Development and evaluation of an artificial intelligence for bacterial growth monitoring in clinical bacteriology.

In clinical bacteriology laboratories, reading and processing of sterile plates remain a significant part of the routine workload (30%-40% of the plates). Here, an algorithm was developed for bacterial growth detection starting with any type of specimens and using the most common media in bacteriology. The growth prediction performance of the algorithm for automatic processing of sterile plates was evaluated not only at 18-24 h and 48 h but also at earlier timepoints toward the development of an early growth monitoring system. A total of 3,844 plates inoculated with representative clinical specimens were used. The plates were imaged 15 times, and two different microbiologists read the images randomly and independently, creating 99,944 human ground truths. The algorithm was able, at 48 h, to discriminate growth from no growth with a sensitivity of 99.80% (five false-negative [FN] plates out of 3,844) and a specificity of 91.97%. At 24 h, sensitivity and specificity reached 99.08% and 93.37%, respectively. Interestingly, during human truth reading, growth was reported as early as 4 h, while at 6 h, half of the positive plates were already showing some growth. In this context, automated early growth monitoring in case of normally sterile samples is envisioned to provide added value to the microbiologists, enabling them to prioritize reading and to communicate early detection of bacterial growth to the clinicians.

Towards automated detection, semi-quantification and identification of microbial growth in clinical bacteriology: A proof of concept.

BACKGROUND: Automation in microbiology laboratories impacts management, workflow, productivity and quality. Further improvements will be driven by the development of intelligent image analysis allowing automated detection of microbial growth, release of sterile samples, identification and quantification of bacterial colonies and reading of AST disk diffusion assays. We investigated the potential benefit of intelligent imaging analysis by developing algorithms allowing automated detection, semi-quantification and identification of bacterial colonies. METHODS: Defined monomicrobial and clinical urine samples were inoculated by the BD Kiestra™ InoqulA™ BT module. Image acquisition of plates was performed with the BD Kiestra™ ImagA BT digital imaging module using the BD Kiestra™ Optis™ imaging software. The algorithms were developed and trained using defined data sets and their performance evaluated on both defined and clinical samples. RESULTS: The detection algorithms exhibited 97.1% sensitivity and 93.6% specificity for microbial growth detection. Moreover, quantification accuracy of 80.2% and of 98.6% when accepting a 1 log tolerance was obtained with both defined monomicrobial and clinical urine samples, despite the presence of multiple species in the clinical samples. Automated identification accuracy of microbial colonies growing on chromogenic agar from defined isolates or clinical urine samples ranged from 98.3% to 99.7%, depending on the bacterial species tested. CONCLUSION: The development of intelligent algorithm represents a major innovation that has the potential to significantly increase laboratory quality and productivity while reducing turn-around-times. Further development and validation with larger numbers of defined and clinical samples should be performed before transferring intelligent imaging analysis into diagnostic laboratories.

A phase 1 escalating single-dose and weekly fixed-dose study of cetuximab: pharmacokinetic and pharmacodynamic rationale for dosing.

PURPOSE: This phase 1 study evaluated the pharmacokinetic and pharmacodynamic effects of cetuximab on patients with epithelial malignancies. EXPERIMENTAL DESIGN: Following a skin and tumor biopsy, patients with advanced epithelial malignancies were randomized to receive a single dose of cetuximab at 50, 100, 250, 400, or 500 mg/m2 i.v. Repeat skin (days 2, 8, 15, and 22) and tumor (day 8) biopsies were obtained. Immunohistochemical expression of epidermal growth factor receptor (EGFR) and its pathway members was done on biopsies. Blood samples were obtained over 22 days for pharmacokinetic analyses. After day 22, all patients received weekly 250 mg/m2 cetuximab until disease progression or unacceptable toxicity. RESULTS: Thirty-nine patients enrolled. Rash was noted in 26 (67%) patients. Three patients (two with colon cancer and one with laryngeal cancer) achieved a partial response and 13 patients had stable disease. Pharmacokinetic data revealed mean maximum observed cetuximab concentrations and mean area under the concentration-time curve from time zero to infinity increased in a dose-dependent manner up to 400 mg/m2 cetuximab. Mean clearance was similar at cetuximab doses>or=100 mg/m2, supporting saturation of EGFR binding at 250 mg/m2. Pharmacodynamic evaluation revealed that patients with partial response/stable disease had a higher-grade rash and higher cetuximab trough levels than those with progressive disease (P=0.032 and 0.002, respectively). Administration of single doses (250-500 mg/m2) of cetuximab resulted in a dose-dependent decrease in EGFR protein expression levels in skin over time, supporting a minimal dose of cetuximab at 250 mg/m2 for a pharmacodynamic effect. CONCLUSION: This study provides a pharmacokinetic and pharmacodynamic rationale for the dosing of cetuximab.

Machine scoring of Her2/neu immunohistochemical stains.

OBJECTIVE: To establish the feasibility of a machine scoring method for her2/neu immunohistochemistry in samples of breast carcinoma. STUDY DESIGN: A total of 65 consecutive cases of breast carcinoma with immunohistochemical stainingfor her2/neu by the Herceptest (Dako Corp., Carpinteria, California, U.S.A.) method (DAB chromogen with hematoxylin counterstain) were analyzed using an Extended Slide Wizard (Tripath Imaging, Inc., Burlington, North Carolina, U.S.A.) workstation running prototype software. Representative fields of view from the positive control, negative control and up to 10 fields from the stained tumor sample were captured interactively with a phased alternating line 3 CCD color camera. To determine the amount of specific membrane staining, chromogen separation of nuclear counterstain and membrane-positive stain was performed based on their respective absorption coefficients in the three color channels. The amount of specific membrane staining was scored based on a training set covering the rangefrom 0 to 3 + staining scores according to Dako. Manual scores of 2 + were tested for amplification by fluorescence in situ hybridization. RESULTS: The automated scoring results correlated highly with the manual scores obtained per the Herceptest (Dako) instructions (R2>.92). The results were obtained in real time in the interactive mode. CONCLUSION: Machine scoring of immunohistochemical stains is practical, rapid and inherently reproducible, especially for samples with 1+ and 2+ manual scores.