Background: Demand forecasting is the area of predictive analytics devoted to predicting future volumes of services or consumables. Fair understanding and estimation of how demand will vary facilitates the optimal utilization of resources. In a medical laboratory, accurate forecasting of future demand, that is, test volumes, can increase efficiency and facilitate long-term laboratory planning. Importantly, in an era of utilization management initiatives, accurately predicted volumes compared to the realized test volumes can form a precise way to evaluate utilization management initiatives. Laboratory test volumes are often highly amenable to forecasting by time-series models; however, the statistical software needed to do this is generally either expensive or highly technical. Method: In this paper, we describe an open-source web-based software tool for time-series forecasting and explain how to use it as a demand forecasting tool in clinical laboratories to estimate test volumes. Results: This tool has three different models, that is, Holt-Winters multiplicative, Holt-Winters additive, and simple linear regression. Moreover, these models are ranked and the best one is highlighted. Conclusion: This tool will allow anyone with historic test volume data to model future demand.

Introduction: Postgraduate students spend a sizeable proportion of their time on social media platforms such as WhatsApp and Facebook. This change in our social interaction needs to be accommodated in our teaching methods. To engage them and arouse their curiosity, WhatsApp is an ideal platform. Digital photography by cell phone cameras has made it possible to share cases and discuss them with students round the clock. Objective: The primary aim of the study was to develop sharing and discussion of images using WhatsApp. It also aimed at gathering feedback by means of a questionnaire from pathology residents about their views about the use of WhatsApp for teaching purpose. Materials and Methods: A WhatsApp group by the name “Pathology on the Go” was created with the authors of this study as group administrators and all junior and senior resident doctors (69) as members. The group was used to discuss interesting cases, quiz questions, and other pathology-related academic issues. At the end of 4 weeks, a questionnaire was distributed among the members, and feedback was sought regarding their experience in the group. Results: Over a 4-week period, 16 cases were discussed with 647 posts. A total of 45 participants out of 69 were active participants, and they had an average of 14 posts over the 4-week period. Majority of the participants found the discussions very useful with minimal disruption of the daily routine. Conclusion: There is a need to incorporate Web 2.0 tools such as WhatsApp in our teaching methods to capture as much screen time of the students as possible.

Background: Recent studies of molecular biology have provided great advances for diagnostic molecular pathology. Automated diagnostic systems with computerized scanning for sampled cells in fluids or smears are now widely utilized. Automated analysis of tissue sections is, however, very difficult because they exhibit a complex mixture of overlapping malignant tumor cells, benign host-derived cells, and extracellular materials. Thus, traditional histological diagnosis is still the most powerful method for diagnosis of diseases. Methods: We have developed a novel computer-assisted pathology system for rapid, automated histological analysis of hematoxylin and eosin (H and E)-stained sections. It is a multistage recognition system patterned after methods that human pathologists use for diagnosis but harnessing machine learning and image analysis. The system first analyzes an entire H and E-stained section (tissue) at low resolution to search suspicious areas for cancer and then the selected areas are analyzed at high resolution to confirm the initial suspicion. Results: After training the pathology system with gastric tissues samples, we examined its performance using other 1905 gastric tissues. The system's accuracy in detecting malignancies was shown to be almost equal to that of conventional diagnosis by expert pathologists. Conclusions: Our novel computerized analysis system provides a support for histological diagnosis, which is useful for screening and quality control. We consider that it could be extended to be applicable to many other carcinomas after learning normal and malignant forms of various tissues. Furthermore, we expect it to contribute to the development of more objective grading systems, immunohistochemical staining systems, and fluorescent-stained image analysis systems.

Objectives: Investigators have ruled out herpes simplex virus (HSV) infection without the detection of herpes simplex deoxyribonucleic acid in cerebrospinal fluid (CSF) (i.e., HSV polymerase chain reaction [PCR]) by laboratory (normal CSF white blood cell count and protein) and clinical criteria (age ≥2 years, no history of human immunodeficiency virus or solid-organ transplant). Compared to HSV PCR of all samples, the algorithm saves money in test costs and may decrease exposure to acyclovir by illustrating the low probability that the patient has HSV. Concern exists that algorithm use may cause harm through alteration of empiric acyclovir treatment in patients with true HSV central nervous system infection. Methods: All Department of Veterans Affair's patients with a positive HSV PCR of the CSF between 2000 and 2013 were identified and their medical records reviewed to determine the extent and possible impact of omitted HSV PCR testing by the algorithm. Results: Of 6357 total results, 101 patients had a positive CSF HSV PCR in the study period. Among the positive CSF HSV PCR results, the algorithm excluded 7 (7%) from PCR testing. Record review indicated these seven patients not tested by the algorithm with a positive CSF HSV PCR were considered by their attending physician not to have active HSV. Conclusion: The algorithm to screen HSV tests had no propensity to harm.

Background: The frozen section pathology practice at Mayo Clinic in Rochester performs ~20,000 intraoperative consultations a year (~70–80/weekday). To prepare for intraoperative consultations, surgical pathology fellows and residents review the case history, previous pathology, and relevant imaging the day before surgery. Before the work described herein, review of pending surgical pathology cases was a paper-based process requiring handwritten transcription from the electronic health record, a laborious and potentially error prone process. Methods: To facilitate more efficient case review, a modular extension of an existing surgical listing software application (Surgical and Procedure Scheduling [SPS]) was developed. The module (SPS-pathology-specific module [PM]) added pathology-specific functionality including recording case notes, prefetching of radiology, pathology, and operative reports from the medical record, flagging infectious cases, and real-time tracking of cases in the operating room. After implementation, users were surveyed about its impact on the surgical pathology practice. Results: There were 16 survey respondents (five staff pathologists and eleven residents or fellows). All trainees (11/11) responded that the application improved an aspect of surgical list review including abstraction from medical records (10/11), identification of possibly infectious cases (7/11), and speed of list preparation (10/11). The average reported time savings in list preparation was 1.4 h/day. Respondents indicated the application improved the speed (11/16), clarity (13/16), and accuracy (10/16) of morning report. During the workday, respondents reported the application improved real-time case review (14/16) and situational awareness of ongoing cases (13/16). Conclusions: A majority of respondents found the SPS-PM improved all preparatory and logistical aspects of the Mayo Clinic frozen section surgical pathology practice. In addition, use of the SPS-PM saved an average of 1.4 h/day for residents and fellows engaged in preparatory case review.

The University of Pittsburgh's Department of Biomedical Informatics and Division of Pathology Informatics created a Science, Technology, Engineering, and Mathematics (STEM) pipeline in 2011 dedicated to providing cutting-edge informatics research and career preparatory experiences to a diverse group of highly motivated high-school students. In this third editorial installment describing the program, we provide a brief overview of the pipeline, report on achievements of the past scholars, and present results from self-reported assessments by the 2015 cohort of scholars. The pipeline continues to expand with the 2015 addition of the innovation internship, and the introduction of a program in 2016 aimed at offering first-time research experiences to undergraduates who are underrepresented in pathology and biomedical informatics. Achievements of program scholars include authorship of journal articles, symposium and summit presentations, and attendance at top 25 universities. All of our alumni matriculated into higher education and 90% remain in STEM majors. The 2015 high-school program had ten participating scholars who self-reported gains in confidence in their research abilities and understanding of what it means to be a scientist.

Background: Colorectal cancer (CRC) is the third most common cancer among men and women. Its diagnosis in early stages, typically done through the analysis of colon biopsy images, can greatly improve the chances of a successful treatment. This paper proposes to use convolution neural networks (CNNs) to predict three tissue types related to the progression of CRC: benign hyperplasia (BH), intraepithelial neoplasia (IN), and carcinoma (Ca). Methods: Multispectral biopsy images of thirty CRC patients were retrospectively analyzed. Images of tissue samples were divided into three groups, based on their type (10 BH, 10 IN, and 10 Ca). An active contour model was used to segment image regions containing pathological tissues. Tissue samples were classified using a CNN containing convolution, max-pooling, and fully-connected layers. Available tissue samples were split into a training set, for learning the CNN parameters, and test set, for evaluating its performance. Results: An accuracy of 99.17% was obtained from segmented image regions, outperforming existing approaches based on traditional feature extraction, and classification techniques. Conclusions: Experimental results demonstrate the effectiveness of CNN for the classification of CRC tissue types, in particular when using presegmented regions of interest.