A process mining- deep learning approach to predict survival in a cohort of hospitalized COVID-19 patients.

BACKGROUND: Various machine learning and artificial intelligence methods have been used to predict outcomes of hospitalized COVID-19 patients. However, process mining has not yet been used for COVID-19 prediction. We developed a process mining/deep learning approach to predict mortality among COVID-19 patients and updated the prediction in 6-h intervals during the first 72 h after hospital admission. METHODS: The process mining/deep learning model produced temporal information related to the variables and incorporated demographic and clinical data to predict mortality. The mortality prediction was updated in 6-h intervals during the first 72 h after hospital admission. Moreover, the performance of the model was compared with published and self-developed traditional machine learning models that did not use time as a variable. The performance was compared using the Area Under the Receiver Operator Curve (AUROC), accuracy, sensitivity, and specificity. RESULTS: The proposed process mining/deep learning model outperformed the comparison models in almost all time intervals with a robust AUROC above 80% on a dataset that was imbalanced. CONCLUSIONS: Our proposed process mining/deep learning model performed significantly better than commonly used machine learning approaches that ignore time information. Thus, time information should be incorporated in models to predict outcomes more accurately.

Number needed to screen for TB in clinical, structural or occupational risk groups.

BACKGROUND: Screening for active TB using active case-finding (ACF) may reduce TB incidence, prevalence, and mortality; however, yield of ACF interventions varies substantially across populations. We systematically reviewed studies reporting on ACF to calculate the number needed to screen (NNS) for groups at high risk for TB.METHODS: We conducted a literature search for studies reporting ACF for adults published between November 2010 and February 2020. We determined active TB prevalence detected through various screening strategies and calculated crude NNS for - TB confirmed using culture or Xpert® MTB/RIF, and weighted mean NNS stratified by screening strategy, risk group, and country-level TB incidence.RESULTS: We screened 27,223 abstracts; 90 studies were included (41 in low/moderate and 49 in medium/high TB incidence settings). High-risk groups included inpatients, outpatients, people living with diabetes (PLWD), migrants, prison inmates, persons experiencing homelessness (PEH), healthcare workers, and miners. Screening strategies included symptom-based screening, chest X-ray and Xpert testing. NNS varied widely across and within incidence settings based on risk groups and screening methods. Screening tools with higher sensitivity (e.g., Xpert, CXR) were associated with lower NNS estimates.CONCLUSIONS: NNS for ACF strategies varies substantially between adult risk groups. Specific interventions should be tailored based on local epidemiology and costs.

Does tuberculosis screening improve individual outcomes? A systematic review.

BACKGROUND: To determine if tuberculosis (TB) screening improves patient outcomes, we conducted two systematic reviews to investigate the effect of TB screening on diagnosis, treatment outcomes, deaths (clinical review assessing 23 outcome indicators); and patient costs (economic review). METHODS: Pubmed, EMBASE, Scopus and the Cochrane Library were searched between 1/1/1980-13/4/2020 (clinical review) and 1/1/2010-14/8/2020 (economic review). As studies were heterogeneous, data synthesis was narrative. FINDINGS: Clinical review: of 27,270 articles, 18 (n=3 trials) were eligible. Nine involved general populations. Compared to passive case finding (PCF), studies showed lower smear grade (n=2/3) and time to diagnosis (n=2/3); higher pre-treatment losses to follow-up (screened 23% and 29% vs PCF 15% and 14%; n=2/2); and similar treatment success (range 68-81%; n=4) and case fatality (range 3-11%; n=5) in the screened group. Nine reported on risk groups. Compared to PCF, studies showed lower smear positivity among those culture-confirmed (n=3/4) and time to diagnosis (n=2/2); and similar (range 80-90%; n=2/2) treatment success in the screened group. Case fatality was lower in n=2/3 observational studies; both reported on established screening programmes. A neonatal trial and post-hoc analysis of a household contacts trial found screening was associated with lower all-cause mortality. Economic review: From 2841 articles, six observational studies were eligible. Total costs (n=6) and catastrophic cost prevalence (n=4; range screened 9-45% vs PCF 12-61%) was lower among those screened. INTERPRETATION: We found very limited patient outcome data. Collecting and reporting this data must be prioritised to inform policy and practice. FUNDING: WHO and EDCTP.

A systematic review of the number needed to screen for active TB among people living with HIV.

BACKGROUND: Systematic screening for active TB is recommended for all people living with HIV (PLWH); however, case detection remains poor globally. We investigated the yield of active case finding (ACF) by calculating the number needed to screen (NNS) to detect a case of active TB among PLWH.METHODS: We identified studies reporting ACF for TB among PLWH published from November 2010 to February 2020. We calculated crude NNS for Xpert- or culture-confirmed TB and weighted mean NNS stratified by screening approach, population/risk group, and country TB burden.RESULTS: Of the 27,221 abstracts screened, we identified 58 studies eligible for inclusion, including 5 in low/moderate TB incidence settings and 53 in medium/high incidence settings. Populations screened for TB included inpatients, outpatients not receiving antiretroviral therapy (ART), outpatients receiving ART, those with CD4 < 200 cells/µL, children aged ≤15 years, pregnant PLWH, and PLWH in prisons. Screening tools included symptom-based screening, chest X-ray, C-reactive protein levels, and Xpert. The weighted mean NNS varied across groups but was consistently low, ranging from 4 among inpatients in moderate/high TB burden settings to 137 among pregnant PLWH in moderate/high TB burden settings.CONCLUSIONS: ACF is a high yield intervention among PLWH. Approaches to screening should be tailored to local epidemiological and health-system contexts, and sensitive screening tools such as Xpert should be implemented where feasible.

Diagnostic accuracy of C-reactive protein for active pulmonary tuberculosis: a meta-analysis.

SETTING: Systematic screening for active pulmonary tuberculosis (PTB) is recommended for high-risk populations, including people living with the human immunodeficiency virus (PLHIV); however, currently recommended TB screening tools are inadequate for most high-burden settings. OBJECTIVE: To determine whether C-reactive protein (CRP) possesses the necessary test characteristics to screen individuals for active PTB. DESIGN: We performed a systematic review and meta-analysis of studies evaluating the diagnostic accuracy of CRP (10 mg/l cut-off point) for culture-positive PTB. Pooled diagnostic accuracy estimates were generated using random-effects meta-analysis for out-patients and in-patients, and for pre-specified subgroups based on HIV status and test indication. RESULTS: We identified nine unique studies enrolling 1793 adults from out-patient (five studies, 1121 patients) and in-patient settings (five studies, 672 patients), 72% of whom had confirmed HIV infection. Among out-patients, CRP had high sensitivity (93%, 95%CI 88-98) and moderate specificity (60%, 95%CI 40-75) for active PTB. Specificity was lowest among in-patients (21%, 95%CI 6-52) and highest among out-patients undergoing TB screening (range 58-81%). There was no difference in summary estimates by HIV status. CONCLUSION: CRP, which is available as a simple, inexpensive and point-of-care test, can be used to screen PLHIV presenting for routine HIV/AIDS (acquired immune-deficiency syndrome) care for active TB.

Feasibility of a streamlined tuberculosis diagnosis and treatment initiation strategy.

OBJECTIVE: To assess the feasibility of a streamlined strategy for improving tuberculosis (TB) diagnostic evaluation and treatment initiation among patients with presumed TB. DESIGN: Single-arm interventional pilot study at five primary care health centers of a streamlined, SIngle-saMPLE (SIMPLE) TB diagnostic evaluation strategy: 1) examination of two smear results from a single spot sputum specimen using light-emitting diode fluorescence microscopy, and 2) daily transportation of smear-negative sputum samples to Xpert® MTB/RIF testing sites. RESULTS: Of 1212 adults who underwent sputum testing for TB, 99.6% had two smears examined from the spot sputum specimen. Sputum was transported for Xpert testing within 1 clinic day for 83% (907/1091) of the smear-negative patients. Of 157 (13%) patients with bacteriologically positive TB, 116 (74%) were identified using sputum smear microscopy and 41 (26%) using Xpert testing of smear-negative samples. Anti-tuberculosis treatment was initiated in 142 (90%) patients with bacteriologically positive TB, with a median time to treatment of 1 day for smear-positive patients and 6 days for smear-negative, Xpert-positive patients. CONCLUSION: The SIMPLE TB strategy led to successful incorporation of Xpert testing and rapid treatment initiation in the majority of patients with bacteriologically confirmed TB in a resource-limited setting.

Impact of mycobacterial culture among HIV-infected adults with presumed TB in Uganda: a prospective cohort study.

BACKGROUND: Implementation of new tuberculosis (TB) diagnostic strategies in resource-constrained settings is challenging. We measured the impact of solid and liquid mycobacterial cultures on treatment practices for patients undergoing TB evaluation in Kampala, Uganda. METHODS: We enrolled consecutive smear-negative, human immunodeficiency virus positive adults with cough of ⩾2 weeks from September 2009 to April 2010. Laboratory technicians performed mycobacterial cultures on solid and liquid media. We compared empiric treatment decisions with solid and liquid culture in terms of diagnostic yield and time to results, and assessed impact on patient management. RESULTS: Of 200 patients enrolled, 26 (13%) had culture-confirmed TB: 22 (85%) on solid culture alone, 2 (8%) on liquid culture alone, and 2 (8%) on both solid and liquid culture. Thirty-four patients received empiric anti-tuberculosis treatment, but only 10 (29%) were culture-positive. Median time to a positive result on solid culture was 92 days (interquartile range [IQR] 69-148) compared to 106 days (IQR 66-157) for liquid culture. No patients initiated treatment following a positive result on liquid culture. CONCLUSION: The introduction of mycobacterial culture did not influence care for patients undergoing evaluation for TB in Kampala, Uganda. Attention to contextual factors surrounding implementation is needed to ensure the effective introduction of new testing strategies in low-income countries.

Contexte : La mise en œuvre de nouvelles stratégies de diagnostic de la tuberculose (TB) dans les contextes de ressources limitées constitue un défi. Nous avons mesuré l'impact des cultures mycobactériennes en milieu solide et liquide sur les pratiques de traitement des patients ayant une évaluation de la TB à Kampala, Ouganda.Méthodes : Nous avons enrôlé des patients adultes consécutifs à frottis négatif, positifs pour le virus de l'immunodéficience humaine avec toux de ⩾2 semaines, de septembre 2009 à avril 2010. Les techniciens de laboratoire ont réalisé des cultures mycobactériennes en milieu solide et liquide. Nous avons comparé les décisions de traitement empirique aux cultures en milieu solide et liquide en termes de rendement diagnostique et de délai d'obtention des résultats et nous avons évalué l'impact sur la gestion des patients.Résultats : Des 200 patients enrôlés, 26 (13%) avaient une TB confirmée par culture, 22 (85%) par culture en milieu solide seule, 2 (8%) par culture en milieu liquide seul et 2 (8%) par culture à la fois en milieu solide et liquide. Trente-quatre patients ont reçu un traitement de TB empirique, mais seulement 10 (29%) ont eu une TB à culture positive. Le délai médian d'obtention d'un résultat de culture positive en milieu solide a été de 92 jours (IQR 69­148). Le délai médian d'obtention d'un résultat de culture positive en milieu liquide a été de 106 jours (IQR 66­157). Aucun patient n'a commencé un traitement à la suite d'un résultat de culture positive en milieu liquide.Conclusion : L'introduction de la culture mycobactérienne n'a pas influencé les soins aux patients bénéficiant d'une évaluation de TB à Kampala, Ouganda. Il est nécessaire d'être attentif aux facteurs contextuels entourant la mise en œuvre afin d'assurer une introduction effective de nouvelles stratégies de tests dans les pays à faible revenu.

Marco de referencia: La ejecución de nuevas estrategias de diagnóstico de la tuberculosis (TB) en los entornos con limitación de recursos es problemática. En el presente estudio se midió la repercusión del uso del cultivo de micobacterias en medio sólido o liquido sobre las prácticas de tratamiento de los pacientes en curso de investigación diagnóstica de la TB en Kampala, Uganda.Métodos: Se incluyeron de manera consecutiva en el estudio los pacientes adultos, seronegativos frente al virus de la inmunodeficiencia humana, que consultaban por tos de ⩾2 semanas de duración y presentaban baciloscopia negativa, de septiembre del 2009 a abril del 2010. Los auxiliares de laboratorio practicaron el cultivo de micobacterias en medio sólido y medio líquido. Se compararon las decisiones empíricas de tratamiento y los tipos de cultivo, con respecto al rendimiento diagnóstico y al lapso hasta obtener los resultados y se evaluó su repercusión en el manejo de los pacientes.Resultados: De los 200 pacientes que participaron en el estudio, 26 obtuvieron confirmación del diagnóstico de TB mediante el cultivo (13%), 22 de ellos con el cultivo en medio sólido únicamente (85%), dos con el cultivo en medio líquido exclusivamente y dos con ambos tipos de cultivo (8%). Treinta y cuatro pacientes recibieron tratamiento antituberculoso empírico, pero solo 10 de ellos obtuvieron un cultivo positivo (29%). La mediana del lapso hasta obtener el resultado del cultivo en medio sólido fue 92 días (IQR 69­148). La mediana de este lapso con los cultivos en medio líquido fue 106 días (IQR 66­157). Ningún paciente inició el tratamiento antituberculoso después de haber obtenido el resultado positivo del cultivo en medio líquido.Conclusión: La introducción del cultivo para micobacterias no tiene ninguna influencia en la atención que reciben los pacientes en quienes se investiga la TB en Kampala, Uganda. Es importante prestar atención a los factores contextuales que rodean la ejecución, a fin de lograr una introducción eficaz de las nuevas estrategias diagnósticas en los países con recursos limitados.

Evaluation of mobile digital light-emitting diode fluorescence microscopy in Hanoi, Viet Nam.

SETTING: Hanoi Lung Hospital, Hanoi, Viet Nam. OBJECTIVE: To compare the accuracy of CellScopeTB, a manually operated mobile digital fluorescence microscope, with conventional microscopy techniques. DESIGN: Patients referred for sputum smear microscopy to the Hanoi Lung Hospital from May to September 2013 were included. Ziehl-Neelsen (ZN) smear microscopy, conventional light-emitting diode (LED) fluorescence microscopy (FM), CellScopeTB-based LED FM and Xpert(®) MTB/RIF were performed on sputum samples. The sensitivity and specificity of microscopy techniques were determined in reference to Xpert results, and differences were compared using McNemar's paired test of proportions. RESULTS: Of 326 patients enrolled, 93 (28.5%) were Xpert-positive for TB. The sensitivity of ZN microscopy, conventional LED FM, and CellScopeTB-based LED FM was respectively 37.6% (95%CI 27.8-48.3), 41.9% (95%CI 31.8-52.6), and 35.5% (95%CI 25.8-46.1). The sensitivity of CellScopeTB was similar to that of conventional LED FM (difference -6.5%, 95%CI -18.2 to 5.3, P = 0.33) and ZN microscopy (difference -2.2%, 95%CI -9.2 to 4.9, P = 0.73). The specificity was >99% for all three techniques. DISCUSSION: CellScopeTB performed similarly to conventional microscopy techniques in the hands of experienced TB microscopists. However, the sensitivity of all sputum microscopy techniques was low. Options enabled by digital microscopy, such as automated imaging with real-time computerized analysis, should be explored to increase sensitivity.