Artificial intelligence methods for improved detection of undiagnosed heart failure with preserved ejection fraction.

AIM: Heart failure with preserved ejection fraction (HFpEF) remains under-diagnosed in clinical practice despite accounting for nearly half of all heart failure (HF) cases. Accurate and timely diagnosis of HFpEF is crucial for proper patient management and treatment. In this study, we explored the potential of natural language processing (NLP) to improve the detection and diagnosis of HFpEF according to the European Society of Cardiology (ESC) diagnostic criteria. METHODS AND RESULTS: In a retrospective cohort study, we used an NLP pipeline applied to the electronic health record (EHR) to identify patients with a clinical diagnosis of HF between 2010 and 2022. We collected demographic, clinical, echocardiographic and outcome data from the EHR. Patients were categorized according to the left ventricular ejection fraction (LVEF). Those with LVEF ≥50% were further categorized based on whether they had a clinician-assigned diagnosis of HFpEF and if not, whether they met the ESC diagnostic criteria. Results were validated in a second, independent centre. We identified 8606 patients with HF. Of 3727 consecutive patients with HF and LVEF ≥50% on echocardiogram, only 8.3% had a clinician-assigned diagnosis of HFpEF, while 75.4% met ESC criteria but did not have a formal diagnosis of HFpEF. Patients with confirmed HFpEF were hospitalized more frequently; however the ESC criteria group had a higher 5-year mortality, despite being less comorbid and experiencing fewer acute cardiovascular events. CONCLUSIONS: This study demonstrates that patients with undiagnosed HFpEF are an at-risk group with high mortality. It is possible to use NLP methods to identify likely HFpEF patients from EHR data who would likely then benefit from expert clinical review and complement the use of diagnostic algorithms.

Regional performance variation in external validation of four prediction models for severity of COVID-19 at hospital admission: An observational multi-centre cohort study.

BACKGROUND: Prediction models should be externally validated to assess their performance before implementation. Several prediction models for coronavirus disease-19 (COVID-19) have been published. This observational cohort study aimed to validate published models of severity for hospitalized patients with COVID-19 using clinical and laboratory predictors. METHODS: Prediction models fitting relevant inclusion criteria were chosen for validation. The outcome was either mortality or a composite outcome of mortality and ICU admission (severe disease). 1295 patients admitted with symptoms of COVID-19 at Kings Cross Hospital (KCH) in London, United Kingdom, and 307 patients at Oslo University Hospital (OUH) in Oslo, Norway were included. The performance of the models was assessed in terms of discrimination and calibration. RESULTS: We identified two models for prediction of mortality (referred to as Xie and Zhang1) and two models for prediction of severe disease (Allenbach and Zhang2). The performance of the models was variable. For prediction of mortality Xie had good discrimination at OUH with an area under the receiver-operating characteristic (AUROC) 0.87 [95% confidence interval (CI) 0.79-0.95] and acceptable discrimination at KCH, AUROC 0.79 [0.76-0.82]. In prediction of severe disease, Allenbach had acceptable discrimination (OUH AUROC 0.81 [0.74-0.88] and KCH AUROC 0.72 [0.68-0.75]). The Zhang models had moderate to poor discrimination. Initial calibration was poor for all models but improved with recalibration. CONCLUSIONS: The performance of the four prediction models was variable. The Xie model had the best discrimination for mortality, while the Allenbach model had acceptable results for prediction of severe disease.

Biological responses to COVID-19: Insights from physiological and blood biomarker profiles.

BACKGROUND: Understanding the spectrum and course of biological responses to coronavirus disease 2019 (COVID-19) may have important therapeutic implications. We sought to characterise biological responses among patients hospitalised with severe COVID-19 based on serial, routinely collected, physiological and blood biomarker values. METHODS AND FINDINGS: We performed a retrospective cohort study of 1335 patients hospitalised with laboratory-confirmed COVID-19 (median age 70 years, 56 % male), between 1st March and 30th April 2020. Latent profile analysis was performed on serial physiological and blood biomarkers. Patient characteristics, comorbidities and rates of death and admission to intensive care, were compared between the latent classes. A five class solution provided the best fit. Class 1 "Typical response" exhibited a moderately elevated and rising C-reactive protein (CRP), stable lymphopaenia, and the lowest rates of 14-day adverse outcomes. Class 2 "Rapid hyperinflammatory response" comprised older patients, with higher admission white cell and neutrophil counts, which declined over time, accompanied by a very high and rising CRP and platelet count, and exibited the highest mortality risk. Class 3 "Progressive inflammatory response" was similar to the typical response except for a higher and rising CRP, though similar mortality rate. Class 4 "Inflammatory response with kidney injury" had prominent lymphopaenia, moderately elevated (and rising) CRP, and severe renal failure. Class 5 "Hyperinflammatory response with kidney injury" comprised older patients, with a very high and rising CRP, and severe renal failure that attenuated over time. Physiological measures did not substantially vary between classes at baseline or early admission. CONCLUSIONS AND RELEVANCE: Our identification of five distinct classes of biomarker profiles provides empirical evidence for heterogeneous biological responses to COVID-19. Early hyperinflammatory responses and kidney injury may signify unique pathophysiology that requires targeted therapy.

Optimal treatment for poor responders to ovarian stimulation: does in vitro insemination offer any advantages to intrauterine insemination?

A retrospective study was performed of 1832 consecutive in vitro insemination (IVF)/intracytoplasmic sperm injection (ICSI) cycles over 18 months, to analyse the benefits or otherwise to the patient of continuing with in vitro treatment or converting the assisted conception cycle to intrauterine insemination (IUI). Two hundred and seventy cycles were identified in which three follicles or fewer were obtained after controlled ovarian hyperstimulation; in 143 of these cycles, the clinicians or patients elected to abandon all treatment, whereas treatment was continued in 127 patients. In 79 cycles, the patients proceeded with IVF/ICSI and in 48 patients, the cycles were converted to IUI. Data were analysed with regard to the clinical pregnancy rate. In addition, the data for IUI were compared with eight cycles of supraovulation IUI (S/IUI) performed over the same period. There were no significant differences in clinical pregnancy rates among any treatment modality 6/48 (12.5%), 6/79 (7.7%) and 1/8 (12.5%) for IUI, IVF and S/IUI, respectively (P = 0.64). The lowest total number of motile spermatozoa required to achieve pregnancy using IUI was 2.0 x 10(6). In conclusion, it appears that, if the treatment is suitable, patients who respond poorly to controlled hyperstimulation for IVF would not be disadvantaged in achieving a pregnancy by offering them conversion to the medically and financially less interventional IUI.

Effect on clinical outcome of the interval between collection of epididymal and testicular spermatozoa and intracytoplasmic sperm injection in obstructive azoospermia.

We wished to determine whether the interval between surgical retrieval of epididymal and testicular spermatozoa in obstructive azoospermia and their subsequent use in intracytoplasmic sperm injection (ICSI) has an effect on their fertilizing capacity and pregnancy rates in patients undergoing ICSI. This was a retrospective review of 164 consecutive cycles of ICSI in partners of men undergoing surgical sperm retrieval for obstructive azoospermia. Seventy-three cycles used fresh testicular spermatozoa; in 35 cycles ICSI was performed within 4 hours of sperm retrieval, and in 38 cycles spermatozoa were incubated overnight before ICSI. Epididymal spermatozoa were used in 29 cycles; 22 cases within 4 hours of retrieval and 7 cases following overnight culture. Cyropreserved testicular and epididymal spermatozoa were used in 42 and 20 ICSI cycles, respectively. Fertilization and clinical pregnancy rates were calculated for each treatment group. Fertilization rates for epididymal spermatozoa were 67% at 4 hours, 56% at 24 hours, and 63% for cryopreserved spermatozoa (P =.52). Fertilization rates for testicular spermatozoa were 63% at 4 hours, 71% at 24 hours, and 60% for cryopreserved spermatozoa (P =.16). Unlike testicular spermatozoa, cryopreserved epididymal spermatozoa showed a significant increase in clinical pregnancy rates with cryopreservation, with rates of 4 of 22, 1 of 7, and 10 of 20 at 4 hours, 24 hours, and cryopreservation, respectively (P =.049). This study confirms that fertilization and pregnancy rates following ICSI with motile spermatozoa are unaffected by the duration between surgical retrieval of spermatozoa and their injection into oocytes. It also demonstrates that of all treatment modalities, the use of frozen epididymal spermatozoa was associated with the greatest pregnancy rates.

The value of routine estradiol monitoring in assisted conception cycles.

BACKGROUND: Traditional monitoring of an in vitro fertilization (IVF) treatment cycle includes regular estradiol levels and ultrasound scans in an attempt to reduce the risk of ovarian hyperstimulation syndrome (OHSS). The need for estradiol monitoring remains controversial. METHODS: We reviewed 538 consecutive cycles of IVF that were carried out in our unit to ascertain whether routine estradiol monitoring was of help in preventing OHSS and could be used to predict treatment outcome. Two hundred and sixty-eight patients had their ovarian response monitored with ultrasound (USS) and estradiol levels on the day of hCG administration. The following 270 had USS monitoring but only had an estradiol level checked if they were deemed to be at high risk of OHSS (> 20 follicles on USS or symptomatic). RESULTS: Pregnancy rates per treatment cycle and per embryo transfer were similar in the two groups (all p > 0.05). There were two patients in each group requiring admission to hospital for OHSS. CONCLUSIONS: Estradiol levels did not correlate with IVF outcome. In summary therefore estradiol levels are a poor predictor of treatment success and done routinely do not reduce the incidence of OHSS. It is only necessary to measure the estradiol level in those patients at risk of OHSS on USS monitoring.