Michelle R. Ananda-Rajah
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
Research Subjects
Michelle R. Ananda-Rajah has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Monica A. Slavin
Sir Peter MacCallum Department of Oncology University of Melbourne Melbourne Victoria Australia
6 shared publications - Karin A. Thursky
Centre for Health Services Research in Cancer, Peter MacCallum Cancer Centre, Melbourne, Victoria, Australia; The Sir Peter MacCallum Department of Oncology, University of Melbourne, Parkville, Victoria, Australia
4 shared publications - Allen C. Cheng
Monash University
3 shared publications Michael Dooley
Pharmacy Department, Alfred Health, Melbourne, Victoria, Australia; Faculty of Pharmacy & Pharmaceutical Science, Monash University, Melbourne, Victoria, Australia
2 shared publicationsA. Bajel
Hematology & Bone Marrow Transplant Service, Royal Melbourne Hospital, Melbourne, Victoria
1 shared publicationA. Grigg
Hematology & Bone Marrow Transplant Service, Royal Melbourne Hospital, Melbourne, Victoria
1 shared publication
Latest Publications
- 1 February 2015
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 53, 251-260
Automatic detection of patients with invasive fungal disease from free-text computed tomography (CT) scans
- 1 February 2015
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 53, 251-260
Automatic detection of patients with invasive fungal disease from free-text computed tomography (CT) scans
- Open Access
- 24 September 2014
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 9 (9) , e107797
Facilitating Surveillance of Pulmonary Invasive Mold Diseases in Patients with Haematological Malignancies by Screening Computed Tomography Reports Using Natural Language Processing
Prospective surveillance of invasive mold diseases (IMDs) in haematology patients should be standard of care but is hampered by the absence of a reliable laboratory prompt and the difficulty of manual surveillance. We used a high throughput technology, natural language processing (NLP), to develop a classifier based on machine learning techniques to screen computed tomography (CT) reports supportive for IMDs. We conducted a retrospective case-control study of CT reports from the clinical encounter and up to 12-weeks after, from a random subset of 79 of 270 case patients with 33 probable/proven IMDs by international definitions, and 68 of 257 uninfected-control patients identified from 3 tertiary haematology centres. The classifier was trained and tested on a reference standard of 449 physician annotated reports including a development subset (n = 366), from a total of 1880 reports, using 10-fold cross validation, comparing binary and probabilistic predictions to the reference standard to generate sensitivity, specificity and area under the receiver-operating-curve (ROC). For the development subset, sensitivity/specificity was 91% (95%CI 86% to 94%)/79% (95%CI 71% to 84%) and ROC area was 0.92 (95%CI 89% to 94%). Of 25 (5.6%) missed notifications, only 4 (0.9%) reports were regarded as clinically significant. CT reports are a readily available and timely resource that may be exploited by NLP to facilitate continuous prospective IMD surveillance with translational benefits beyond surveillance alone.
- 24 September 2014
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 9 (9) , e107797
Open AccessFacilitating Surveillance of Pulmonary Invasive Mold Diseases in Patients with Haematological Malignancies by Screening Computed Tomography Reports Using Natural Language Processing
Prospective surveillance of invasive mold diseases (IMDs) in haematology patients should be standard of care but is hampered by the absence of a reliable laboratory prompt and the difficulty of manual surveillance. We used a high throughput technology, natural language processing (NLP), to develop a classifier based on machine learning techniques to screen computed tomography (CT) reports supportive for IMDs. We conducted a retrospective case-control study of CT reports from the clinical encounter and up to 12-weeks after, from a random subset of 79 of 270 case patients with 33 probable/proven IMDs by international definitions, and 68 of 257 uninfected-control patients identified from 3 tertiary haematology centres. The classifier was trained and tested on a reference standard of 449 physician annotated reports including a development subset (n = 366), from a total of 1880 reports, using 10-fold cross validation, comparing binary and probabilistic predictions to the reference standard to generate sensitivity, specificity and area under the receiver-operating-curve (ROC). For the development subset, sensitivity/specificity was 91% (95%CI 86% to 94%)/79% (95%CI 71% to 84%) and ROC area was 0.92 (95%CI 89% to 94%). Of 25 (5.6%) missed notifications, only 4 (0.9%) reports were regarded as clinically significant. CT reports are a readily available and timely resource that may be exploited by NLP to facilitate continuous prospective IMD surveillance with translational benefits beyond surveillance alone.
- 1 December 2012
- Published by Wolters Kluwer Health in Current Opinion in Infectious Diseases
- Vol. 25 (6) , 605-611
Making sense of posaconazole therapeutic drug monitoring
Purpose of review Therapeutic drug monitoring (TDM) may be an important adjunct to optimizing the use of posaconazole. Recent findings Limited clinical studies suggest that an exposure-response relationship for posaconazole exists for the treatment of established invasive fungal diseases (IFDs), with emerging but less compelling data supporting its role in prophylaxis. The high prevalence of subtherapeutic levels has not translated to high prophylactic failure rates perhaps because of preferential uptake by effector cells important in the front-line defence against Aspergillus species. Nevertheless, TDM would appear prudent in patients deemed at highest risk for IFD with correction of patient modifiable factors and attention to drug administration important in optimizing drug exposure. TDM performed within a few days after commencing posaconazole may be predictive of steady-state levels, thus minimizing the delay in obtaining results in addition to identifying a subset of patients who may remain persistently subtherapeutic and also resistant to dose-escalation. Trough levels may be supplanted by untimed levels at steady state, thereby expanding the practicalities of TDM. We propose that TDM becomes one of the several measures in an integrated approach to IFD prevention combining screening of high-risk haematology patients for invasive aspergillosis at presentation, together with prospective surveillance for IFD, explicit criteria for switching to an alternative prophylactic agent and adherence to infection control practices. Summary Growing evidence supports the value of TDM for posaconazole to identify patients who may benefit from correction of modifiable factors impacting bioavailability, dosage adjustment or switch to an alternative agent.
- 1 December 2012
- Published by Wolters Kluwer Health in Current Opinion in Infectious Diseases
- Vol. 25 (6) , 605-611
Making sense of posaconazole therapeutic drug monitoring
Purpose of review Therapeutic drug monitoring (TDM) may be an important adjunct to optimizing the use of posaconazole. Recent findings Limited clinical studies suggest that an exposure-response relationship for posaconazole exists for the treatment of established invasive fungal diseases (IFDs), with emerging but less compelling data supporting its role in prophylaxis. The high prevalence of subtherapeutic levels has not translated to high prophylactic failure rates perhaps because of preferential uptake by effector cells important in the front-line defence against Aspergillus species. Nevertheless, TDM would appear prudent in patients deemed at highest risk for IFD with correction of patient modifiable factors and attention to drug administration important in optimizing drug exposure. TDM performed within a few days after commencing posaconazole may be predictive of steady-state levels, thus minimizing the delay in obtaining results in addition to identifying a subset of patients who may remain persistently subtherapeutic and also resistant to dose-escalation. Trough levels may be supplanted by untimed levels at steady state, thereby expanding the practicalities of TDM. We propose that TDM becomes one of the several measures in an integrated approach to IFD prevention combining screening of high-risk haematology patients for invasive aspergillosis at presentation, together with prospective surveillance for IFD, explicit criteria for switching to an alternative prophylactic agent and adherence to infection control practices. Summary Growing evidence supports the value of TDM for posaconazole to identify patients who may benefit from correction of modifiable factors impacting bioavailability, dosage adjustment or switch to an alternative agent.
- 1 February 2012
- Published by Wolters Kluwer Health in Current Opinion in Infectious Diseases
- Vol. 25 (1) , 107-115
The case for antifungal stewardship
Antimicrobial stewardship (AMS) has overwhelmingly focussed on antibiotics while antifungal agents have been largely neglected despite the few published audits of antifungal drug use demonstrating clear deficiencies in prescribing behaviour. In this review, we outline not only the elements of antifungal stewardship (AFS) in common with AMS but also features specific to antifungal drugs, combined with insights from our experience in AFS. Invasive fungal diseases (IFDs) have a lower institutional incidence relative to infections caused by multiresistant bacteria, but their health and economic burden are substantial. Pharmacy costs inclusive of antifungal agents are a major determinant of IFD-attributable hospital cost. High drug costs and the toxicities of antifungal agents are the principal rationale for AFS while antifungal resistance is an emerging but less prevalent issue. The high mortality/morbidity associated with IFDs, including adverse impact on curative chemotherapy, combined with suboptimal diagnostic tools, has driven the overuse of antifungal drugs. De-escalation of empiric therapy is one of the most challenging aspects of AFS to implement. Nonculture-based tests may enhance AFS, but refinement of both target populations and clinical pathways incorporating their use is required. Performance indicators including structural, process and outcome measures are integral for demonstrating the value of AFS programmes. Practice guidelines adapted to the local context are the cornerstone of AFS. Local epidemiology informs the choice of antifungal agents for the prevention and management of IFDs, underscoring the need for surveillance. Adherence to minimum standards of prescribing ensures that clinical outcomes are optimized and drug toxicities minimized, thus meeting healthcare quality and safety goals.
- 1 February 2012
- Published by Wolters Kluwer Health in Current Opinion in Infectious Diseases
- Vol. 25 (1) , 107-115
The case for antifungal stewardship
Antimicrobial stewardship (AMS) has overwhelmingly focussed on antibiotics while antifungal agents have been largely neglected despite the few published audits of antifungal drug use demonstrating clear deficiencies in prescribing behaviour. In this review, we outline not only the elements of antifungal stewardship (AFS) in common with AMS but also features specific to antifungal drugs, combined with insights from our experience in AFS. Invasive fungal diseases (IFDs) have a lower institutional incidence relative to infections caused by multiresistant bacteria, but their health and economic burden are substantial. Pharmacy costs inclusive of antifungal agents are a major determinant of IFD-attributable hospital cost. High drug costs and the toxicities of antifungal agents are the principal rationale for AFS while antifungal resistance is an emerging but less prevalent issue. The high mortality/morbidity associated with IFDs, including adverse impact on curative chemotherapy, combined with suboptimal diagnostic tools, has driven the overuse of antifungal drugs. De-escalation of empiric therapy is one of the most challenging aspects of AFS to implement. Nonculture-based tests may enhance AFS, but refinement of both target populations and clinical pathways incorporating their use is required. Performance indicators including structural, process and outcome measures are integral for demonstrating the value of AFS programmes. Practice guidelines adapted to the local context are the cornerstone of AFS. Local epidemiology informs the choice of antifungal agents for the prevention and management of IFDs, underscoring the need for surveillance. Adherence to minimum standards of prescribing ensures that clinical outcomes are optimized and drug toxicities minimized, thus meeting healthcare quality and safety goals.
- 4 November 2011
- Published by Ferrata Storti Foundation (Haematologica) in Haematologica
- Vol. 97 (3) , 459-463
Comparative clinical effectiveness of prophylactic voriconazole/posaconazole to fluconazole/itraconazole in patients with acute myeloid leukemia/myelodysplastic syndrome undergoing cytotoxic chemotherapy over a 12-year period
Post-induction aplasia for acute myeloid leukemia/myelodysplastic syndrome is a high-risk period for invasive fungal diseases. The effectiveness of fluconazole, itraconazole solution, voriconazole and posaconazole prophylaxis used consecutively from December 1998 to January 2010 in patients with acute myeloid leukemia/myelodysplastic syndrome undergoing remission-induction chemotherapy was retrospectively evaluated. A total of 216 consecutive patients received 573 prophylaxis courses. Breakthrough-invasive fungal disease incidence in fluconazole, itraconazole, voriconazole, posaconazole recipients was 25%, 16%, 14% and 3%, respectively. Voriconazole/posconazole versus fluconazole/itraconazole combined was associated with significant reductions in breakthrough-invasive fungal disease incidence (20% vs. 8%, P=0.011), premature discontinuations (46% vs. 22% P<0.001) and empiric antifungal treatment (31% vs. 8.5%, P<0.001). Microbiologically confirmed infections were molds. Posaconazole compared to other drugs was associated with fewer courses requiring computed-tomography (43% vs. 26%, P<0.001). Adoption of voriconazole/posaconazole has decreased invasive fungal disease incidence, empiric antifungal treatment and for posaconazole, computed-tomography demand, with effectiveness of posaconazole comparable to clinical trial experience.
- 4 November 2011
- Published by Ferrata Storti Foundation (Haematologica) in Haematologica
- Vol. 97 (3) , 459-463
Comparative clinical effectiveness of prophylactic voriconazole/posaconazole to fluconazole/itraconazole in patients with acute myeloid leukemia/myelodysplastic syndrome undergoing cytotoxic chemotherapy over a 12-year period
Post-induction aplasia for acute myeloid leukemia/myelodysplastic syndrome is a high-risk period for invasive fungal diseases. The effectiveness of fluconazole, itraconazole solution, voriconazole and posaconazole prophylaxis used consecutively from December 1998 to January 2010 in patients with acute myeloid leukemia/myelodysplastic syndrome undergoing remission-induction chemotherapy was retrospectively evaluated. A total of 216 consecutive patients received 573 prophylaxis courses. Breakthrough-invasive fungal disease incidence in fluconazole, itraconazole, voriconazole, posaconazole recipients was 25%, 16%, 14% and 3%, respectively. Voriconazole/posconazole versus fluconazole/itraconazole combined was associated with significant reductions in breakthrough-invasive fungal disease incidence (20% vs. 8%, P=0.011), premature discontinuations (46% vs. 22% P<0.001) and empiric antifungal treatment (31% vs. 8.5%, P<0.001). Microbiologically confirmed infections were molds. Posaconazole compared to other drugs was associated with fewer courses requiring computed-tomography (43% vs. 26%, P<0.001). Adoption of voriconazole/posaconazole has decreased invasive fungal disease incidence, empiric antifungal treatment and for posaconazole, computed-tomography demand, with effectiveness of posaconazole comparable to clinical trial experience.
- Open Access
- 1 May 2011
- Published by American Society for Microbiology in Antimicrobial Agents and Chemotherapy
- Vol. 55 (5) , 1953-1960
Attributable Hospital Cost and Antifungal Treatment of Invasive Fungal Diseases in High-Risk Hematology Patients: an Economic Modeling Approach
Studies using patient-level data to determine the attributable cost of invasive fungal diseases (IFDs) are few. Using a case-control study with activity-based costing of patients admitted to a quaternary hospital from 2002 to 2007, we determined attributable hospitalization cost (and 12 weeks thereafter), length of stay (LOS), and costly antifungal treatment (C-AT; liposomal amphotericin B, voriconazole, posaconazole, caspofungin), expressed as defined daily doses (DDDs) per IFD episode, in patients with hematological malignancies and hematopoietic stem cell recipients. Matching criteria and median regression modeling controlled for confounding variables, including LOS prior to IFD onset. Multiple mycoses were identified in 43 matched case-control pairs ( n = 86). A separate sensitivity analysis included 22 unmatched patients. IFD status was associated with a median excess cost of AU$30,957 (95% confidence interval [CI] = AU$2,368 to AU$59,546; P = 0.034), approximating at purchasing power parity US$21,203 (95% CI = US$1,622 to US$40,784) and €15,788 (95% CI = €1,208 to €30,368), increasing to AU$80,291 (95% CI = AU$33,636 to AU$126,946; P = 0.001), i.e., US$54,993 (95% CI = US$23,038 to US$86,948) and €40,948 (95% CI = €17,154 to €64,742), with intensive care unit (ICU) requirement. Cost determinants were pharmacy costs (64%; P < 0.001) inclusive of antifungal treatment (27%; P < 0.001) and ward costs (27%; P = 0.091), with proportions persisting through 12 weeks for 25 surviving matched pairs (pharmacy, 60% [ P = 0.12]; ward, 31% [ P = 0.21]). Median LOS was not significantly increased unless unmatched patients were included (8 days, 95% CI = 1.8 to 14 days; P = 0.012). Excess C-ATs were 17 DDDs (95% CI = 15 to 19 DDDs; P < 0.001) per case patient and 19 DDDs (95% CI = 16 to 22 DDDs; P < 0.001) per ICU patient. The sensitivity analysis was confirmatory (for median cost, AU$29,441, 95% CI = AU$5,571 to AU$53,310, P = 0.016; for C-AT, 17 DDDs, 95% CI = 16 to 18 DDDs, P < 0.001). IFD results in increased hospital and ICU costs, with pharmacy costs, including antifungal treatment, being major determinants. Consumption of costly antifungal drugs may be a novel resource metric with wider generalizability than cost alone.
- 1 May 2011
- Published by American Society for Microbiology in Antimicrobial Agents and Chemotherapy
- Vol. 55 (5) , 1953-1960
Open AccessAttributable Hospital Cost and Antifungal Treatment of Invasive Fungal Diseases in High-Risk Hematology Patients: an Economic Modeling Approach
Studies using patient-level data to determine the attributable cost of invasive fungal diseases (IFDs) are few. Using a case-control study with activity-based costing of patients admitted to a quaternary hospital from 2002 to 2007, we determined attributable hospitalization cost (and 12 weeks thereafter), length of stay (LOS), and costly antifungal treatment (C-AT; liposomal amphotericin B, voriconazole, posaconazole, caspofungin), expressed as defined daily doses (DDDs) per IFD episode, in patients with hematological malignancies and hematopoietic stem cell recipients. Matching criteria and median regression modeling controlled for confounding variables, including LOS prior to IFD onset. Multiple mycoses were identified in 43 matched case-control pairs ( n = 86). A separate sensitivity analysis included 22 unmatched patients. IFD status was associated with a median excess cost of AU$30,957 (95% confidence interval [CI] = AU$2,368 to AU$59,546; P = 0.034), approximating at purchasing power parity US$21,203 (95% CI = US$1,622 to US$40,784) and €15,788 (95% CI = €1,208 to €30,368), increasing to AU$80,291 (95% CI = AU$33,636 to AU$126,946; P = 0.001), i.e., US$54,993 (95% CI = US$23,038 to US$86,948) and €40,948 (95% CI = €17,154 to €64,742), with intensive care unit (ICU) requirement. Cost determinants were pharmacy costs (64%; P < 0.001) inclusive of antifungal treatment (27%; P < 0.001) and ward costs (27%; P = 0.091), with proportions persisting through 12 weeks for 25 surviving matched pairs (pharmacy, 60% [ P = 0.12]; ward, 31% [ P = 0.21]). Median LOS was not significantly increased unless unmatched patients were included (8 days, 95% CI = 1.8 to 14 days; P = 0.012). Excess C-ATs were 17 DDDs (95% CI = 15 to 19 DDDs; P < 0.001) per case patient and 19 DDDs (95% CI = 16 to 22 DDDs; P < 0.001) per ICU patient. The sensitivity analysis was confirmatory (for median cost, AU$29,441, 95% CI = AU$5,571 to AU$53,310, P = 0.016; for C-AT, 17 DDDs, 95% CI = 16 to 18 DDDs, P < 0.001). IFD results in increased hospital and ICU costs, with pharmacy costs, including antifungal treatment, being major determinants. Consumption of costly antifungal drugs may be a novel resource metric with wider generalizability than cost alone.
- 6 August 2010
- Published by Springer Nature in Intensive Care Medicine
- Vol. 36 (11) , 1890-1898
The role of general quality improvement measures in decreasing the burden of endemic MRSA in a medical–surgical intensive care unit
Purpose To determine whether any of several quality improvement interventions with none specifically targeting methicillin-resistant Staphylococcus aureus (MRSA) were associated with a decline in endemic MRSA prevalence in an intensive care unit (ICU) where active screening and contact isolation precautions for known MRSA colonised patients are not practised. Setting Medical–surgical ICU with 2,000 admissions/year. Design 8.5-year retrospective time-series analysis. Interventions ICU re-location, antibiotic stewardship utilising computerised decision-support and infectious-diseases physician rounds, dedicated ICU infection control practitioners, alcohol-based hand rub solution (ABHRS). Method Regression modelling was used to evaluate trends in S. aureus prevalence density (monthly clinical isolates per 1,000 patient-days), antibiotic consumption, infection control consumables, ABHRS and their temporal relationship with MRSA prevalence. Results Methicillin-resistant S. aureus prevalence density decreased by 83% [95% confidence interval (CI) −68% to −91%, p < 0.001]. Rates of MRSA bacteraemia decreased 89% (95% CI −79% to −94%, p = 0.001) with no statistically significant change in methicillin-sensitive S. aureus bacteraemia. Hospital MRSA prevalence density decreased 17% (95% CI −5% to −27%, p = 0.005), suggesting that ICU was not shifting MRSA elsewhere. In ICU, broad-spectrum antibiotic use decreased by 26% (95% CI −12% to −38%, p = 0.008), coinciding with a decrease in MRSA, but time-series analysis did not show a significant association. On multivariate analysis, only ABHRS was significantly associated with a decrease in MRSA, but it was formally introduced late in the study period when MRSA was already in decline. Conclusion General quality improvement measures were associated with a decrease in endemic MRSA in a high-risk setting without use of resource-intensive active surveillance and isolation practices.
- 6 August 2010
- Published by Springer Nature in Intensive Care Medicine
- Vol. 36 (11) , 1890-1898
The role of general quality improvement measures in decreasing the burden of endemic MRSA in a medical–surgical intensive care unit
Purpose To determine whether any of several quality improvement interventions with none specifically targeting methicillin-resistant Staphylococcus aureus (MRSA) were associated with a decline in endemic MRSA prevalence in an intensive care unit (ICU) where active screening and contact isolation precautions for known MRSA colonised patients are not practised. Setting Medical–surgical ICU with 2,000 admissions/year. Design 8.5-year retrospective time-series analysis. Interventions ICU re-location, antibiotic stewardship utilising computerised decision-support and infectious-diseases physician rounds, dedicated ICU infection control practitioners, alcohol-based hand rub solution (ABHRS). Method Regression modelling was used to evaluate trends in S. aureus prevalence density (monthly clinical isolates per 1,000 patient-days), antibiotic consumption, infection control consumables, ABHRS and their temporal relationship with MRSA prevalence. Results Methicillin-resistant S. aureus prevalence density decreased by 83% [95% confidence interval (CI) −68% to −91%, p < 0.001]. Rates of MRSA bacteraemia decreased 89% (95% CI −79% to −94%, p = 0.001) with no statistically significant change in methicillin-sensitive S. aureus bacteraemia. Hospital MRSA prevalence density decreased 17% (95% CI −5% to −27%, p = 0.005), suggesting that ICU was not shifting MRSA elsewhere. In ICU, broad-spectrum antibiotic use decreased by 26% (95% CI −12% to −38%, p = 0.008), coinciding with a decrease in MRSA, but time-series analysis did not show a significant association. On multivariate analysis, only ABHRS was significantly associated with a decrease in MRSA, but it was formally introduced late in the study period when MRSA was already in decline. Conclusion General quality improvement measures were associated with a decrease in endemic MRSA in a high-risk setting without use of resource-intensive active surveillance and isolation practices.