Application of Machine and Deep Learning Algorithms in Intelligent Clinical Decision Support Systems in Healthcare

Kim, Jong Taek

doi:10.4172/2157-7420.1000321

Cited by 21 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the past decade, various advanced techniques in predictive analytics commonly known as machine learning (ML) have gained interest in orthopaedics and medicine at large. 1 The effectiveness of ML compared with more traditional methods has been well demonstrated in solving classification problems, especially in medical image analysis, but as of yet has not been widely adopted by spine surgeons. 2 , 3 The increasing accumulation of health data leaves a gap between available data and actual data use.…”

Section: Introductionmentioning

confidence: 99%

Applied Machine Learning for Spine Surgeons: Predicting Outcome for Patients Undergoing Treatment for Lumbar Disc Herniation Using PRO Data

Pedersen

Andersen

Carreon

et al. 2020

Global Spine Journal

View full text Add to dashboard Cite

Study Design: Retrospective/prospective study. Objective: Models based on preoperative factors can predict patients’ outcome at 1-year follow-up. This study measures the performance of several machine learning (ML) models and compares the results with conventional methods. Methods: Inclusion criteria were patients who had lumbar disc herniation (LDH) surgery, identified in the Danish national registry for spine surgery. Initial training of models included 16 independent variables, including demographics and presurgical patient-reported measures. Patients were grouped by reaching minimal clinically important difference or not for EuroQol, Oswestry Disability Index, Visual Analog Scale (VAS) Leg, and VAS Back and by their ability to return to work at 1 year follow-up. Data were randomly split into training, validation, and test sets by 50%/35%/15%. Deep learning, decision trees, random forest, boosted trees, and support vector machines model were trained, and for comparison, multivariate adaptive regression splines (MARS) and logistic regression models were used. Model fit was evaluated by inspecting area under the curve curves and performance during validation. Results: Seven models were arrived at. Classification errors were within ±1% to 4% SD across validation folds. ML did not yield superior performance compared with conventional models. MARS and deep learning performed consistently well. Discrepancy was greatest among VAS Leg models. Conclusions: Five predictive ML and 2 conventional models were developed, predicting improvement for LDH patients at the 1-year follow-up. We demonstrate that it is possible to build an ensemble of models with little effort as a starting point for further model optimization and selection.

show abstract

Section: Introductionmentioning

confidence: 99%

Applied Machine Learning for Spine Surgeons: Predicting Outcome for Patients Undergoing Treatment for Lumbar Disc Herniation Using PRO Data

Pedersen

Andersen

Carreon

et al. 2020

Global Spine Journal

View full text Add to dashboard Cite

show abstract

“…Similarly, healthcare commissioners can be assured that the standardised assessment was comprehensive and does not generate false positives leading to the over prescribing of CPAP therapy. Furthermore, as large volumes of patients come through this intelligent system, we suggest that machine-based learning should be applied to further refine decision prompts [34]. We have described the use for initial assessment, but having collected and stored the initial data, the next opportunity is to make use of informatics for objective monitoring and follow-up of their progress, and much of that may be possible remotely.…”

Section: Discussionmentioning

confidence: 99%

Implementation of a computer-guided consultation in the assessment of suspected obstructive sleep apnoea syndrome

et al. 2020

View full text Add to dashboard Cite

BackgroundWe describe implementation of a clinical decision support system, a computer-guided consultation (CGC), in the assessment of subjects referred with suspected obstructive sleep apnoea syndrome (OSAS).MethodsTwo cohorts of patients were assessed. The first 100 cases had data collected with the CGC by a specialist sleep physician (stage1). A further 100 cases were assessed by a nonspecialist using the CGC (stage 2). For each case, the diagnosis suggested by the CGC was compared with the final diagnosis made by a second specialist sleep physician blinded to the CGC diagnosis.ResultsStage 1: of 100 people evaluated, a final diagnosis of OSAS was made by both the sleep specialist and CGC in 88% of cases. In 7 of the remaining 12 cases, both agreed there was “No evidence of OSAS”; in 5 cases the CGC did not reach a final diagnosis instead prompting specialist referral. Stage 2: 100 people were evaluated; 95% were evaluable. Both CGC and the sleep specialist made a diagnosis of OSAS in 83 cases (87%), in 5 cases both agreed there was no OSAS, whereas in 7 cases the CGC prompted a specialist review due to unexplained symptoms. The CGC was concordant with the final diagnosis in 95% and 93% of cases in the two cohorts, respectively and where there was doubt, prompted for clinical review. No OSAS cases were overlooked by the CGC.ConclusionAn intelligent CGC program creates opportunities in sleep medicine management pathways to safely yet effectively utilise nonspecialists working under specialist supervision.

show abstract

“…In the healthcare context, AI systems are being developed to support a variety of processes, including clinical (e.g., diagnostic, treatment, documentation) and administrative (e.g., management, scheduling, billing) processes (Park et al, 2019). Studies have shown that while many AI systems have been developed, few have achieved success in practice to date (He et al, 2019;Kim, 2018). Challenges that have hindered development of successful AI systems in healthcare include the dynamic nature of healthcare information, limits to data standardization, data sharing, and interoperability of datasets that must be fed into AI systems; limited transparency of AI mechanisms to users; and ethical issues related to ownership of information, consent, privacy, and discrimination (He et al, 2019;Racine, Boehlen, & Sample, 2019).…”

Section: Human-ai Collaboration In Knowledge Workmentioning

confidence: 99%

Batman and Robin in Healthcare Knowledge Work: Human-AI Collaboration by Clinical Documentation Integrity Specialists

Bossen

Pine

2023

ACM Trans. Comput.-Hum. Interact.

View full text Add to dashboard Cite

This paper describes the successful collaboration ‘in the wild’ between Clinical Documentation Integrity Specialists (CDIS) and an Artificial Intelligence (AI)-embedded software to conduct knowledge work. CDIS review patient charts in near real time to improve clinicians’ documentation, with the goal to make medical documentation more accurate, consistent and complete. CDIS collaborate with an AI-embedded “Computer Assisted Coding” (CAC) system that scans records from the Electronic Healthcare Record and auto-suggests codes based on natural language processing. CDIS find the CAC's suggestions are often inaccurate—often humorously so. Still, they find the CAC to be a useful helper, like Robin is to Batman. This human-AI collaboration is contingent on several factors: the flexible integration of the AI into the workflow similar to the notion of unremarkable AI; supporting the CDIS’ sensemaking; the CDIS’ knowledge about the CAC being predictably unreliable, an experience by the CDIS of the AI's value; humans remaining in control; and ability to experiment with the AI, which spurs reflection and learning for these knowledge workers.

show abstract

Application of Machine and Deep Learning Algorithms in Intelligent Clinical Decision Support Systems in Healthcare

Cited by 21 publications

References 0 publications

Applied Machine Learning for Spine Surgeons: Predicting Outcome for Patients Undergoing Treatment for Lumbar Disc Herniation Using PRO Data

Applied Machine Learning for Spine Surgeons: Predicting Outcome for Patients Undergoing Treatment for Lumbar Disc Herniation Using PRO Data

Implementation of a computer-guided consultation in the assessment of suspected obstructive sleep apnoea syndrome

Batman and Robin in Healthcare Knowledge Work: Human-AI Collaboration by Clinical Documentation Integrity Specialists

Contact Info

Product

Resources

About