BMC Medical Informatics and Decision Making最新文献

{"title":"Development, validation and recalibration of a prediction model for prediabetes: an EHR and NHANES-based study.","authors":"Nicholas J Casacchia, Kristin M Lenoir, Joseph Rigdon, Brian J Wells","doi":"10.1186/s12911-024-02803-w","DOIUrl":"10.1186/s12911-024-02803-w","url":null,"abstract":"<p><strong>Background: </strong>A prediction model that estimates the risk of elevated glycated hemoglobin (HbA1c) was developed from electronic health record (EHR) data to identify adult patients at risk for prediabetes who may otherwise go undetected. We aimed to assess the internal performance of a new penalized regression model using the same EHR data and compare it to the previously developed stepdown approximation for predicting HbA1c ≥ 5.7%, the cut-off for prediabetes. Additionally, we sought to externally validate and recalibrate the approximation model using 2017-2020 pre-pandemic National Health and Nutrition Examination Survey (NHANES) data.</p><p><strong>Methods: </strong>We developed logistic regression models using EHR data through two approaches: the Least Absolute Shrinkage and Selection Operator (LASSO) and stepdown approximation. Internal validation was performed using the bootstrap method, with internal performance evaluated by the Brier score, C-statistic, calibration intercept and slope, and the integrated calibration index. We externally validated the approximation model by applying original model coefficients to NHANES, and we examined the approximation model's performance after recalibration in NHANES.</p><p><strong>Results: </strong>The EHR cohort included 22,635 patients, with 26% identified as having prediabetes. Both the LASSO and approximation models demonstrated similar discrimination in the EHR cohort, with optimism-corrected C-statistics of 0.760 and 0.763, respectively. The LASSO model included 23 predictor variables, while the approximation model contained 8. Among the 2,348 NHANES participants who met the inclusion criteria, 30.1% had prediabetes. External validation of the LASSO model was not possible due to the unavailability of some predictor variables. The approximation model discriminated well in the NHANES dataset, achieving a C-statistic of 0.787.</p><p><strong>Conclusion: </strong>The approximation method demonstrated comparable performance to LASSO in the EHR development cohort, making it a viable option for healthcare organizations with limited resources to collect a comprehensive set of candidate predictor variables. NHANES data may be suitable for externally validating a clinical prediction model developed with EHR data to assess generalizability to a nationally representative sample, depending on the model's intended use and the alignment of predictor variable definitions with those used in the model's original development.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"387"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11657225/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142852899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of deep learning in wound size measurement using fingernail as the reference.","authors":"Dun-Hao Chang, Duc-Khanh Nguyen, Thi-Ngoc Nguyen, Chien-Lung Chan","doi":"10.1186/s12911-024-02778-8","DOIUrl":"10.1186/s12911-024-02778-8","url":null,"abstract":"<p><strong>Objective: </strong>Most current wound size measurement devices or applications require manual wound tracing and reference markers. Chronic wound care usually relies on patients or caregivers who might have difficulties using these devices. Considering a more human-centered design, we propose an automatic wound size measurement system by combining three deep learning (DL) models and using fingernails as a reference.</p><p><strong>Materials and methods: </strong>DL models (Mask R-CNN, Yolov5, U-net) were trained and tested using photographs of chronic wounds and fingernails. Nail width was obtained through using Mask R-CNN, Yolov5 to crop the wound from the background, and U-net to calculate the wound area. The system's effectiveness and accuracy were evaluated with 248 images, and users' experience analysis was conducted with 30 participants.</p><p><strong>Results: </strong>Individual model training achieved a 0.939 Pearson correlation coefficient (PCC) for nail-width measurement. Yolov5 had the highest mean average precision (0.822) with an Intersection-over-Union threshold of 0.5. U-net achieved a mean pixel accuracy of 0.9523. The proposed system recognized 100% of fingernails and 97.76% of wounds in the test datasets. PCCs for converting nail width to measured and default widths were 0.875 and 0.759, respectively. Most inexperienced caregivers consider convenience is the most important factor when using a size-measuring tool. Our proposed system yielded 90% satisfaction in the convenience aspect as well as the overall evaluation.</p><p><strong>Conclusion: </strong>The proposed system performs fast and easy-to-use wound size measurement with acceptable precision. Its novelty not only allows for conveniences and easy accessibility in homecare settings and for inexperienced caregivers; but also facilitates clinical treatments and documentation, and supports telemedicine.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"390"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11656912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142853024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards improving district health information system data consistency, report completeness and timeliness in Neno district, Malawi.","authors":"Moses Banda Aron, Wiseman Emmanuel Nkhomah, Luckson Dullie, Beatrice Matanje, Chiyembekezo Kachimanga, Enoch Ndarama, Stellar Chibvunde, Manuel Mulwafu, Gladys Mtalimanja Banda, Kondwani Mpinga, Martha Kutsamba, Margaret Mikwamba, Isaac Mphande, Kondwani Matiya, Charles F Buleya, Mwayi Chunga, Fabien Munyaneza","doi":"10.1186/s12911-024-02802-x","DOIUrl":"10.1186/s12911-024-02802-x","url":null,"abstract":"<p><strong>Background: </strong>Quality data is crucial in making informed decisions regarding health services; However, the literature suggests that in many LMICs including Malawi, it remains of poor quality. Data quality is measured in terms of completeness, timeliness and consistency among other parameters. We describe the Ministry of Health's District Health Information System (DHIS2) report completeness and timeliness at three levels: National, South West Zone (SWZ) and Neno district. Further, describe data consistency following data quality assessments (DQA) in Neno district, Malawi.</p><p><strong>Methods: </strong>We conducted a descriptive retrospective study by extracting DHIS2 report completeness and timeliness at three levels and used DQA data in Neno district between January 2016 and December 2022. We defined report completeness as the number of reports in DHIS2 against those expected, timeliness as the number of reports entered into DHIS2 before the deadline and consistency as the level of agreement between three sources: register, report and DHIS2 system. We presented the data graphically and calculated yearly median reporting rates for weekly, monthly and quarterly reports against the national target of 85%. We utilized a verification factor (VF) of 0-200% to evaluate consistency between three sources in the Neno district. VF exceeding 100% indicated over-reporting, 100% as a perfect match, and less than 100% as under-reporting, with an acceptable 90-110% range.</p><p><strong>Results: </strong>During the study period, we found increased trends in weekly, monthly and quarterly report completeness at all three levels but were below 85%. Neno district surpassed the target from 2020 onward for weekly reports and from 2019 onward for monthly reports. Similar increased trends were observed for report timeliness with below threshold of 85% except for Neno district monthly report from 2021 onward. We found inconsistencies in data entry from the report to DHIS2 (VF: >90% - <110%) in Neno district. Similarly, under and over-reporting occurred between the register and the report (VF: <90% and > 110%) were observed. These findings should be considered when using DHIS2 for decision-making.</p><p><strong>Conclusion: </strong>In general, we found increased completeness and timeliness rates at all three levels, however, less than the set target of 85%. We suggest continued support, including routine DQAs and report monitoring, towards improving DHIS2 data quality.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"376"},"PeriodicalIF":3.3,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11622671/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142791451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A heuristic evaluation of a pharmacy surveillance information system.","authors":"Reza Abbasi, Mehrdad Farzandipour, Habiballah Rahimi, Yang Gong, Ehsan Nabovati","doi":"10.1186/s12911-024-02786-8","DOIUrl":"10.1186/s12911-024-02786-8","url":null,"abstract":"<p><strong>Introduction: </strong>The pharmacy surveillance information system (PSIS) is intended to manage the dispensing practice of under-controlled drugs and substances. We designed and developed a PSIS for the first time in a developing country. This study aimed to evaluate the usability of this system using a heuristic evaluation method before the pilot implementation in outpatient pharmacies.</p><p><strong>Materials and methods: </strong>The study was conducted in 2022 during the development of a pharmacy surveillance information system. Five evaluators examined the system using Nielson's heuristic evaluation method. The detected usability problems were categorized into 10 Nielson's usability principles, and their severity was calculated.</p><p><strong>Results: </strong>In total, 91 unique usability problems were identified. The most detected usability problems were minor (60%). The \"consistency and standard\" (31%), \"aesthetic and minimalist design\" (28%), and \"match between system and the real world\" (12%) were the most frequent problems. Also, the \"flexibility and efficiency of use\" (mean = 2.9), \"error prevention\" (2.85), and \"user control and freedom\" (2.8) were the most severe problems.</p><p><strong>Conclusion: </strong>The study has identified the most common and severe usability issues of an information system. It is important for the system developers to address these issues as it can significantly improve users' trust and satisfaction. Therefore, all the identified usability problems were resolved before the system was implemented.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"374"},"PeriodicalIF":3.3,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11619703/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating structured and unstructured data for predicting emergency severity: an association and predictive study using transformer-based natural language processing models.","authors":"Xingyu Zhang, Yanshan Wang, Yun Jiang, Charissa B Pacella, Wenbin Zhang","doi":"10.1186/s12911-024-02793-9","DOIUrl":"10.1186/s12911-024-02793-9","url":null,"abstract":"<p><strong>Background: </strong>Efficient triage in emergency departments (EDs) is critical for timely and appropriate care. Traditional triage systems primarily rely on structured data, but the increasing availability of unstructured data, such as clinical notes, presents an opportunity to enhance predictive models for assessing emergency severity and to explore associations between patient characteristics and severity outcomes. This study aimed to evaluate the effectiveness of combining structured and unstructured data to predict emergency severity more accurately.</p><p><strong>Methods: </strong>Data from the 2021 National Hospital Ambulatory Medical Care Survey (NHAMCS) for adult ED patients were used. Emergency severity was categorized into urgent (scores 1-3) and non-urgent (scores 4-5) based on the Emergency Severity Index. Unstructured data, including chief complaints and reasons for visit, were processed using a Bidirectional Encoder Representations from Transformers (BERT) model. Structured data included patient demographics and clinical information. Four machine learning models-Logistic Regression, Random Forest, Gradient Boosting, and Extreme Gradient Boosting-were applied to three data configurations: structured data only, unstructured data only, and combined data. A mean probability model was also created by averaging the predicted probabilities from the structured and unstructured models.</p><p><strong>Results: </strong>The study included 8,716 adult patients, of whom 74.6% were classified as urgent. Association analysis revealed significant predictors of emergency severity, including older age (OR = 2.13 for patients 65 +), higher heart rate (OR = 1.56 for heart rates > 90 bpm), and specific chronic conditions such as chronic kidney disease (OR = 2.28) and coronary artery disease (OR = 2.55). Gradient Boosting with combined data demonstrated the highest performance, achieving an area under the curve (AUC) of 0.789, an accuracy of 0.726, and a precision of 0.892. The mean probability model also showed improvements over structured-only models.</p><p><strong>Conclusions: </strong>Combining structured and unstructured data improved the prediction of emergency severity in ED patients, highlighting the potential for enhanced triage systems. Integrating text data into predictive models can provide more accurate and nuanced severity assessments, improving resource allocation and patient outcomes. Further research should focus on real-time application and validation in diverse clinical settings.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"372"},"PeriodicalIF":3.3,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11619330/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142779083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a nomogram model for prolonged length of stay in spinal fusion patients: a retrospective analysis.","authors":"Linghong Wu, Xiaozhong Peng, Yao Lu, Cuiping Fu, Liujun She, Guangwei Zhu, Xianglong Zhuo, Wei Hu, Xiangtao Xie","doi":"10.1186/s12911-024-02787-7","DOIUrl":"10.1186/s12911-024-02787-7","url":null,"abstract":"<p><strong>Objective: </strong>To develop a nomogram model for the prediction of the risk of prolonged length of hospital stay (LOS) in spinal fusion patients.</p><p><strong>Methods: </strong>A retrospective cohort study was carried out on 6272 patients who had undergone spinal fusion surgery. Least absolute shrinkage and selection operator (LASSO) regression was performed on the training sets to screen variables, and the importance of independent variables was ranked via random forest. In addition, various independent variables were used in the construction of models 1 and 2. A receiver operating characteristic curve was used to evaluate the models' predictive performance. We employed Delong tests to compare the area under the curve (AUC) of the different models. Assessment of the models' capability to improve classification efficiency was achieved using continuous net reclassification improvement (NRI) and integrated discrimination improvement (IDI). The Hosmer-Lemeshow method and calibration curve was utilised to assess the calibration degree, and decision curve to evaluate its clinical practicality. A bootstrap technique that involved 10 cross-validations and was performed 10,000 times was used to conduct internal and external validation. The were outcomes of the model exhibited in a nomogram graphics. The developed nomogram was validated both internally and externally.</p><p><strong>Results: </strong>Model 1 was identified as the optimal model. The risk factors for prolonged LOS comprised blood transfusion, operation type, use of tranexamic acid (TXA), diabetes, electrolyte disturbance, body mass index (BMI), surgical procedure performed, the number of preoperative diagnoses and operative time. The diagnostic performance of the nomogram model was satisfactory, with AUC values of 0.784 and 0.795 for the internal and external validation sets, respectively. Model discrimination was favourable in both the internal (C-statistic, 0.811) and external (C-statistic, 0.814) validation sets. Calibration curve and Hosmer-Lemeshow test showed acceptable agreement between predicted and actual results. The decision curve shows that the model provides net clinical benefit within a certain decision threshold range.</p><p><strong>Conclusions: </strong>This study developed and validated a nomogram to identify the risk of prolonged LOS in spinal fusion patients, which may help clinicians to identify high-risk groups at an early stage. Predictors identified included blood transfusion, operation type, use of TXA, diabetes, electrolyte disturbance, BMI, surgical procedure performed, number of preoperative diagnoses and operative time.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"373"},"PeriodicalIF":3.3,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11619620/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Decision Tree-Driven IoT systems for improved pre-natal diagnostic accuracy.","authors":"Xuewen Yang, Ling Liu, Yan Wang","doi":"10.1186/s12911-024-02759-x","DOIUrl":"10.1186/s12911-024-02759-x","url":null,"abstract":"<p><p>Prenatal diagnostics are vital for the woman as well as her unborn baby. The diagnostics help in the early identification of the possibility of complication and the initial measures that help to ameliorate the mother and the fetus health status are taken. Over the year's various techniques have been employed in diagnosing genetic disorders before birth that lack effectiveness in terms of cost, time, and places to access ultra-modern health facilities. To overcome these problems, this paper puts forward a diagnostic model that integrates Internet of Things innovation with a Machine Learning approach which is the Decision Tree Algorithms. First, it implies the application of IOT devices in the collection of vital information like heart rate, blood pressure, glucose levels, and fetal movement. The data is structured in the form of a dataset and transmitted to a Big Data storage for warehousing and processing. Secondly, the DTA is employed to analyze the data and look for patterns and possibilities of future health complications. The DTA operates in that it divides the dataset into subsets considering specific features and formulates a tree-like model of decisions. At every node, the algorithm chooses the attribute which has the highest information gain, to partition the data into different classes. This process goes on until it reaches a decision node through which, it can decide probable health problems from the input data. To increase the reliability of the developed model this study fine-tunes the model by using a large database of pre-natal health records. The system is capable of collecting data in real-time and flagging data that needs attention in the case of any abnormality to the health professional. The above methodology was tested on a 1000-record database of pre-natal health records where the proposal achieved 95% possibility of potential health problems as against 85% by classical statistical analysis. Furthermore, the system scaled down the number of false positive cases by 20 percent and false negatives by 15 percent thus the efficacy of the system.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"375"},"PeriodicalIF":3.3,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11622561/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated derivation of diagnostic criteria for lung cancer using natural language processing on electronic health records: a pilot study.","authors":"Andrew Houston, Sophie Williams, William Ricketts, Charles Gutteridge, Chris Tackaberry, John Conibear","doi":"10.1186/s12911-024-02790-y","DOIUrl":"10.1186/s12911-024-02790-y","url":null,"abstract":"<p><strong>Background: </strong>The digitisation of healthcare records has generated vast amounts of unstructured data, presenting opportunities for improvements in disease diagnosis when clinical coding falls short, such as in the recording of patient symptoms. This study presents an approach using natural language processing to extract clinical concepts from free-text which are used to automatically form diagnostic criteria for lung cancer from unstructured secondary-care data.</p><p><strong>Methods: </strong>Patients aged 40 and above who underwent a chest x-ray (CXR) between 2016 and 2022 were included. ICD-10 and unstructured data were pulled from their electronic health records (EHRs) over the preceding 12 months to the CXR. The unstructured data were processed using named entity recognition to extract symptoms, which were mapped to SNOMED-CT codes. Subsumption of features up the SNOMED-CT hierarchy was used to mitigate against sparse features and a frequency-based criteria, combined with univariate logarithmic probabilities, was applied to select candidate features to take forward to the model development phase. A genetic algorithm was employed to identify the most discriminating features to form the diagnostic criteria.</p><p><strong>Results: </strong>75002 patients were included, with 1012 lung cancer diagnoses made within 12 months of the CXR. The best-performing model achieved an AUROC of 0.72. Results showed that an existing 'disorder of the lung', such as pneumonia, and a 'cough' increased the probability of a lung cancer diagnosis. 'Anomalies of great vessel', 'disorder of the retroperitoneal compartment' and 'context-dependent findings', such as pain, statistically reduced the risk of lung cancer, making other diagnoses more likely. The performance of the developed model was compared to the existing cancer risk scores, demonstrating superior performance.</p><p><strong>Conclusions: </strong>The proposed methods demonstrated success in leveraging unstructured secondary-care data to derive diagnostic criteria for lung cancer, outperforming existing risk tools. These advancements show potential for enhancing patient care and results. However, it is essential to tackle specific limitations by integrating primary care data to ensure a more thorough and unbiased development of diagnostic criteria. Moreover, the study highlights the importance of contextualising SNOMED-CT concepts into meaningful terminology that resonates with clinicians, facilitating a clearer and more tangible understanding of the criteria applied.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"371"},"PeriodicalIF":3.3,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11616170/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142778984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Patient and caregiver perceptions of electronic health records interoperability in the NHS and its impact on care quality: a focus group study.","authors":"Edmond Li, Olivia Lounsbury, Jonathan Clarke, Hutan Ashrafian, Ara Darzi, Ana Luisa Neves","doi":"10.1186/s12911-024-02789-5","DOIUrl":"10.1186/s12911-024-02789-5","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The proliferation of electronic health records (EHR) in health systems of many high-income countries has ushered in profound changes to how clinical information is used, stored, and disseminated. For patients, being able to easily access and share their health information electronically through interoperable EHRs can often impact safety and their experience when seeking care across healthcare providers. While extensive research exists examining how EHRs affected workflow and technical challenges such as limited interoperability, much of it was done from the viewpoint of healthcare staff rather than from patients themselves. This leaves a critical knowledge gap in our evidence base to inform better implementation of health information technologies which needs addressing.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Aims and objectives: &lt;/strong&gt;This study aimed to explore how patients with chronic conditions or polypharmacy and their caregivers perceive the current state of EHR interoperability, identify instances where it was associated with negative health outcomes, and elucidate patient-driven recommendations to address concerns raised.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A total of 18 patients and caregivers participated in five online focus groups between May-July 2022. Thematic analysis was performed to generate codes and derive higher-order themes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Participants highlighted that EHR interoperability in the NHS does not meet patient needs and expectations. While patients' understanding of the concept of EHR interoperability was mixed, most were able to describe how the inability to seamlessly share health information within EHR has negatively impacted care. Limited interoperability contributed to inaccurate medical records, perpetuated existing incorrect information, impaired clinical decision-making, and often required patients to resort to using workarounds. Patients also voiced ideas for potential solutions for consideration. These included a move towards a one-centralised system approach, strengthening data security measures to augment other efforts to increase interoperability, prioritising health information technology training for NHS staff, and involving more allied health professionals and patients themselves in the EHR data curation process.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;Our study contributes to the existing body of literature by providing the perspectives of patients and carers most likely to encounter interoperability challenges and therefore those most ideally positioned to propose potential solutions. As highlighted by patients, researchers and policymakers should consider social, educational, and organisational solutions, in addition to technical solutions. Lack of interoperability (i.e., the ability to share a patient's health information electronically between healthcare providers) can affect the quality of care received. However, much of the existing research was done from the viewpoint of h","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"370"},"PeriodicalIF":3.3,"publicationDate":"2024-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11616290/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142766470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive modelling of linear growth faltering among pediatric patients with Diarrhea in Rural Western Kenya: an explainable machine learning approach.","authors":"Billy Ogwel, Vincent H Mzazi, Alex O Awuor, Caleb Okonji, Raphael O Anyango, Caren Oreso, John B Ochieng, Stephen Munga, Dilruba Nasrin, Kirkby D Tickell, Patricia B Pavlinac, Karen L Kotloff, Richard Omore","doi":"10.1186/s12911-024-02779-7","DOIUrl":"10.1186/s12911-024-02779-7","url":null,"abstract":"<p><strong>Introduction: </strong>Stunting affects one-fifth of children globally with diarrhea accounting for an estimated 13.5% of stunting. Identifying risk factors for its precursor, linear growth faltering (LGF), is critical to designing interventions. Moreover, developing new predictive models for LGF using more recent data offers opportunity to enhance model accuracy, interpretability and capture new insights. We employed machine learning (ML) to derive and validate a predictive model for LGF among children enrolled with diarrhea in the Vaccine Impact on Diarrhea in Africa (VIDA) study and the Enterics for Global Heath (EFGH) - Shigella study in rural western Kenya.</p><p><strong>Methods: </strong>We used 7 diverse ML algorithms to retrospectively build prognostic models for the prediction of LGF (≥ 0.5 decrease in height/length for age z-score [HAZ]) among children 6-35 months. We used de-identified data from the VIDA study (n = 1,106) combined with synthetic data (n = 8,894) in model development, which entailed split-sampling and K-fold cross-validation with over-sampling technique, and data from EFGH-Shigella study (n = 655) for temporal validation. Potential predictors (n = 65) included demographic, household-level characteristics, illness history, anthropometric and clinical data were identified using boruta feature selection with an explanatory model analysis used to enhance interpretability.</p><p><strong>Results: </strong>The prevalence of LGF in the development and temporal validation cohorts was 187 (16.9%) and 147 (22.4%), respectively. Feature selection identified the following 6 variables used in model development, ranked by importance: age (16.6%), temperature (6.0%), respiratory rate (4.1%), SAM (3.4%), rotavirus vaccination (3.3%), and skin turgor (2.1%). While all models showed good prediction capability, the gradient boosting model achieved the best performance (area under the curve % [95% Confidence Interval]: 83.5 [81.6-85.4] and 65.6 [60.8-70.4]) on the development and temporal validation datasets, respectively.</p><p><strong>Conclusion: </strong>Our findings accentuate the enduring relevance of established predictors of LGF whilst demonstrating the practical utility of ML algorithms for rapid identification of at-risk children.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"368"},"PeriodicalIF":3.3,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11613762/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142766473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}