17 research outputs found
Prediction of disease comorbidity using explainable artificial intelligence and machine learning techniques: A systematic review
No full textObjective:
Disease comorbidity is a major challenge in healthcare affecting the patient's quality of life and costs. AI-based prediction of comorbidities can overcome this issue by improving precision medicine and providing holistic care. The objective of this systematic literature review was to identify and summarise existing machine learning (ML) methods for comorbidity prediction and evaluate the interpretability and explainability of the models.
Materials and methods:
The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework was used to identify articles in three databases: Ovid Medline, Web of Science and PubMed. The literature search covered a broad range of terms for the prediction of disease comorbidity and ML, including traditional predictive modelling.
Results:
Of 829 unique articles, 58 full-text papers were assessed for eligibility. A final set of 22 articles with 61 ML models was included in this review. Of the identified ML models, 33 models achieved relatively high accuracy (80–95%) and AUC (0.80–0.89). Overall, 72% of studies had high or unclear concerns regarding the risk of bias.
Discussion:
This systematic review is the first to examine the use of ML and explainable artificial intelligence (XAI) methods for comorbidity prediction. The chosen studies focused on a limited scope of comorbidities ranging from 1 to 34 (mean = 6), and no novel comorbidities were found due to limited phenotypic and genetic data. The lack of standard evaluation for XAI hinders fair comparisons.
Conclusion:
A broad range of ML methods has been used to predict the comorbidities of various disorders. With further development of explainable ML capacity in the field of comorbidity prediction, there is a significant possibility of identifying unmet health needs by highlighting comorbidities in patient groups that were not previously recognised to be at risk for particular comorbidities
Towards mitigating health inequity via machine learning: a nationwide cohort study to develop and validate ethnicity-specific models for prediction of cardiovascular disease risk in COVID-19 patients
No full textBackground Emerging data-driven technologies in healthcare, such as risk prediction models, hold great promise but also pose challenges regarding potential bias and exacerbation of existing health inequalities, which have been observed across diseases such as cardiovascular disease (CVD) and COVID-19. This study addresses the impact of ethnicity in risk prediction modelling for cardiovascular events following SARS-CoV-2 infection and explores the potential of ethnicity-specific models to mitigate disparities.
Methods This retrospective cohort study utilises six linked datasets accessed through National Health Service (NHS) England’s Secure Data Environment (SDE) service for England, via the BHF Data Science Centre’s CVD-COVID-UK/COVID-IMPACT Consortium. Inclusion criteria were established, and demographic information, risk factors, and ethnicity categories were defined. Four feature selection methods (LASSO, Random Forest, XGBoost, QRISK) were employed and ethnicity-specific prediction models were trained and tested using logistic regression. Discrimination (AUROC) and calibration performance were assessed for different populations and ethnicity groups.
Findings Several differences were observed in the models trained on the whole study cohort vs ethnicity-specific groups. At the feature selection stage, ethnicity-specific models yielded different selected features. AUROC discrimination measures showed consistent performance across most ethnicity groups, with QRISK-based models performing relatively poorly. Calibration performance exhibited variation across ethnicity groups and age categories. Ethnicity-specific models demonstrated the potential to enhance calibration performance for certain ethnic groups.
Interpretation This research highlights the importance of considering ethnicity in risk prediction modelling to ensure equitable healthcare outcomes. Differences in selected features and asymmetric calibration across ethnicities underscore the necessity of tailored approaches. Ethnicity-specific models offer a pathway to addressing disparities and improving model performance. The study emphasises the role of data-driven technologies in either alleviating or exacerbating existing health inequalities.
Evidence before this study Research has suggested that SARS-CoV-2 infections may have prognostic value in predicting later cardiovascular disease outcomes, two diseases where ethnicity-based health inequalities have been observed. Existing health inequalities are at risk of being exacerbated by bias in emerging data-driven technologies such as risk prediction models, and there currently exists no recommended practice to mitigate this issue. Model performances are not typically stratified by ethnic groups and, if reported, ethnic groups are often only included in higher-level categories that have been criticised for simplicity of definition and for missing key ethnic heterogeneity
Prediction of disease comorbidity using explainable artificial intelligence and machine learning techniques: A systematic review
No full textOBJECTIVE: Disease comorbidity is a major challenge in healthcare affecting the patient's quality of life and costs. AI-based prediction of comorbidities can overcome this issue by improving precision medicine and providing holistic care. The objective of this systematic literature review was to identify and summarise existing machine learning (ML) methods for comorbidity prediction and evaluate the interpretability and explainability of the models. MATERIALS AND METHODS: The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework was used to identify articles in three databases: Ovid Medline, Web of Science and PubMed. The literature search covered a broad range of terms for the prediction of disease comorbidity and ML, including traditional predictive modelling. RESULTS: Of 829 unique articles, 58 full-text papers were assessed for eligibility. A final set of 22 articles with 61 ML models was included in this review. Of the identified ML models, 33 models achieved relatively high accuracy (80-95%) and AUC (0.80-0.89). Overall, 72% of studies had high or unclear concerns regarding the risk of bias. DISCUSSION: This systematic review is the first to examine the use of ML and explainable artificial intelligence (XAI) methods for comorbidity prediction. The chosen studies focused on a limited scope of comorbidities ranging from 1 to 34 (mean = 6), and no novel comorbidities were found due to limited phenotypic and genetic data. The lack of standard evaluation for XAI hinders fair comparisons. CONCLUSION: A broad range of ML methods has been used to predict the comorbidities of various disorders. With further development of explainable ML capacity in the field of comorbidity prediction, there is a significant possibility of identifying unmet health needs by highlighting comorbidities in patient groups that were not previously recognised to be at risk for particular comorbidities
Trochus smaragdinus Trochus
No full textsmaragdinus, Trochus [Jujubinus striatus (Linnaeus, 1758)] (Figures 6E, F) 1872b: 32 [VI: 114] as Trochus striatus var. smaragdina —nomen nudum 1875b: 24 [XIII: 250] as Trochus striatus var. smaragdina —nomen nudum 1878c: 82 [XIX: 396] as Trochus striatus var. smaragdina —nomen nudum 1880b: 220 [XXVI: 518] as Trochus striatus var. smaragdina —available name Type material. MCZR–M–11700 —7 sh “Mirulinus smaragdinus Monts. Sfax”// 155 sh “ Jujubinus smaragdinus C. d’Africa ”// 4 sh “ Jujubinus smaragdinus Monts. Coste d’Africa ” Label in the box: “ T. (Zizyphinus) striatus, Lin. var. smaragdina, Monts Boll. M. Ital. 1880, p. 220. C. D’Afr.!” Type locality. Described from coasts of Africa (Tunisia). Remarks. Raised to species level by Monterosato (1884h: 46) and there made available from its first description (1880b). Recorded by MolluscaBase (2018) as a synonym of Jujubinus striatus (Linnaeus, 1758). It is probably a valid species. subcincta, Gibbula [Gibbula ardens (Salis Marschlins, 1793)] (Figures 6G, H) 1880b: 217 [XXVI: 515]—available name as Trochus succinctus 1888a: 171 [XXXIII: 833]—available name Type material. MCZR –M–11358 —4 sh “ Gibbula subcincta Monts Spugne di Sfax!” “ T. (Gibbula) succinctus, Monts n. sp. C. di Barbaria”// 14 sh “ T. (Gibbula) succinctus Monts Boll. Mal. Ital 1880, p. 217 C. d`Africa!” Type locality. Described from coasts of Barberia (Tunisia) and Palermo (Sicily). Remarks. Nomen novum pro Trochus succinctus Monterosato, 1880 (name emended by the Author) non Gibbula succincta Carpenter, 1864. Recorded by MolluscaBase (2018) as a synonym of Gibbula ardens (Salis Marschlins, 1793).Published as part of Appolloni, Massimo, Smriglio, Carlo, Amati, Bruno, Lugliè, Lorenzo, Nofroni, Italo, Tringali, Lionello P., Mariottini, Paolo & Oliverio, Marco, 2018, Catalogue of the primary types of marine molluscan taxa described by Tommaso Allery Di Maria, Marquis of Monterosato, deposited in the Museo Civico di Zoologia, Roma, pp. 1-138 in Zootaxa 4477 (1) on page 29, DOI: 10.11646/zootaxa.4477.1.1, http://zenodo.org/record/145465
Evaluating an mRNA based body fluid identification test using SYBR green fluorescent dye and real-time PCR
No full textThe requirement to have more definitive and wider ranging body fluid identification (BFID) tests has resulted in a range of mRNA based real-time PCR BFI assays utilising Taqman fluorescent dye. An attempt to make a reliable and cost effective BFI test utilising the alternative SYBR Green fluorescent dye was carried out. RNA was extracted from blood and saliva stains from both male and female donors, this was then reverse transcribed using M-MLV and random hexamers. Using real-time PCR, relative quantitation of blood and saliva specific markers was carried out on the cDNA from the blood and saliva samples using the SYBR® Green fluorescent dye. Melting curve analysis was also performed immediately following PCR amplification. The relative quantitation values were calculated using the formula 2-ΔΔCT and all samples were normalised to reference gene 18s rRNA. The results revealed good specificity for a number of markers using this chemistry, however some markers were undetected. Blood markers NCF2, SPTB, PBDG and saliva specific markers HTN3, SPRR1A, KRT4 and KRT13 were investigated. In the SYBR green studies, the most specific markers were NCF2, KRT4, KRT13 and SPRR1A, showing reproducible results in a number of studies. Blood marker SPTB also appeared to be specific to blood however the melt curve data for this marker in each study was questionable given the low melting temperature for the amplified products. Blood specific marker PBGD, and saliva specific marker HTN3 were not detected using SYBR Green and saliva marker STATH was detected however in each case appeared to be non-specific in nature when them melt curves were analysed. Analysis of the 18s rRNA Ct values showed a higher expression in saliva than in blood in almost all instances, this may be due to collection of a higher number of cells when using a buccal swab, coupled with the inability to accurately quantify the RNA extracts before reverse transcription. Taqman assays were run on all markers as an additional test, to compare with the SYBR green data. All markers except SPTB showed very good specificity for their respective body fluids. SPTB, like in the SYBR green studies was detected in blood more than saliva, however detection was never consistent in each sample. It can therefore be said that real-time PCR using SYBR Green dye was capable of identifying specific mRNA markers blood and saliva however, the lack of specificity for this type of assay makes its use as a routine identification of body fluids in forensic casework not suitable. The main aim of this study was to develop a more cost effective BFID and as such involved the use of SYBR Green as a cheaper alternative to TaqMan. However, throughout these studies, it appeared to be quite costly in terms of validating a SYBR Green experiment, as more reagents were required in the long run due to vast amount of no template controls required per experiment. It therefore would appear that while SYBR Green is cheaper to buy, the cost to validate these type of experiments can be quite high, due to the non-specific nature of the dye itself. The SYBR Green studies were also much more time consuming with regards to data interpretation as post analysis of the amplification plot and melt curves is a necessity with this detection chemistry to ensure successful interpretation of the data
Enhancing Patient Outcome Prediction Through Deep Learning With Sequential Diagnosis Codes From Structured Electronic Health Record Data: Systematic Review
No full textBackgroundThe use of structured electronic health records in health care systems has grown rapidly. These systems collect huge amounts of patient information, including diagnosis codes representing temporal medical history. Sequential diagnostic information has proven valuable for predicting patient outcomes. However, the extent to which these types of data have been incorporated into deep learning (DL) models has not been examined.
ObjectiveThis systematic review aims to describe the use of sequential diagnostic data in DL models, specifically to understand how these data are integrated, whether sample size improves performance, and whether the identified models are generalizable.
MethodsRelevant studies published up to May 15, 2023, were identified using 4 databases: PubMed, Embase, IEEE Xplore, and Web of Science. We included all studies using DL algorithms trained on sequential diagnosis codes to predict patient outcomes. We excluded review articles and non–peer-reviewed papers. We evaluated the following aspects in the included papers: DL techniques, characteristics of the dataset, prediction tasks, performance evaluation, generalizability, and explainability. We also assessed the risk of bias and applicability of the studies using the Prediction Model Study Risk of Bias Assessment Tool (PROBAST). We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist to report our findings.
ResultsOf the 740 identified papers, 84 (11.4%) met the eligibility criteria. Publications in this area increased yearly. Recurrent neural networks (and their derivatives; 47/84, 56%) and transformers (22/84, 26%) were the most commonly used architectures in DL-based models. Most studies (45/84, 54%) presented their input features as sequences of visit embeddings. Medications (38/84, 45%) were the most common additional feature. Of the 128 predictive outcome tasks, the most frequent was next-visit diagnosis (n=30, 23%), followed by heart failure (n=18, 14%) and mortality (n=17, 13%). Only 7 (8%) of the 84 studies evaluated their models in terms of generalizability. A positive correlation was observed between training sample size and model performance (area under the receiver operating characteristic curve; P=.02). However, 59 (70%) of the 84 studies had a high risk of bias.
ConclusionsThe application of DL for advanced modeling of sequential medical codes has demonstrated remarkable promise in predicting patient outcomes. The main limitation of this study was the heterogeneity of methods and outcomes. However, our analysis found that using multiple types of features, integrating time intervals, and including larger sample sizes were generally related to an improved predictive performance. This review also highlights that very few studies (7/84, 8%) reported on challenges related to generalizability and less than half (38/84, 45%) of the studies reported on challenges related to explainability. Addressing these shortcomings will be instrumental in unlocking the full potential of DL for enhancing health care outcomes and patient care.
Trial RegistrationPROSPERO CRD42018112161; https://tinyurl.com/yc6h9rw
Digital ethnicity data in population-wide electronic health records in England:a description of completeness, coverage, and granularity of diversity
No full textBackground The link between ethnicity and healthcare inequity, and the urgency for better data is well-recognised. This study describes ethnicity data in nation-wide electronic health records in England, UK.Methods We conducted a retrospective cohort study using de-identified person-level records for the England population available in the National Health Service (NHS) Digital trusted research environment. Primary care records (GDPPR) were linked to hospital and national mortality records. We assessed completeness, consistency, and granularity of ethnicity records using all available SNOMED-CT concepts for ethnicity and NHS ethnicity categories.Findings From 61.8 million individuals registered with a primary care practice in England, 51.5 (83.3%) had at least one ethnicity record in GDPPR, increasing to 93{middle dot}9% when linked with hospital records. Approximately 12{middle dot}0% had at least two conflicting ethnicity codes in primary care records. Women were more likely to have ethnicity recorded than men. Ethnicity was missing most frequently in individuals from 18 to 39 years old and in the southern regions of England. Individuals with an ethnicity record had more comorbidities recorded than those without. Of 489 SNOMED-CT ethnicity concepts available, 255 were used in primary care records. Discrepancies between SNOMED-CT and NHS ethnicity categories were observed, specifically within "Other-" ethnicity groups.Interpretation More than 250 ethnicity sub-groups may be found in health records for the English population, although commonly categorised into "White", "Black", "Asian", "Mixed", and "Other". One in ten individuals do not have ethnicity information recorded in primary care or hospital records. SNOMED-CT codes represent more diversity in ethnicity groups than the NHS ethnicity classification. Improved recording of self-reported ethnicity at first point-of-care and consistency in ethnicity classification across healthcare settings can potentially improve the accuracy of ethnicity in research and ultimately care for all ethnicities.Funding British Heart Foundation Data Science Centre led by Health Data Research UK.Evidence before this study Ethnicity has been highlighted as a significant factor in the disproportionate impact of SARS-CoV-2 infection and mortality. Better knowledge of ethnicity data recorded in real clinical practice is required to improve health research and ultimately healthcare. We searched PubMed from database inception to 14th July 2022 for publications using the search terms “ethnicity” and “electronic health records” or “EHR,” without language restrictions. 228 publications in 2019, before the COVID-19 pandemic, and 304 publications between 2020 and 2022 were identified. However, none of these publications used or reported any of over 400 available SNOMED-CT concepts for ethnicity to account for more granularity and diversity than captured by traditional high-level classification limited to 5 to 9 ethnicity groups.Added value of this study We provide a comprehensive study of the largest collection of ethnicity records from a national-level electronic health records trusted research environment, exploring completeness, consistency, and granularity. This work can serve as a data resource profile of ethnicity from routinely-collected EHR in England.Implications of all the available evidence To achieve equity in healthcare, we need to understand the differences between individuals, as well as the influence of ethnicity both on health status and on health interventions, including variation in the behaviour of tests and therapies. Thus, there is a need for measurements, thresholds, and risk estimates to be tailored to different ethnic groups. This study presents the different medical concepts describing ethnicity in routinely collected data that are readily available to researchers and highlights key elements for improving their accuracy in research. We aim to encourage researchers to use more granular ethnicity than the than typical approaches which aggregate ethnicity into a limited number of categories, failing to reflect the diversity of underlying populations. Accurate ethnicity data will lead to a better understanding of individual diversity, which will help to address disparities and influence policy recommendations that can translate into better, fairer health for all.</div
Ethnic disparities in COVID-19 mortality and cardiovascular disease in England and Wales between 2020-2022
No full textAn increased risk of COVID-19 mortality risk among certain ethnic groups is well-reported, however data on ethnic disparities in COVID-19-related cardiovascular disease (CVD) are lacking. We estimated age-standardised incidence rates and adjusted hazard ratios for 28-day mortality and 30-day CVD by sex for individual ethnicity groups from England and Wales, using linked health and administrative data. We studied 6-level census-based ethnicity group classification, 10-level classification (only for Wales), and 19-level classification as well as any ethnicity sub-groups comprising >1000 individuals each (only for England). COVID-19 28-day mortality and 30-day CVD risk was increased in most non-White ethnic groups in England, and Asian population in Wales, between 23rd January 2020 and 1st April 2022. English data show mortality decreased during the Omicron variant’s dominance, whilst CVD risk [95% confidence interval] remained elevated for certain ethnic groups when compared to White populations (January-April 2022): by 120% [28-280%] in White and Asian men and 58% [32-90%] in Pakistan men, as compared to White British men; and by 75% [13-172%] in Bangladeshi women, 55% [19-102%] in Caribbean women, and 82% [31-153%] in Any Other Ethnic Group women, as compared to White British women. Ethnically diverse populations in the UK remained disproportionately affected by CVD throughout and beyond the COVID-19 pandemic
Ethnic disparities in COVID-19 mortality and cardiovascular disease in England and Wales between 2020-2022
No full textAn increased risk of COVID-19 mortality risk among certain ethnic groups is well-reported, however data on ethnic disparities in COVID-19-related cardiovascular disease (CVD) are lacking. We estimated age-standardised incidence rates and adjusted hazard ratios for 28-day mortality and 30-day CVD by sex for individual ethnicity groups from England and Wales, using linked health and administrative data. We studied 6-level census-based ethnicity group classification, 10-level classification (only for Wales), and 19-level classification as well as any ethnicity sub-groups comprising >1000 individuals each (only for England). COVID-19 28-day mortality and 30-day CVD risk was increased in most non-White ethnic groups in England, and Asian population in Wales, between 23rd January 2020 and 1st April 2022. English data show mortality decreased during the Omicron variant's dominance, whilst CVD risk [95% confidence interval] remained elevated for certain ethnic groups when compared to White populations (January-April 2022): by 120% [28-280%] in White and Asian men and 58% [32-90%] in Pakistan men, as compared to White British men; and by 75% [13-172%] in Bangladeshi women, 55% [19-102%] in Caribbean women, and 82% [31-153%] in Any Other Ethnic Group women, as compared to White British women. Ethnically diverse populations in the UK remained disproportionately affected by CVD throughout and beyond the COVID-19 pandemic.</p
Ethnicity data resource in population-wide health records: completeness, coverage and granularity of diversity
No full textIntersectional social determinants including ethnicity are vital in health research. We curated a population-wide data resource of self-identified ethnicity data from over 60 million individuals in England primary care, linking it to hospital records. We assessed ethnicity data in terms of completeness, consistency, and granularity and found one in ten individuals do not have ethnicity information recorded in primary care. By linking to hospital records, ethnicity data were completed for 94% of individuals. By reconciling SNOMED-CT concepts and census-level categories into a consistent hierarchy, we organised more than 250 ethnicity sub-groups including and beyond "White", "Black", "Asian", "Mixed" and "Other, and found them to be distributed in proportions similar to the general population. This large observational dataset presents an algorithmic hierarchy to represent self-identified ethnicity data collected across heterogeneous healthcare settings. Accurate and easily accessible ethnicity data can lead to a better understanding of population diversity, which is important to address disparities and influence policy recommendations that can translate into better, fairer health for all
