JFJesper Fleischer

Jesper Fleischer

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jesper Fleischer has a total of 91 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Machine Learning to Diagnose Complications of Diabetes

    by Agatha F. Scheideman, Mandy M. Shao, Henry Zelada, Jorge Cuadros, Joshua Foreman, Pinaki Sarder, Cindy Ho, Niels Ejskjaer, Jesper Fleischer, Simon Lebech Cichosz, et al.

    Machine learning (ML) uses computer systems to develop statistical algorithms and statistical models that can draw inferences from demographic data, structured behavioral data, continuous glucose monitor (CGM) tracings, laboratory data, cardiovascular and neurological physiology measurements, and images from a variety of sources. ML is becoming increasingly used to diagnose complications of diabetes based on these types of datasets. In this article, we review the current status, barriers to progress, and future prospects for using ML to diagnose seven complications of diabetes, including five traditional complications, one set of other systemic complications, and one prediction that can result in favorable or unfavorable outcomes. The complications include (1) diabetic retinopathy, (2) diabetic nephropathy, (3) peripheral neuropathy, (4) autonomic neuropathy, (5) diabetic foot ulcers, and (6) other systemic complications. The prediction is for outcomes in hospitalized patients with diabetes. ML for these purposes is in its infancy, as evidenced by only a limited number of products having received regulatory clearance at this time. However, as multicenter reference datasets become available, it will become possible to train algorithms on increasingly larger and more complex datasets and patterns so that diagnoses and predictions will become increasingly accurate. The use of novel choices of images and imaging technologies will contribute to progress in this field. ML is poised to become a widely used tool for the diagnosis of complications and predictions of outcomes and glycemia in people with diabetes.


  • From Stability to Variability: Classification of Healthy Individuals, Prediabetes, and Type 2 Diabetes Using Glycemic Variability Indices from Continuous Glucose Monitoring Data

    by Simon Lebech Cichosz, Thomas Kronborg, Esben Laugesen, Stine Hangaard, Jesper Fleischer, Troels Krarup Hansen, Morten Hasselstrøm Jensen, Per Løgstrup Poulsen, Peter Vestergaard

    Objective: This study aims to investigate the continuum of glucose control from normoglycemia to dysglycemia (HbA1c ≥ 5.7%/39 mmol/mol) using metrics derived from continuous glucose monitoring (CGM). In addition, we aim to develop a machine learning-based classification model to classify dysglycemia based on observed patterns. Methods: Data from five distinct studies, each featuring at least two days of CGM, were pooled. Participants included individuals classified as healthy, with prediabetes, or with type 2 diabetes mellitus (T2DM). Various CGM indices were extracted and compared across groups. The data set was split 70/30 for training and testing two classification models (XGBoost/Logistic Regression) to differentiate between prediabetes or dysglycemia and the healthy group. Results: The analysis included 836 participants (healthy: n = 282; prediabetes: n = 133; T2DM: n = 432). Across all CGM indices, a progressive shift was observed from the healthy group to those with diabetes ( P < 0.001). Statistically significant differences ( P < 0.01) were noted in mean glucose, time below range, time above 140 mg/dl, mobility, multiscale complexity index, and glycemic risk index when transitioning from health to prediabetes. The XGBoost models achieved the highest receiver operating characteristic area under the curve values on the test data set ranging from 0.91 [confidence interval (CI): 0.87–0.95] (prediabetes identification) to 0.97 [CI: 0.95–0.98] (dysglycemia identification). Conclusion: Our findings demonstrate a gradual deterioration of glucose homeostasis and increased glycemic variability across the spectrum from normo- to dysglycemia, as evidenced by CGM metrics. The performance of CGM-based indices in classifying healthy individuals and those with prediabetes and diabetes is promising.


  • Cardiovascular Autonomic Neuropathy Independently Predicts Incident Foot Ulcers in People With Diabetes: A Prospective Cohort Study

    by Jennifer A. Pallin, Pernille F. Rønn, Tarunveer S. Ahluwalia, Anne Rasmussen, Jesper Fleischer, Marit E. Jørgensen, Sean F. Dinneen, Patricia M. Kearney, Claire M. Buckley, Christian S. Hansen


  • Open Access

    Effect of 12‐week continuous positive airway pressure therapy on glucose levels assessed by continuous glucose monitoring in people with type 2 diabetes and obstructive sleep apnoea; a randomized controlled trial

    by Anne Margareta Banghøj, Christoffer Krogager, Peter Lommer Kristensen, Klavs Würgler Hansen, Esben Laugesen, Jesper Fleischer, Simon Lebech Cichosz, Per Løgstrup Poulsen, Martin Glymer Kirkegaard, Birger Thorsteinsson, et al.

    Aim: Obstructive sleep apnoea (OSA) is frequent in type 2 diabetes (T2D). The aim was to investigate the effect of a 12‐week treatment with continuous positive airway pressure (CPAP) on glycaemic control assessed by continuous glucose monitoring (CGM), HbA1c and fasting blood glucose in patients with T2D and newly detected OSA.Methods: In a randomized controlled multicentre study, 72 participants with T2D and moderate to severe OSA (78% male, age 62 ± 7, AHI 35 ± 15) were recruited from outpatient clinics in three Danish hospitals and were randomized to CPAP intervention or control. The main outcome was glycaemic control assessed by 6 days CGM at baseline and after 12‐week therapy, as well as by HbA1c and fasting blood glucose.Results: No significant changes were found in average glucose levels, time in glucose range, time with hypoglycaemia, time with hyperglycaemia or coefficient of variability. HbA1c decreased 0.7 mmol/mol (0.07%; P = .8) in the CPAP group and increased 0.8 mmol/mol (0.08%; P = .6) in the control group (intergroup difference, P = .6). Fasting blood glucose increased by 0.2 mmol/L (P = .02) in the CPAP group and by 0.4 mmol/L (P = .01) in the control group (intergroup difference, P = .7). In a prespecified subgroup analysis comparing participants with high adherence (minimum usage of four hours/night for 70% of all nights) to CPAP to the control group, no significant changes were observed either, although these participants had a tendency towards better glycaemic indices.Conclusions: CPAP treatment for 12 weeks does not significantly change glycaemic control in patients with type 2 diabetes and OSA.


  • Open Access

    P168 Prevalence and characteristics of cardiovascular autonomic dysfunction in patients with systemic lupus erythematosus

    by Amanda Zinglersen, Katrine Iversen, Esben Laugesen, Jesper Fleischer, Søren Jacobsen

    Background The prevalence of cardiovascular autonomic dysfunction (CAN) has previously been described with large variation (10–90%) in patients with systemic lupus erythematosus (SLE). CAN is assessed by heart rate variability (HRV) or cardiovascular autonomic reflex tests (CARTs), but these two methods have not previously been compared in SLE patients. Further, little is known about the autonomic nervous system (ANS) impairments at different stages of CAN. Consequently, the purpose of this study is, in a large cohort of SLE patients, to determine the prevalence of CAN and to characterize the ANS function at different CAN-stages by HRV and CARTs. Methods CAN was tested in 111 SLE patients with a 5-minute HRV-test and three CARTs. HRV-items reflecting parasympathetic (PNS) function (high frequency power, HFP) and mixed PNS-sympathetic (SNS) function (low frequency power, LFP; total power, TP; LFP/HFP-ratio and peak LF) were calculated. CAN was staged by the number of abnormal CARTs; early CAN: one abnormal CART, definite CAN: two or more abnormal CARTs. Fifty-five SLE patients were age and gender matched to 55 CAN-tested healthy controls (HC). Results The prevalence of definite CAN in SLE is higher than in HCs (24.1% vs. 1.9%, p=0.001). CAN-stage was significantly associated all HRV-measures, except LF/HF-ratio. SLE patients without definite CAN had lower PNS activity than HCs without definite CAN (HFP: 42.7 vs. 87.5 ms2, p=0.006; LFP/HFP-ratio: 1.79 vs. 1.00, p=0.010, resp.). Furthermore, SLE patients with definite CAN had signs of lower mixed PNS-SNS-function as determined by LFP, TP and peak LF (all pConclusions The prevalence of CAN in SLE patients was 12 times higher than in HCs. In SLE patients, early CAN was associated with impaired PNS function, whereas definite CAN was characterized by impaired function of the PNS and SNS.


  • Open Access

    The Effect of Marine n-3 Polyunsaturated Fatty Acids on Heart Rate Variability in Renal Transplant Recipients: A Randomized Controlled Trial

    by Hanne Sether Lilleberg, Simon Lebech Cichosz, My Svensson, Jeppe Hagstrup Christensen, Jesper Fleischer, Ivar Eide, Trond Jenssen

    Resting heart rate (rHR) and heart rate variability (HRV) are non-invasive measurements that predict the risk of sudden cardiac death (SCD). Marine n-3 polyunsaturated fatty acid (PUFA) supplementation may decrease rHR, increase HRV, and reduce the risk of SCD. To date, no studies have investigated the effect of marine n-3 PUFA on HRV in renal transplant recipients. In a randomized controlled trial, 132 renal transplant recipients were randomized to receive either three 1 g capsules of marine n-3 PUFA, each containing 460 mg/g EPA and 380 mg/g DHA, or control (olive oil) for 44 weeks. HRV was calculated in the time and frequency domains during a conventional cardiovascular reflex test (response to standing, deep breathing, and Valsalva maneuver) and during 2 min of resting in the supine position. There was no significant effect of marine n-3 PUFA supplementation on time-domain HRV compared with controls. rHR decreased 3.1 bpm (± 13.1) for patients receiving marine n-3 PUFA compared to 0.8 (± 11.0) in controls (p = 0.28). In the frequency domain HRV analyses, there was a significant change in response to standing in both high and low frequency measures, 2.9 (p = 0.04, 95% CI (1.1;8)) and 2.7 (p = 0.04, 95% CI (1.1;6.5)), respectively. In conclusion, 44 weeks of supplemental marine n-3 PUFAs in renal transplant recipients significantly improved the cardiac autonomic function, assessed by measuring HRV during conventional cardiovascular reflex tests.


  • Cardiac Autonomic Function Is Associated With Myocardial Flow Reserve in Type 1 Diabetes

    by Emilie H. Zobel, Philip Hasbak, Signe A. Winther, Christian Stevns Hansen, Jesper Fleischer, Bernt J. von Scholten, Lene Holmvang, Andreas Kjaer, Peter Rossing, Tine W. Hansen

    The link between cardiac autonomic neuropathy and risk of cardiovascular disease is highlighted as an area in which research is needed. This study was undertaken to evaluate the association between measures of cardiac autonomic function and cardiac vascular function in type 1 diabetes using new and sensitive methods. This was a cross-sectional study in patients with type 1 diabetes, stratified by normoalbuminuria (n = 30) and macroalbuminuria (n = 30), and in healthy control subjects (n = 30). Cardiac autonomic function was evaluated using heart rate variability (HRV) indices, cardiovascular autonomic reflex tests (CARTs), and cardiac 123I-metaiodobenzylguanidine (MIBG) imaging. Cardiac vascular function was assessed as myocardial flow reserve (MFR) measured by cardiac 82Rb-positron emission tomography/computed tomography. The measures of cardiac autonomic function (except low frequency–to–high frequency ratio and the Valsalva test ratio) were positively correlated to MFR in unadjusted analysis. All the HRV indices lost significance after adjustment for age and heart rate. After further adjustment for relevant cardiovascular risk factors, the late heart-to-mediastinum ratio directly measuring the function of adrenergic receptors and sympathetic integrity (from the MIBG scintigraphy) and the 30-to-15 ratio (a CART), remained positively associated with MFR (P ≤ 0.04). Cardiac autonomic dysfunction, including loss of cardiac sympathetic integrity in type 1 diabetes, is associated with and may contribute to impaired myocardial blood flow regulation.


  • Risk Factors for the Presence and Progression of Cardiovascular Autonomic Neuropathy in Type 2 Diabetes: ADDITION-Denmark

    by Signe T. Andersen, Daniel R. Witte, Jesper Fleischer, Henning Andersen, Torsten Lauritzen, Marit E. Jørgensen, Troels S. Jensen, Rodica Pop-Busui, Morten Charles

    OBJECTIVE To examine the course of cardiovascular autonomic neuropathy (CAN) and related cardiometabolic risk factors in patients with type 2 diabetes. RESEARCH DESIGN AND METHODS CAN and cardiometabolic risk factors were assessed in the Danish arm of the Anglo-Danish-Dutch Study of Intensive Treatment in People With Screen Detected Diabetes in Primary Care (ADDITION-Denmark) at 6-year (n = 777) and 13-year (n = 443) follow-up examinations. Cardiovascular autonomic reflex tests (CARTs)—that is, lying to standing, deep breathing, and the Valsalva maneuver—and 2-min resting heart rate variability (HRV) indices were obtained as the main measures of CAN. Risk factors related to CAN status, as determined by CARTs, were studied by using multivariate logistic regressions. The effect of risk factors on continuous CARTs and HRV indices, and their changes over time, were estimated in linear mixed models. RESULTS A progressive yet heterogeneous course of CAN occurred between the 6- and 13-year follow-ups. Higher HbA1c, weight, BMI, and triglycerides were associated with prevalent CAN. No significant effect of risk factors on CARTs was found when they were analyzed as continuous variables. CART indices decreased over time, and a trend of decreasing HRV indices was seen. Higher HbA1c and BMI were associated with lower HRV index values, but these differences diminished over time. CONCLUSIONS These data confirm that hyperglycemia, obesity, and hypertriglyceridemia are negatively related to indices of CAN, although these effects diminish over time. The observed heterogeneous course of CAN may challenge the present clinical approach of categorically classifying CARTs to diagnose CAN and the notion of CAN being irreversible.


  • Open Access

    Comment on Lachin et al. Association of Glycemic Variability in Type 1 Diabetes With Progression of Microvascular Outcomes in the Diabetes Control and Complications Trial. Diabetes Care 2017;40:777–783

    by Jesper Fleischer, Simon Lebech Cichosz, Troels Krarup Hansen

    Inspired by the interesting study from Lachin et al. (1), we performed post hoc analyses of existing data from two of our recent clinical studies (2,3) to investigate the possible association between the glycemic variability parameter mean amplitude of glycemic excursions (MAGE) calculated from either self-monitoring of blood glucose (SMBG) or continuous glucose monitoring (CGM) devices. In both studies, all patients were equipped with a CGM device and instructed to perform SMBG measurements for 3 days in a row. In the first study (2), 21 patients with type 1 diabetes performed seven blood glucose measurements each day. Our post hoc analysis showed no correlation between MAGESMBG and MAGECGM, R 2 = …


  • Continuous glucose monitoring adds information beyond HbA1c in well-controlled diabetes patients with early cardiovascular autonomic neuropathy

    by Jesper Fleischer, Esben Laugesen, Simon Lebech Cichosz, Pernille Hoeyem, Thomas Fremming Dejgaard, Per Loegstrup Poulsen, Lise Tarnow, Troels Krarup Hansen