworming (7.5%). Physical examination was appropriate only for 23.8% of the diagnoses of respiratory or gastrointestinal diseases, ear infection and sore throat. Respiratory rate was checked only in 33.5% of the children with fever and cough, dehydration status was assessed in only 16.5% of the diarrhoea cases. Forty-seven percent of patients received incorrect treatment. Sixty-four percent of the children, before the introduction of ALMANACH, received at least one antibiotic, although for 87.1% antibiotic therapy was unnecessary. The review of 8'047 paediatric consultations between May 2016 and September 2017 showed that with ALMANACH, malnutrition detection, deworming and Vitamin A supplementation increased respectively to 4.4%, 50.2% and 27.5%. Antibiotic prescription decreased to 21.83% and all children were examined and treated in compliance with the protocols.

CONCLUSION

A survey will be conducted one year after the implementation to validate these initial promising results. If the efficacy of the approach is confirmed, ALMANACH could establish as a powerful innovation for primary health care.

Parallel Design of Browsing Scheme and Data Model for Multi-Level Hierarchical Application Devoted to Management of Patient with Infectious Disease in Primary Care

Many decision systems are based on a hierarchical approach, enriching the known context used to finally choose the right potential action. Designing the scheme for browsing the clinical guidelines is a task devoted to expert in infectious diseases. Designing the data model is a task devoted to the expert in data modeling. As a consequence, browsing scheme and data model generally differ in terms of abstraction levels. While the browsing scheme proposes to navigate into depth, the data model stays flat. We propose here a novel method to design in parallel the browsing scheme and the data model so that both of them reflect the different abstraction levels in decision process.

Design of a Visual Interface for Comparing Antibiotics Using Rainbow Boxes

Non-optimal prescriptions of antibiotics have a negative impact on patients and population. Clinical practice guidelines are not always followed by doctors because the rationale of the recommendations is not always clear and can be difficult to understand. In this paper, we propose a new approach consisting in presenting the properties of antibiotics for allowing doctors to compare them and choose the most appropriate one. For that, we used and extended rainbow boxes, a new technique for overlapping set visualization. We tested our approach on 11 clinical situations related to urinary infections, and assessed the simplicity, the interest and utility with 11 doctors. 10 of them found that this approach was interesting and useful in clinical practice. Further studies are needed to confirm this preliminary work.

Higher Quality and Lower Cost from Improving Hospital Discharge Decision Making

This paper reports research on improving decisions about hospital discharges - decisions that are now made by physicians based on mainly subjective evaluations of patients' discharge status. We report an experiment on uptake of our clinical decision support software (CDSS) which presents physicians with evidence-based discharge criteria that can be effectively utilized at the point of care where the discharge decision is made. One experimental treatment we report prompts physician attentiveness to the CDSS by replacing the default option of universal "opt in" to patient discharge with the alternative default option of "opt out" from the CDSS recommendations to discharge or not to discharge the patient on each day of hospital stay. We also report results from experimental treatments that implement the CDSS under varying conditions of time pressure on the subjects. The experiment was conducted using resident physicians and fourth-year medical students at a university medical school as subjects.

Uncovering healthcare practitioners' information processing using the think-aloud method: From paper-based guideline to clinical decision support system

OBJECTIVE

To investigate whether the use of the think-aloud method with propositional analysis could be helpful in the design of a Clinical Decision Support System (CDSS) providing guideline recommendations about long-term follow-up of childhood cancer survivors.

MATERIALS AND METHODS

The think-aloud method was used to gain insight into healthcare professionals' information processing while reviewing a paper-based guideline. A total of 13 healthcare professionals (6 physicians and 7 physician assistants) prepared 2 fictitious patient consults using the paper-based guideline. Propositional analysis was used to analyze verbal protocols of the think-aloud sessions. A prototype CDSS was developed and a usability study was performed, again with the think-aloud method.

RESULTS

The analysis revealed that the paper-based guideline did not support healthcare practitioners in finding patient-specific recommendations. An information processing model for retrieving recommendations was developed and used as input for the design of a CDSS prototype user interface. Usability analysis of the prototype CDSS showed that the navigational structure of the system fitted well with healthcare practitioners' daily practices.

CONCLUSIONS

The think-aloud method combined with propositional analysis of healthcare practitioners' verbal utterances while they processed a paper-based guideline was useful in the design of a usable CDSS providing patient-specific guideline recommendations.