Remote and rapid pathological diagnosis in a resource challenged unit

Evaluation of a machine-learning model based on laboratory parameters for the prediction of acute leukaemia subtypes: a multicentre model development and validation study in France

BACKGROUND

Acute leukaemias are life-threatening haematological cancers characterised by the infiltration of transformed immature haematopoietic cells in the blood and bone marrow. Prompt and accurate diagnosis of the three main acute leukaemia subtypes (ie acute lymphocytic leukaemia [ALL], acute myeloid leukaemia [AML], and acute promyelocytic leukaemia [APL]) is of utmost importance to guide initial treatment and prevent early mortality but requires cytological expertise that is not always available. We aimed to benchmark different machine-learning strategies using a custom variable selection algorithm to propose an extreme gradient boosting model to predict leukaemia subtypes on the basis of routine laboratory parameters.

METHODS

This multicentre model development and validation study was conducted with data from six independent French university hospital databases. Patients aged 18 years or older diagnosed with AML, APL, or ALL in any one of these six hospital databases between March 1, 2012, and Dec 31, 2021, were recruited. 22 routine parameters were collected at the time of initial disease evaluation; variables with more than 25% of missing values in two datasets were not used for model training, leading to the final inclusion of 19 parameters. The performances of the final model were evaluated on internal testing and external validation sets with area under the receiver operating characteristic curves (AUCs), and clinically relevant cutoffs were chosen to guide clinical decision making. The final tool, Artificial Intelligence Prediction of Acute Leukemia (AI-PAL), was developed from this model.

FINDINGS

1410 patients diagnosed with AML, APL, or ALL were included. Data quality control showed few missing values for each cohort, with the exception of uric acid and lactate dehydrogenase for the cohort from Hôpital Cochin. 679 patients from Hôpital Lyon Sud and Centre Hospitalier Universitaire de Clermont-Ferrand were split into the training (n=477) and internal testing (n=202) sets. 731 patients from the four other cohorts were used for external validation. Overall AUCs across all validation cohorts were 0·97 (95% CI 0·95-0·99) for APL, 0·90 (0·83-0·97) for ALL, and 0·89 (0·82-0·95) for AML. Cutoffs were then established on the overall cohort of 1410 patients to guide clinical decisions. Confident cutoffs showed two (0·14%) wrong predictions for ALL, four (0·28%) wrong predictions for APL, and three (0·21%) wrong predictions for AML. Use of the overall cutoff greatly reduced the number of missing predictions; diagnosis was proposed for 1375 (97·5%) of 1410 patients for each category, with only a slight increase in wrong predictions. The final model evaluation across both the internal testing and external validation sets showed accuracy of 99·5% for ALL diagnosis, 98·8% for AML diagnosis, and 99·7% for APL diagnosis in the confident model and accuracy of 87·9% for ALL diagnosis, 86·3% for AML diagnosis, and 96·1% for APL diagnosis in the overall model.

INTERPRETATION

AI-PAL allowed for accurate diagnosis of the three main acute leukaemia subtypes. Based on ten simple laboratory parameters, its broad availability could help guide initial therapies in a context where cytological expertise is lacking, such as in low-income countries.

FUNDING

None.

The role of telepathology in improving cancer diagnostic and research capacity in sub-Saharan Africa

Non-communicable disease (NCD), including cancer, disproportionately affect Low- and Middle-Income Countries (LMICs). This inequity is in part due to limitations of pathology services, both human and infrastructural. While significant improvements have been made to address these gaps, creative approaches that are mindful of regional priorities, cultural differences, and unique local challenges are needed. In this perspective, we will describe the implementation of telepathology services in sub-Saharan Africa (SSA) that serve as cornerstones for direct patient care, multi-disciplinary care coordination, research programs, and building human capacity through training. Models and challenges of system implementation, sustainability, and pathologist engagement will be discussed. Using disease and site-specific examples, we will suggest metrics for quality control and improvement initiatives that are critical for providing high-quality cancer registry data and necessary for future implementation of therapeutic and interventional clinical trials.

Five decades of low intensity and low survival: adapting intensified regimens to cure pediatric Burkitt lymphoma in Africa

Long-term cure of childhood Burkitt lymphoma (BL) in sub-Saharan Africa after treatment with single-agent cyclophosphamide has been documented for more than half of a century. Contemporary cure rates for the highest-risk patients with BL in high-income countries exceed 90% using intensive multiagent chemotherapy. By contrast, the majority of African children with BL still die. Data spanning 5 decades in Africa have repeatedly shown that the children most likely to achieve cure with limited cyclophosphamide regimens are those with lower-stage disease isolated to the jaw. Attempts to intensify the cyclophosphamide monotherapy backbone with the addition of vincristine, low-dose methotrexate, prednisone, doxorubicin, and/or low-dose cytarabine have not yielded significant improvement. High-dose methotrexate is a critical component in the treatment of childhood BL worldwide. Although initial efforts in Africa to incorporate high-dose methotrexate resulted in high treatment-related mortality, more recent collaborative experiences from North and West Africa, as well as Central America, demonstrate that it can be administered safely and effectively, despite limitations in supportive care resources. Recognizing the unacceptable disparity in curative outcomes for BL between the United States/Europe and equatorial Africa, there is a critical need to safely adapt contemporary treatment regimens to optimize curative outcomes amid the resource limitations in regions where BL is endemic. Here, we critically review reports of BL treatment outcomes from low- and middle-income countries, in addition to data from high-income countries that predated modern intensified regimens, to identify potential strategies to improve the therapeutic approach for children suffering from BL in sub-Saharan Africa.

Telepathological evaluation of paediatric histological specimens in support of a hospital in Tanzania

Background/Objective

In a project of telepathology (TP) between German pathologists and a hospital in Tanzania, trained technical assistants have uploaded digital histological images onto the internet-based platform ipath. The diagnoses from 486 paediatric specimens were analysed.

Methods

The investigation included diagnoses, either primarily done via TP or secondarily after a further workup of the paraffin-embedded tissue, which was sent to Germany for cases which could not be solved via TP. In the latter, the initial TP-diagnoses were compared with the results after re-evaluation.

Results

The median age was 11 years. The cohort comprised 390 benign diseases (80.2%) and 96 malignant diseases (19.8%). For benign diseases, the most frequent anatomic sites were lymph nodes, skin, and soft tissue, breast, and head&-neck. Frequent diagnoses were non-specific inflammations and benign tumors. In malignant diseases, the most sites were lymph nodes, skin, soft tissue, head&neck, and ovary and the most frequent diseases sarcomas and lymphomas. The paraffin embedded tissue of 179 cases (36.3%) was shipped to Germany. With the concordance analysis, we could discover the mandatory necessity for the possibility of second opinion in difficult cases.

Conclusion

An exclusively TP-support cannot meet all requirements of modern medical diagnostics. The education of local pathologists is imperative.

Teleoncology for children with cancer: A scoping review on applications and outcomes

BACKGROUND AND OBJECTIVES

Teleoncology can be used to reduce the limitations due to the lack of access to specialists, inadequate resources and training, and reducing unnecessary travels and arising of the costs. The purpose of this study was to review the literatures to identify and classify the areas of application and outcomes of using teleoncology in diagnosis, management, and treatment of children with cancer.

METHODS

This scoping review of the published literatures was conducted by searching the Web of Science, PubMed/Medline, Scopus, and Cochrane Library databases in October 2019. Studies investigated telemedicine in diagnosis, management, and treatment of cancer in children were also included. We identified and classified different applications and the reported outcomes of this technology.

RESULTS

In this study, 1834 articles were retrieved, and after removing the unrelated and duplicated articles, 20 articles were reviewed ultimately. We found that, teleoncology services were provided to the patients with cancer, their parents, and nurses in various clinical fields such as telepathology, telemental care (telepsychology), teleneurology, teledermatology, telehematology, and teleophthalmology. The findings also showed that, the outcomes of using telemedicine in children with cancer can be classified into six general categories (five primary and 14 secondary outcomes). Primary outcomes including diagnosis accuracy, reduced costs as well as mortality and secondary outcomes consist of improved relationship and training, better care management, satisfaction, and workload.

CONCLUSION

The use of telemedicine for children with cancer is growing, and there is a tendency for using this technology for families and clinical staff. Providing teleoncology services to children with cancer may improve diagnosis accuracy and reduce the cost and mortality rate. Also, better care management, appropriate relationships and training, increased satisfaction, and decreased workload may be achieved.

Label-Free Leukemia Monitoring by Computer Vision

Acute lymphoblastic leukemia (ALL) is the most common childhood cancer. While there are a number of well‐recognized prognostic biomarkers at diagnosis, the most powerful independent prognostic factor is the response of the leukemia to induction chemotherapy (Campana and Pui: Blood 129 (2017) 1913–1918). Given the potential for machine learning to improve precision medicine, we tested its capacity to monitor disease in children undergoing ALL treatment. Diagnostic and on‐treatment bone marrow samples were labeled with an ALL‐discriminating antibody combination and analyzed by imaging flow cytometry. Ignoring the fluorescent markers and using only features extracted from bright‐field and dark‐field cell images, a deep learning model was able to identify ALL cells at an accuracy of >88%. This antibody‐free, single cell method is cheap, quick, and could be adapted to a simple, laser‐free cytometer to allow automated, point‐of‐care testing to detect slow early responders. Adaptation to other types of leukemia is feasible, which would revolutionize residual disease monitoring. © 2020 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Re-evaluation of challenging telepathological diagnoses in support of a hospital in Tanzania

Since 2007, a hospital in Tanzania has been supported with histopathological reports via telepathology (TP) by German pathologists. For this, the Internet-based platform iPath is used. The aim of this study was to analyse the rate of discrepancies in defined diagnostic groups. After shipment of paraffin-embedded tissue to Germany, specimens were processed according to recent diagnostic standards. All diagnoses were grouped into eight benign and 11 malignant main categories. The comparison comprised the following categories: 1, identical diagnosis; 2, mild discordance; 3, correct distinction between benign and malignant process, 4, false malignant; 5, false benign; and 6, no primary diagnosis possible. The cohort comprised 396 benign and 336 malignant diseases. Of the benign diseases, 62% were category 1, 23% category 2, 2% category 3, 6% category 4 and 7% category 6. Of the malignant diseases, 42% were category 1, 16% category 2, 12% category 3, 14% category 5 and 15% category 6. Exclusive support with static TP cannot meet all requirements of modern medical diagnostics. However, the project shows a approach for how pathologists in industrial countries can help low-income countries. In difficult cases, the opportunity for a final work-up using additional methods must be given for useful diagnostic purposes.

Remote Patient Monitoring and Telemedicine in Neonatal and Pediatric Settings: Scoping Literature Review

Background

Telemedicine and telehealth solutions are emerging rapidly in health care and have the potential to decrease costs for insurers, providers, and patients in various settings. Pediatric populations that require specialty care are disadvantaged socially or economically or have chronic health conditions that will greatly benefit from results of studies utilizing telemedicine technologies. This paper examines the emerging trends in pediatric populations as part of a systematic literature review and provides a scoping review of the type, extent, and quantity of research available.

Objective

This paper aims to examine the role of remote patient monitoring (RPM) and telemedicine in neonatal and pediatric settings. Findings can be used to identify strengths, weaknesses, and gaps in the field. The identification of gaps will allow for interventions or research to improve health care quality and costs.

Methods

A systematic literature review is being conducted to gather an adequate amount of relevant research for telehealth in pediatric populations. The fields of RPM and telemedicine are not yet very well established by the health care services sector, and definitions vary across health care systems; thus, the terms are not always defined similarly throughout the literature. Three databases were scoped for information for this specific review, and 56 papers were included for review.

Results

Three major telemedicine trends emerged from the review of 45 relevant papers—RPM, teleconsultation, and monitoring patients within the hospital, but without contact—thus, decreasing the likelihood of infection or other adverse health effects.

Conclusions

While the current telemedicine approaches show promise, limited studied conditions and small sample sizes affect generalizability, therefore, warranting further research. The information presented can inform health care providers of the most widely implemented, studied, and effective forms of telemedicine for patients and their families and the telemedicine initiatives that are most cost efficient for health systems. While the focus of this review is to summarize some telehealth applications in pediatrics, we have also presented research studies that can inform providers about the importance of data sharing of remote monitoring data between hospitals. Further reports will be developed to inform health systems as the systematic literature review continues.

Sustainable Development of Pathology in Sub-Saharan Africa: An Example From Ghana

Context.—

Pathology services are poorly developed in Sub-Saharan Africa. Komfo Anokye Teaching Hospital in Kumasi, Ghana, asked for help from the pathology department of the University Hospital of North Norway, Tromsø.

Objective.—

To reestablish surgical pathology and cytology in an African pathology department in which these functions had ceased completely, and to develop the department into a self-supporting unit of good international standard and with the capacity to train new pathologists.

Design.—

Medical technologists from Kumasi were trained in histotechnology in Norway, they were returned to Kumasi, and they produced histologic slides that were temporarily sent to Norway for diagnosis. Two Ghanaian doctors received pathology training for 4 years in Norway. Mutual visits by pathologists and technologists from the 2 hospitals were arranged for the introduction of immunohistochemistry and cytology. Pathologists from Norway visited Kumasi for 1 month each year during 2007–2010. Microscopes and immunohistochemistry equipment were provided from Norway. Other laboratory equipment and a new building were provided by the Ghanaian hospital.

Results.—

The Ghanaian hospital had a surgical pathology service from the first project year. At 11 years after the start of the project, the services included autopsy, surgical pathology, cytopathology, frozen sections, and limited use of immunohistochemistry, and the department had 10 residents at different levels of training.

Conclusions.—

A Ghanaian pathology department that performed autopsies only was developed into a self-supported department with surgical pathology, cytology, immunohistochemistry, and frozen section service, with an active residency program and the capacity for further development that is independent from assistance abroad.

The Empirical Foundations of Telepathology: Evidence of Feasibility and Intermediate Effects

INTRODUCTION

Telepathology evolved from video microscopy (i.e., "television microscopy") research in the early 1950s to video microscopy used in basic research in the biological sciences to a basic diagnostic tool in telemedicine clinical applications. Its genesis can be traced to pioneering feasibility studies regarding the importance of color and other image-based parameters for rendering diagnoses and a series of studies assessing concordance of virtual slide and light microscopy diagnoses. This article documents the empirical foundations of telepathology.

METHODS

A selective review of the research literature during the past decade (2005-2016) was conducted using robust research design and adequate sample size as criteria for inclusion.

CONCLUSIONS

The evidence regarding feasibility/acceptance of telepathology and related information technology applications has been well documented for several decades. The majority of evidentiary studies focused on intermediate outcomes, as indicated by comparability between telepathology and conventional light microscopy. A consistent trend of concordance between the two modalities was observed in terms of diagnostic accuracy and reliability. Additional benefits include use of telepathology and whole slide imaging for teaching, research, and outreach to resource-limited countries. Challenges still exist, however, in terms of use of telepathology as an effective diagnostic modality in clinical practice.

The use of anthracyclines in the treatment of endemic Burkitt lymphoma

Burkitt lymphoma is the most common malignancy in children in Malawi, the world's poorest country, where there is a long history of treating this disease using a 28-day cyclophosphamide-based protocol. Stage III/IV disease has had poor outcomes. In an attempt to improve the outcome for higher stage disease, anthracyclines were added to the existing protocol. The disease-free (DFS) and overall survival (OS) of 58 children with cytologically confirmed Burkitt lymphoma admitted during 2012-2014 and treated using this protocol were calculated. Six (10%) children had stage I disease, ten (17%) stage II and 42 stage III or IV (73%). Overall 12-month DFS (OS) was 68·5% (72·9%); for stage I disease 100% (100%), stage II 56·2% (60%), stage III/IV 66·3% (72·2%). The DFS was significantly improved from the previous protocol (P = 8 × 10^-4 ). The addition of doxorubicin to stage III and IV disease resulted in a markedly improved DFS. Anthracyclines are deliverable in resource-poor settings and possibly improve the survival of children with Burkitt lymphoma.

Implementation and Validation of Telepathology Triage at Cancer Referral Center in Rural Rwanda

Purpose

Connecting a cancer patient to the appropriate treatment requires the correct diagnosis provided in a timely manner. In resource-limited settings, the anatomic pathology bridge to efficient, accurate, and timely cancer care is often challenging. In this study, we present the first phase of an anatomic telepathology triage system, which was implemented and validated at the Butaro District Hospital in northern rural Rwanda.

Methods

Select cases over a 9-month period in three segments were evaluated by static image telepathology and were independently evaluated by standard glass slide histology. Each case via telepathology was classified as malignant, benign, infectious/inflammatory, or nondiagnostic and was given an exact histologic diagnosis.

Results

For cases triaged as appropriate for telepathology, correlation with classification and exact diagnosis demonstrated greater than 95% agreement over the study. Cases in which there was disagreement were analyzed for cause, and the triage process was adjusted to avoid future problems.

Conclusion

Challenges to obtaining a correct and complete diagnosis with telepathology alone included the need for immunohistochemistry, assessment of the quality of images, and the lack of images representing an entire sample. The next phase of the system will assess the effect of telepathology triage on turnaround time and the value of on-site immunohistochemistry in reducing that metric and the need for evaluation outside of telepathology.

Oncologic Care and Pathology Resources in Africa: Survey and Recommendations

The connection of a clinician who identifies a patient with signs and symptoms of malignancy to an oncologist who has the tools to treat a patient's cancer requires a diagnostic pathology laboratory to receive, process, and diagnose the tumor. Without an accurate classification, nothing is known of diagnosis, prognosis, or treatment by the clinical team, and most important, the patient is left scared, confused, and without hope. The vast majority of deaths from malignancies occur in sub-Saharan Africa primarily as a result of lack of public awareness of cancer and how it is diagnosed and treated in the setting of a severe lack of resources (physical and personnel) to actually diagnose tumors. To correct this massive health disparity, a plan of action is required across the continent of Africa to bring diagnostic medicine into the modern era and connect patients with the care they desperately need. We performed a survey of resources in Africa for tissue diagnosis of cancer and asked quantitative questions about tools, personnel, and utilization. We identified a strong correlation between pathology staffing and capacity to provide pathology services. On the basis of this survey and through a congress of concerned pathologists, we propose strategies that will catapult the continent into an era of high-quality pathology services with resultant improvement in cancer outcomes.

Addressing the global health burden of sickle cell disease

A review of the clinical manifestations of sickle cell disease (SCD), available therapeutic interventions and a necessarily limited assessment of progress with their implementation in Nigeria (the country with the largest number of affected individuals worldwide) was recently published in this journal. Despite a disappointing dearth of targeted therapy for a condition whose molecular basis has been well understood for half a century, there is a wealth of evidence-based supportive interventions, including antibiotic and vaccination prophylaxis against early bacteraemic mortality, childhood stroke risk prevention, patient and population education and screening and community care provision that are simple and inexpensive to implement. There is a real opportunity for international collaboration to drive an improvement in healthcare provision for this condition.