Physician Knowledge Base: Clinical Decision Support Systems

Clinical decision support systems in addiction and concurrent disorders: A systematic review and meta-analysis

INTRODUCTION

This review aims to synthesise the literature on the efficacy, evolution, and challenges of implementing Clincian Decision Support Systems (CDSS) in the realm of mental health, addiction, and concurrent disorders.

METHODS

Following PRISMA guidelines, a systematic review and meta-analysis were performed. Searches conducted in databases such as MEDLINE, Embase, CINAHL, PsycINFO, and Web of Science through 25 May 2023, yielded 27,344 records. After necessary exclusions, 69 records were allocated for detailed synthesis. In the examination of patient outcomes with a focus on metrics such as therapeutic efficacy, patient satisfaction, and treatment acceptance, meta-analytic techniques were employed to synthesise data from randomised controlled trials.

RESULTS

A total of 69 studies were included, revealing a shift from knowledge-based models pre-2017 to a rise in data-driven models post-2017. The majority of models were found to be in Stage 2 or 4 of maturity. The meta-analysis showed an effect size of -0.11 for addiction-related outcomes and a stronger effect size of -0.50 for patient satisfaction and acceptance of CDSS.

DISCUSSION

The results indicate a shift from knowledge-based to data-driven CDSS approaches, aligned with advances in machine learning and big data. Although the immediate impact on addiction outcomes is modest, higher patient satisfaction suggests promise for wider CDSS use. Identified challenges include alert fatigue and opaque AI models.

CONCLUSION

CDSS shows promise in mental health and addiction treatment but requires a nuanced approach for effective and ethical implementation. The results emphasise the need for continued research to ensure optimised and equitable use in healthcare settings.

Personalized Deep Learning Model for Clinical Target Volume on Daily Cone Beam Computed Tomography in Breast Cancer Patients

Purpose

Herein, we developed a deep learning algorithm to improve the segmentation of the clinical target volume (CTV) on daily cone beam computed tomography (CBCT) scans in breast cancer radiation therapy. By leveraging the Intentional Deep Overfit Learning (IDOL) framework, we aimed to enhance personalized image-guided radiation therapy based on patient-specific learning.

Methods and Materials

We used 240 CBCT scans from 100 breast cancer patients and employed a 2-stage training approach. The first stage involved training a novel general deep learning model (Swin UNETR, UNET, and SegResNET) on 90 patients. The second stage used intentional overfitting on the remaining 10 patients for patient-specific CBCT outputs. Quantitative evaluation was conducted using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), mean surface distance (MSD), and independent samples t test with expert contours on CBCT scans from the first to 15th fractions.

Results

IDOL integration significantly improved CTV segmentation, particularly with the Swin UNETR model (P values < .05). Using patient-specific data, IDOL enhanced the DSC, HD, and MSD metrics. The average DSC for the 15th fraction improved from 0.9611 to 0.9819, the average HD decreased from 4.0118 mm to 1.3935 mm, and the average MSD decreased from 0.8723 to 0.4603. Incorporating CBCT scans from the initial treatments and first to third fractions further improved results, with an average DSC of 0.9850, an average HD of 1.2707 mm, and an average MSD of 0.4076 for the 15th fraction, closely aligning with physician-drawn contours.

Conclusion

Compared with a general model, our patient-specific deep learning-based training algorithm significantly improved CTV segmentation accuracy of CBCT scans in patients with breast cancer. This approach, coupled with continuous deep learning training using daily CBCT scans, demonstrated enhanced CTV delineation accuracy and efficiency. Future studies should explore the adaptability of the IDOL framework to diverse deep learning models, data sets, and cancer sites.

Perspectives of Decision Support System TeleRehab in the Management of Post-Stroke Telerehabilitation

Stroke is the main cause of disability among adults. Decision-making in stroke rehabilitation is increasingly complex; therefore, the use of decision support systems by healthcare providers is becoming a necessity. However, there is a significant lack of software for the management of post-stroke telerehabilitation (TR). This paper presents the results of the developed software "TeleRehab" to support the decision-making of clinicians and healthcare providers in post-stroke TR. We designed a Python-based software with a graphical user interface to manage post-stroke TR. We searched Scopus, ScienceDirect, and PubMed databases to obtain research papers with results of clinical trials for post-stroke TR and to form the knowledge base of the software. The findings show that TeleRehab suggests recommendations for TR to provide practitioners with optimal and real-time support. We observed feasible outcomes of the software based on synthetic data of patients with balance problems, spatial neglect, and upper and lower extremities dysfunctions. Also, the software demonstrated excellent usability and acceptability scores among healthcare professionals.

[Big data and artificial intelligence in anesthesia : Reality or fiction?]

Big data and artificial intelligence are buzzwords that everyone is talking about and yet always provide a touch of science fiction to the scenery. What is the status of these topics in anesthesia? Are the first robots already rolling through the corridors while doctors are getting bored as all the work has been done? Spoiler alert! We are still far away from achieving this. Initially, paper charts and analogue notes stand in the way of comprehensive digitization. Source systems need to be merged and data standardized, harmonized and validated. Therefore, the friendly android that is rolling towards us, waving and holding a freshly brewed cup of coffee in our thoughts will have to wait; however, a glimpse of the future is already evident in some clinics and the first promising developments are already showing what could be the standard tomorrow. Learning algorithms calculate the length of stay individually for each patient in the intensive care unit (ICU), reducing negative consequences such as readmission and mortality. The field of ultrasound technology for regional anesthesia and closed-loop anesthesia systems is also demonstrating the benefits of artificial intelligence (AI)-assisted technologies in practice. The efforts are diverse and ambitious but they repeatedly collide with privacy challenges and significant capital expenditure, which weigh heavily on an already financially strained healthcare system; however, anyone who listens carefully to the medical staff knows that robots are not what they would expect and the buzzwords big data and artificial intelligence might be less science fiction than initially assumed.

Implementation costs of hospital-based computerised decision support systems: a systematic review

BACKGROUND

The importance of accurately costing implementation strategies is increasingly recognised within the field of implementation science. However, there is a lack of methodological guidance for costing implementation, particularly within digital health settings. This study reports on a systematic review of costing analyses conducted alongside implementation of hospital-based computerised decision support systems.

METHODS

PubMed, Embase, Scopus and CINAHL databases were searched between January 2010 and August 2021. Two reviewers independently screened and selected original research studies that were conducted in a hospital setting, examined the implementation of a computerised decision support systems and reported implementation costs. The Expert Recommendations for Implementing Change Framework was used to identify and categorise implementation strategies into clusters. A previously published costing framework was applied to describe the methods used to measure and value implementation costs. The reporting quality of included studies was assessed using the Consolidated Health Economic Evaluation Reporting Standards checklist.

RESULTS

Titles and abstracts of 1836 articles were screened, with nine articles eligible for inclusion in the review. Implementation costs were most frequently reported under the 'evaluative and iterative strategies' cluster, followed by 'provide interactive assistance'. Labour was the largest implementation-related cost in the included papers, irrespective of implementation strategy. Other reported costs included consumables, durable assets and physical space, which was mostly associated with stakeholder training. The methods used to cost implementation were often unclear. There was variation across studies in the overall quality of reporting.

CONCLUSIONS

A relatively small number of papers have described computerised decision support systems implementation costs, and the methods used to measure and value these costs were not well reported. Priorities for future research should include establishing consistent terminology and appropriate methods for estimating and reporting on implementation costs.

TRIAL REGISTRATION

The review protocol is registered with PROSPERO (ID: CRD42021272948).