Merging Data Diversity of Clinical Medical Records to Improve Effectiveness

Analysis of machine learning algorithmic models for the prediction of vital status at six months after hip fracture in patients older than 74 years

BACKGROUND AND OBJECTIVE

The objective is to develop a model that predicts vital status six months after fracture as accurately as possible. For this purpose we will use five different data sources obtained through the National Hip Fracture Registry, the Health Management Unit and the Economic Management Department.

MATERIAL AND METHODS

The study population is a cohort of patients over 74 years of age who suffered a hip fracture between May 2020 and December 2022. A warehouse is created from five different data sources with the necessary variables. An analysis of missing values and outliers as well as unbalanced classes of the target variable («vital status») is performed. Fourteen different algorithmic models are trained with the training. The model with the best performance is selected and a fine tuning is performed. Finally, the performance of the selected model is analyzed with test data.

RESULTS

A data warehouse is created with 502 patients and 144 variables. The best performing model is Linear Regression. Sixteen of the 24 cases of deceased patients are classified as live, and 14 live patients are classified as deceased. A sensitivity of 31%, an accuracy of 34% and an area under the curve of 0.65 is achieved.

CONCLUSIONS

We have not been able to generate a model for the prediction of six-month survival in the current cohort. However, we believe that the method used for the generation of algorithms based on machine learning can serve as a reference for future works.

Multidisciplinary user experience of a newly implemented electronic patient record in Ireland: An exploratory qualitative study

BACKGROUND

Implementation of an Electronic Patient Record (EPR) in a key milestone in the digital strategy of modern healthcare organisations. The implementation of EPR systems can be viewed as challenging and complex.

OBJECTIVE

The aim of the study was to investigate user perspectives and experiences of the implementation of an Electronic Medical Record in a major academic teaching hospital, with simultaneous 'go-live' across the whole hospital taking place.

METHODS

Focus groups and individual in-depth interviews were conducted with stakeholders and users (n = 105), approximately nine months post-EPR implementation. The study explored EPR users' perceptions using an extended theoretical framework of the DeLone and McLean Information Systems Success Model (2003), which measured information systems, system quality, information quality, service quality, use/perceived usefulness & user satisfaction and net benefits.

RESULTS

Staff engagement and satisfaction was high and the EPR is accepted as the new standard way of completing care. There was agreement that the EPR affords transparency, and greater accountability. There was some concern expressed regarding impact of the EPR on interprofessional and patient/provider interactions and communication. Physicians reported the inputting of social history through free text as an issue of concern and time consuming. The Big Bang approach with mandatory conversion was key to the successful adoption of EPR. There was consensus across professional and administrative respondents that there was no appetite to return to paper-based records.

CONCLUSION

The successful roll out of the EPR reflects the digital readiness of healthcare providers and organisations. The potential for unintended consequences on work process requires continual monitoring. A key future benefit of the EPR will be the capacity to reach a broader understanding and analysis of variation in processes and outcomes within healthcare organisations. It is clear that skills in data analytics will be needed to mine data successfully.

Ten Topics to Get Started in Medical Informatics Research

The vast and heterogeneous data being constantly generated in clinics can provide great wealth for patients and research alike. The quickly evolving field of medical informatics research has contributed numerous concepts, algorithms, and standards to facilitate this development. However, these difficult relationships, complex terminologies, and multiple implementations can present obstacles for people who want to get active in the field. With a particular focus on medical informatics research conducted in Germany, we present in our Viewpoint a set of 10 important topics to improve the overall interdisciplinary communication between different stakeholders (eg, physicians, computational experts, experimentalists, students, patient representatives). This may lower the barriers to entry and offer a starting point for collaborations at different levels. The suggested topics are briefly introduced, then general best practice guidance is given, and further resources for in-depth reading or hands-on tutorials are recommended. In addition, the topics are set to cover current aspects and open research gaps of the medical informatics domain, including data regulations and concepts; data harmonization and processing; and data evaluation, visualization, and dissemination. In addition, we give an example on how these topics can be integrated in a medical informatics curriculum for higher education. By recognizing these topics, readers will be able to (1) set clinical and research data into the context of medical informatics, understanding what is possible to achieve with data or how data should be handled in terms of data privacy and storage; (2) distinguish current interoperability standards and obtain first insights into the processes leading to effective data transfer and analysis; and (3) value the use of newly developed technical approaches to utilize the full potential of clinical data.

Pretrained transformer framework on pediatric claims data for population specific tasks

The adoption of electronic health records (EHR) has become universal during the past decade, which has afforded in-depth data-based research. By learning from the large amount of healthcare data, various data-driven models have been built to predict future events for different medical tasks, such as auto diagnosis and heart-attack prediction. Although EHR is abundant, the population that satisfies specific criteria for learning population-specific tasks is scarce, making it challenging to train data-hungry deep learning models. This study presents the Claim Pre-Training (Claim-PT) framework, a generic pre-training model that first trains on the entire pediatric claims dataset, followed by a discriminative fine-tuning on each population-specific task. The semantic meaning of medical events can be captured in the pre-training stage, and the effective knowledge transfer is completed through the task-aware fine-tuning stage. The fine-tuning process requires minimal parameter modification without changing the model architecture, which mitigates the data scarcity issue and helps train the deep learning model adequately on small patient cohorts. We conducted experiments on a real-world pediatric dataset with more than one million patient records. Experimental results on two downstream tasks demonstrated the effectiveness of our method: our general task-agnostic pre-training framework outperformed tailored task-specific models, achieving more than 10% higher in model performance as compared to baselines. In addition, our framework showed a potential to transfer learned knowledge from one institution to another, which may pave the way for future healthcare model pre-training across institutions.

Systematic Review and Methodological Considerations for the Use of Single Prolonged Stress and Fear Extinction Retention in Rodents

Posttraumatic stress disorder (PTSD) is a mental health condition triggered by experiencing or witnessing a terrifying event that can lead to lifelong burden that increases mortality and adverse health outcomes. Yet, no new treatments have reached the market in two decades. Thus, screening potential interventions for PTSD is of high priority. Animal models often serve as a critical translational tool to bring new therapeutics from bench to bedside. However, the lack of concordance of some human clinical trial outcomes with preclinical animal efficacy findings has led to a questioning of the methods of how animal studies are conducted and translational validity established. Thus, we conducted a systematic review to determine methodological variability in studies that applied a prominent animal model of trauma-like stress, single prolonged stress (SPS). The SPS model has been utilized to evaluate a myriad of PTSD-relevant outcomes including extinction retention. Rodents exposed to SPS express an extinction retention deficit, a phenotype identified in humans with PTSD, in which fear memory is aberrantly retained after fear memory extinction. The current systematic review examines methodological variation across all phases of the SPS paradigm, as well as strategies for behavioral coding, data processing, statistical approach, and the depiction of data. Solutions for key challenges and sources of variation within these domains are discussed. In response to methodological variation in SPS studies, an expert panel was convened to generate methodological considerations to guide researchers in the application of SPS and the evaluation of extinction retention as a test for a PTSD-like phenotype. Many of these guidelines are applicable to all rodent paradigms developed to model trauma effects or learned fear processes relevant to PTSD, and not limited to SPS. Efforts toward optimizing preclinical model application are essential for enhancing the reproducibility and translational validity of preclinical findings, and should be conducted for all preclinical psychiatric research models.