Integrating Artificial Intelligence for Advancing Multiple-Cancer Early Detection via Serum Biomarkers: A Narrative Review.

The concept and policies of multicancer early detection (MCED) have gained significant attention from governments worldwide in recent years. In the era of burgeoning artificial intelligence (AI) technology, the integration of MCED with AI has become a prevailing trend, giving rise to a plethora of MCED AI products. However, due to the heterogeneity of both the detection targets and the AI technologies, the overall diversity of MCED AI products remains considerable. The types of detection targets encompass protein biomarkers, cell-free DNA, or combinations of these biomarkers. In the development of AI models, different model training approaches are employed, including datasets of case-control studies or real-world cancer screening datasets. Various validation techniques, such as cross-validation, location-wise validation, and time-wise validation, are used. All of the factors show significant impacts on the predictive efficacy of MCED AIs. After the completion of AI model development, deploying the MCED AIs in clinical practice presents numerous challenges, including presenting the predictive reports, identifying the potential locations and types of tumors, and addressing cancer-related information, such as clinical follow-up and treatment. This study reviews several mature MCED AI products currently available in the market, detecting their composing factors from serum biomarker detection, MCED AI training/validation, and the clinical application. This review illuminates the challenges encountered by existing MCED AI products across these stages, offering insights into the continued development and obstacles within the field of MCED AI.

Self-Supervised Learning-Based General Laboratory Progress Pretrained Model for Cardiovascular Event Detection.

OBJECTIVE: Leveraging patient data through machine learning techniques in disease care offers a multitude of substantial benefits. Nonetheless, the inherent nature of patient data poses several challenges. Prevalent cases amass substantial longitudinal data owing to their patient volume and consistent follow-ups, however, longitudinal laboratory data are renowned for their irregularity, temporality, absenteeism, and sparsity; In contrast, recruitment for rare or specific cases is often constrained due to their limited patient size and episodic observations. This study employed self-supervised learning (SSL) to pretrain a generalized laboratory progress (GLP) model that captures the overall progression of six common laboratory markers in prevalent cardiovascular cases, with the intention of transferring this knowledge to aid in the detection of specific cardiovascular event. METHODS AND PROCEDURES: GLP implemented a two-stage training approach, leveraging the information embedded within interpolated data and amplify the performance of SSL. After GLP pretraining, it is transferred for target vessel revascularization (TVR) detection. RESULTS: The proposed two-stage training improved the performance of pure SSL, and the transferability of GLP exhibited distinctiveness. After GLP processing, the classification exhibited a notable enhancement, with averaged accuracy rising from 0.63 to 0.90. All evaluated metrics demonstrated substantial superiority ([Formula: see text]) compared to prior GLP processing. CONCLUSION: Our study effectively engages in translational engineering by transferring patient progression of cardiovascular laboratory parameters from one patient group to another, transcending the limitations of data availability. The transferability of disease progression optimized the strategies of examinations and treatments, and improves patient prognosis while using commonly available laboratory parameters. The potential for expanding this approach to encompass other diseases holds great promise. CLINICAL IMPACT: Our study effectively transposes patient progression from one cohort to another, surpassing the constraints of episodic observation. The transferability of disease progression contributed to cardiovascular event assessment.

Trend of HPV Molecular Epidemiology in the Post-Vaccine Era: A 10-Year Study.

Cervical cancer, a major health concern among women worldwide, is closely linked to human papillomavirus (HPV) infection. This study explores the evolving landscape of HPV molecular epidemiology in Taiwan over a decade (2010-2020), where prophylactic HPV vaccination has been implemented since 2007. Analyzing data from 40,561 vaginal swab samples, with 42.0% testing positive for HPV, we reveal shifting trends in HPV genotype distribution and infection patterns. The 12 high-risk genotypes, in order of decreasing percentage, were HPV 52, 58, 16, 18, 51, 56, 39, 59, 33, 31, 45, and 35. The predominant genotypes were HPV 52, 58, and 16, accounting for over 70% of cases annually. The proportions of high-risk and non-high-risk HPV infections varied across age groups. High-risk infections predominated in sexually active individuals aged 30-50 and were mixed-type infections. The composition of high-risk HPV genotypes was generally stable over time; however, HPV31, 33, 39, and 51 significantly decreased over the decade. Of the strains, HPV31 and 33 are shielded by the nonavalent HPV vaccine. However, no reduction was noted for the other seven genotypes. This study offers valuable insights into the post-vaccine HPV epidemiology. Future investigations should delve into HPV vaccines' effects and their implications for cervical cancer prevention strategies. These findings underscore the need for continued surveillance and research to guide effective public health interventions targeting HPV-associated diseases.

A risk assessment framework for multidrug-resistant Staphylococcus aureus using machine learning and mass spectrometry technology.

The emergence of multidrug-resistant bacteria is a critical global crisis that poses a serious threat to public health, particularly with the rise of multidrug-resistant Staphylococcus aureus. Accurate assessment of drug resistance is essential for appropriate treatment and prevention of transmission of these deadly pathogens. Early detection of drug resistance in patients is critical for providing timely treatment and reducing the spread of multidrug-resistant bacteria. This study aims to develop a novel risk assessment framework for S. aureus that can accurately determine the resistance to multiple antibiotics. The comprehensive 7-year study involved ˃20 000 isolates with susceptibility testing profiles of six antibiotics. By incorporating mass spectrometry and machine learning, the study was able to predict the susceptibility to four different antibiotics with high accuracy. To validate the accuracy of our models, we externally tested on an independent cohort and achieved impressive results with an area under the receiver operating characteristic curve of 0. 94, 0.90, 0.86 and 0.91, and an area under the precision-recall curve of 0.93, 0.87, 0.87 and 0.81, respectively, for oxacillin, clindamycin, erythromycin and trimethoprim-sulfamethoxazole. In addition, the framework evaluated the level of multidrug resistance of the isolates by using the predicted drug resistance probabilities, interpreting them in the context of a multidrug resistance risk score and analyzing the performance contribution of different sample groups. The results of this study provide an efficient method for early antibiotic decision-making and a better understanding of the multidrug resistance risk of S. aureus.

Alternate Antimicrobial Therapies and Their Companion Tests.

New antimicrobial approaches are essential to counter antimicrobial resistance. The drug development pipeline is exhausted with the emergence of resistance, resulting in unsuccessful trials. The lack of an effective drug developed from the conventional drug portfolio has mandated the introspection into the list of potentially effective unconventional alternate antimicrobial molecules. Alternate therapies with clinically explicable forms include monoclonal antibodies, antimicrobial peptides, aptamers, and phages. Clinical diagnostics optimize the drug delivery. In the era of diagnostic-based applications, it is logical to draw diagnostic-based treatment for infectious diseases. Selection criteria of alternate therapeutics in infectious diseases include detection, monitoring of response, and resistance mechanism identification. Integrating these diagnostic applications is disruptive to the traditional therapeutic development. The challenges and mitigation methods need to be noted. Applying the goals of clinical pharmacokinetics that include enhancing efficacy and decreasing toxicity of drug therapy, this review analyses the strong correlation of alternate antimicrobial therapeutics in infectious diseases. The relationship between drug concentration and the resulting effect defined by the pharmacodynamic parameters are also analyzed. This review analyzes the perspectives of aligning diagnostic initiatives with the use of alternate therapeutics, with a particular focus on companion diagnostic applications in infectious diseases.

Risk Stratification for Herpes Simplex Virus Pneumonia Using Elastic Net Penalized Cox Proportional Hazard Algorithm with Enhanced Explainability.

Herpes simplex virus (HSV) pneumonia is a serious and often fatal respiratory tract infection that occurs in immunocompromised individuals. The early detection of accurate risk stratification is essential in identifying patients who are at high risk of mortality and may benefit from more aggressive treatment. In this study, we developed and validated a risk stratification model for HSV bronchopneumonia using an elastic net penalized Cox proportional hazard algorithm. We analyzed data from a cohort of 104 critically ill patients with HSV bronchopneumonia identified in Chang Gung Memorial Hospital, Linkou, Taiwan: one of the largest tertiary medical centers in the world. A total of 109 predictors, both clinical and laboratory, were identified in this process to develop a risk stratification model that could accurately predict mortality in patients with HSV bronchopneumonia. This model was able to differentiate the risk of death and predict mortality in patients with HSV bronchopneumonia compared to the APACHE II score in the early stage of ICU admissions. Both hazard ratio coefficient and selection frequency were used as the metrics to enhance the explainability of the informative predictors. Our findings suggest that the elastic net penalized Cox proportional hazard algorithm is a promising tool for risk stratification in patients with HSV bronchopneumonia and could be useful in identifying those at high risk of mortality.

Evaluation of Platelet Alloimmunization by Filtration Enzyme-Linked Immunosorbent Assay.

The current methods for detecting antiplatelet antibodies are mostly manual and labor-intensive. A convenient and rapid detection method is required for effectively detecting alloimmunization during platelet transfusion. In our study, to detect antiplatelet antibodies, positive and negative sera of random-donor antiplatelet antibodies were collected after completing a routine solid-phase red cell adherence test (SPRCA). Platelet concentrates from our random volunteer donors were also prepared using the ZZAP method and then used in a faster, significantly less labor-intensive process, a filtration enzyme-linked immunosorbent assay (fELISA), for detecting antibodies against platelet surface antigens. All fELISA chromogen intensities were processed using ImageJ software. By dividing the final chromogen intensity of each test serum with the background chromogen intensity of whole platelets, the reactivity ratios of fELISA can be used to differentiate positive SPRCA sera from negative sera. A sensitivity of 93.9% and a specificity of 93.3% were obtained for 50 µL of sera using fELISA. The area under the ROC curve reached 0.96 when comparing fELISA with the SPRCA test. We have successfully developed a rapid fELISA method for detecting antiplatelet antibodies.

Data-Driven Two-Stage Framework for Identification and Characterization of Different Antibiotic-Resistant Escherichia coli Isolates Based on Mass Spectrometry Data.

In clinical microbiology, matrix-assisted laser desorption ionization-time-of-flight mass spectrometry (MALDI-TOF MS) is frequently employed for rapid microbial identification. However, rapid identification of antimicrobial resistance (AMR) in Escherichia coli based on a large amount of MALDI-TOF MS data has not yet been reported. This may be because building a prediction model to cover all E. coli isolates would be challenging given the high diversity of the E. coli population. This study aimed to develop a MALDI-TOF MS-based, data-driven, two-stage framework for characterizing different AMRs in E. coli. Specifically, amoxicillin (AMC), ceftazidime (CAZ), ciprofloxacin (CIP), ceftriaxone (CRO), and cefuroxime (CXM) were used. In the first stage, we split the data into two groups based on informative peaks according to the importance of the random forest. In the second stage, prediction models were constructed using four different machine learning algorithms-logistic regression, support vector machine, random forest, and extreme gradient boosting (XGBoost). The findings demonstrate that XGBoost outperformed the other four machine learning models. The values of the area under the receiver operating characteristic curve were 0.62, 0.72, 0.87, 0.72, and 0.72 for AMC, CAZ, CIP, CRO, and CXM, respectively. This implies that a data-driven, two-stage framework could improve accuracy by approximately 2.8%. As a result, we developed AMR prediction models for E. coli using a data-driven two-stage framework, which is promising for assisting physicians in making decisions. Further, the analysis of informative peaks in future studies could potentially reveal new insights. IMPORTANCE Based on a large amount of matrix-assisted laser desorption ionization-time-of-flight mass spectrometry (MALDI-TOF MS) clinical data, comprising 37,918 Escherichia coli isolates, a data-driven two-stage framework was established to evaluate the antimicrobial resistance of E. coli. Five antibiotics, including amoxicillin (AMC), ceftazidime (CAZ), ciprofloxacin (CIP), ceftriaxone (CRO), and cefuroxime (CXM), were considered for the two-stage model training, and the values of the area under the receiver operating characteristic curve (AUC) were 0.62 for AMC, 0.72 for CAZ, 0.87 for CIP, 0.72 for CRO, and 0.72 for CXM. Further investigations revealed that the informative peak m/z 9714 appeared with some important peaks at m/z 6809, m/z 7650, m/z 10534, and m/z 11783 for CIP and at m/z 6809, m/z 10475, and m/z 8447 for CAZ, CRO, and CXM. This framework has the potential to improve the accuracy by approximately 2.8%, indicating a promising potential for further research.

Antibiotic Resistance Diagnosis in ESKAPE Pathogens-A Review on Proteomic Perspective.

Antibiotic resistance has emerged as an imminent pandemic. Rapid diagnostic assays distinguish bacterial infections from other diseases and aid antimicrobial stewardship, therapy optimization, and epidemiological surveillance. Traditional methods typically have longer turn-around times for definitive results. On the other hand, proteomic studies have progressed constantly and improved both in qualitative and quantitative analysis. With a wide range of data sets made available in the public domain, the ability to interpret the data has considerably reduced the error rates. This review gives an insight on state-of-the-art proteomic techniques in diagnosing antibiotic resistance in ESKAPE pathogens with a future outlook for evading the "imminent pandemic".

Towards Accurate Identification of Antibiotic-Resistant Pathogens through the Ensemble of Multiple Preprocessing Methods Based on MALDI-TOF Spectra.

Matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has been used to identify microorganisms and predict antibiotic resistance. The preprocessing method for the MS spectrum is key to extracting critical information from complicated MS spectral data. Different preprocessing methods yield different data, and the optimal approach is unclear. In this study, we adopted an ensemble of multiple preprocessing methods--FlexAnalysis, MALDIquant, and continuous wavelet transform-based methods--to detect peaks and build machine learning classifiers, including logistic regressions, naïve Bayes classifiers, random forests, and a support vector machine. The aim was to identify antibiotic resistance in Acinetobacter baumannii, Acinetobacter nosocomialis, Enterococcus faecium, and Group B Streptococci (GBS) based on MALDI-TOF MS spectra collected from two branches of a referral tertiary medical center. The ensemble method was compared with the individual methods. Random forest models built with the data preprocessed by the ensemble method outperformed individual preprocessing methods and achieved the highest accuracy, with values of 84.37% (A. baumannii), 90.96% (A. nosocomialis), 78.54% (E. faecium), and 70.12% (GBS) on independent testing datasets. Through feature selection, important peaks related to antibiotic resistance could be detected from integrated information. The prediction model can provide an opinion for clinicians. The discriminative peaks enabling better prediction performance can provide a reference for further investigation of the resistance mechanism.

Efficiently Predicting Vancomycin Resistance of Enterococcus Faecium From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach.

Matrix-assisted laser desorption ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has recently become a useful analytical approach for microbial identification. The presence and absence of specific peaks on MS spectra are commonly used to identify the bacterial species and predict antibiotic-resistant strains. However, the conventional approach using few single peaks would result in insufficient prediction power without using complete information of whole MS spectra. In the past few years, machine learning algorithms have been successfully applied to analyze the MALDI-TOF MS peaks pattern for rapid strain typing. In this study, we developed a convolutional neural network (CNN) method to deal with the complete information of MALDI-TOF MS spectra for detecting Enterococcus faecium, which is one of the leading pathogens in the world. We developed a CNN model to rapidly and accurately predict vancomycin-resistant Enterococcus faecium (VREfm) samples from the whole mass spectra profiles of clinical samples. The CNN models demonstrated good classification performances with the average area under the receiver operating characteristic curve (AUROC) of 0.887 when using external validation data independently. Additionally, we employed the score-class activation mapping (CAM) method to identify the important features of our CNN models and found some discriminative signals that can substantially contribute to detecting the ion of resistance. This study not only utilized the complete information of MALTI-TOF MS data directly but also provided a practical means for rapid detection of VREfm using a deep learning algorithm.

Rapid Antibiotic Resistance Serial Prediction in Staphylococcus aureus Based on Large-Scale MALDI-TOF Data by Applying XGBoost in Multi-Label Learning.

Multidrug resistance has become a phenotype that commonly exists among Staphylococcus aureus and is a serious concern for infection treatment. Nowadays, to detect the antibiotic susceptibility, antibiotic testing is generated based on the level of genomic for cure decision consuming huge of time and labor, while matrix-assisted laser desorption-ionization (MALDI) time-of-flight mass spectrometry (TOF/MS) shows its possibility in high-speed and effective detection on the level of proteomic. In this study, on the basis of MALDI-TOF spectra data of discovery cohort with 26,852 samples and replication cohort with 4,963 samples from Taiwan area and their corresponding susceptibilities to oxacillin and clindamycin, a multi-label prediction model against double resistance using Lowest Power set ensemble with XGBoost is constructed for rapid susceptibility prediction. With the output of serial susceptibility prediction, the model performance can realize 77% of accuracy for the serial prediction, the area under the receiver characteristic curve of 0.93 for oxacillin susceptibility prediction, and the area under the receiver characteristic curve of 0.89 for clindamycin susceptibility prediction. The generated multi-label prediction model provides serial antibiotic resistance, such as the susceptibilities of oxacillin and clindamycin in this study, for S. aureus-infected patients based on MALDI-TOF, which will provide guidance in antibiotic usage during the treatment taking the advantage of speed and efficiency.

Large-Scale Samples Based Rapid Detection of Ciprofloxacin Resistance in Klebsiella pneumoniae Using Machine Learning Methods.

Klebsiella pneumoniae is one of the most common causes of hospital- and community-acquired pneumoniae. Resistance to the extensively used quinolone antibiotic, such as ciprofloxacin, has increased in Klebsiella pneumoniae, which leads to the increase in the risk of initial antibiotic selection for Klebsiella pneumoniae treatment. Rapid and precise identification of ciprofloxacin-resistant Klebsiella pneumoniae (CIRKP) is essential for clinical therapy. Nowadays, matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) is another approach to discover antibiotic-resistant bacteria due to its shorter inspection time and lower cost than other current methods. Machine learning methods are introduced to assist in discovering significant biomarkers from MALDI-TOF MS data and construct prediction models for rapid antibiotic resistance identification. This study examined 16,997 samples taken from June 2013 to February 2018 as part of a longitudinal investigation done by Change Gung Memorial Hospitals (CGMH) at the Linkou branch. We applied traditional statistical approaches to identify significant biomarkers, and then a comparison was made between high-importance features in machine learning models and statistically selected features. Large-scale data guaranteed the statistical power of selected biomarkers. Besides, clustering analysis analyzed suspicious sub-strains to provide potential information about their influences on antibiotic resistance identification performance. For modeling, to simulate the real antibiotic resistance predicting challenges, we included basic information about patients and the types of specimen carriers into the model construction process and separated the training and testing sets by time. Final performance reached an area under the receiver operating characteristic curve (AUC) of 0.89 for support vector machine (SVM) and extreme gradient boosting (XGB) models. Also, logistic regression and random forest models both achieved AUC around 0.85. In conclusion, models provide sensitive forecasts of CIRKP, which may aid in early antibiotic selection against Klebsiella pneumoniae. The suspicious sub-strains could affect the model performance. Further works could keep on searching for methods to improve both the model accuracy and stability.

Long short-term memory model - A deep learning approach for medical data with irregularity in cancer predication with tumor markers.

BACKGROUND: Machine learning (ML) has emerged as a superior method for the analysis of large datasets. Application of ML is often hindered by incompleteness of the data which is particularly evident when approaching disease screening data due to varied testing regimens across medical institutions. Here we explored the utility of multiple ML algorithms to predict cancer risk when trained using a large but incomplete real-world dataset of tumor marker (TM) values. METHODS: TM screening data were collected from a large asymptomatic cohort (n = 163,174) at two independent medical centers. The cohort included 785 individuals who were subsequently diagnosed with cancer. Data included levels of up to eight TMs, but for most subjects, only a subset of the biomarkers were tested. In some instances, TM values were available at multiple time points, but intervals between tests varied widely. The data were used to train and test various machine learning models to evaluate their robustness for predicting cancer risk. Multiple methods for data imputation were explored and models were developed for both single time-point as well as time-series data. RESULTS: The ML algorithm, long short-term memory (LSTM), demonstrated superiority over other models for dealing with irregular medical data. A cancer risk prediction tool was trained and validated for a single time-point test of a TM panel including up to four biomarkers (AUROC = 0.831, 95% CI: 0.827-0.835) which outperformed a single threshold method using the same biomarkers. A second model relying on time series data of up to four time-points for 5 TMs had an AUROC of 0.931. CONCLUSIONS: A cancer risk prediction tool was developed by training a LSTM model using a large but incomplete real-world dataset of TM values. The LSTM model was best able to handle irregular data compared to other ML models. The use of time-series TM data can further improve the predictive performance of LSTM models even when the intervals between tests vary widely. These risk prediction tools are useful to direct subjects to further screening sooner, resulting in earlier detection of occult tumors.

Outcomes of Herpes Simplex Virus Pneumonitis in Critically Ill Patients.

Critically ill patients, such as those in intensive care units (ICUs), can develop herpes simplex virus (HSV) pneumonitis. Given the high prevalence of acute respiratory distress syndrome (ARDS) and multiple pre-existing conditions among ICU patients with HSV pneumonitis, factors predicting mortality in this patient population require further investigation. In this retrospective study, the bronchoalveolar lavage or sputum samples of ICU patients were cultured or subjected to a polymerase chain reaction for HSV detection. Univariable and multivariable Cox regressions were conducted for mortality outcomes. The length of hospital stay was plotted against mortality on Kaplan-Meier curves. Among the 119 patients with HSV pneumonitis (age: 65.8 ± 14.9 years), the mortality rate was 61.34% (73 deaths). The mortality rate was significantly lower among patients with diabetes mellitus (odds ratio [OR] 0.12, 95% confidence interval [CI]: 0.02-0.49, p = 0.0009) and significantly higher among patients with ARDS (OR: 4.18, 95% CI: 1.05-17.97, p < 0.0001) or high (≥30) Acute Physiology and Chronic Health Evaluation II scores (OR: 1.08, 95% CI: 1.00-1.18, p = 0.02). Not having diabetes mellitus (DM), developing ARDS, and having a high Acute Physiology and Chronic Health Evaluation II (APACHE II) score were independent predictors of mortality among ICU patients with HSV pneumonitis.

Investigating Unfavorable Factors That Impede MALDI-TOF-Based AI in Predicting Antibiotic Resistance.

The combination of Matrix-Assisted Laser Desorption/Ionization Time-of-Flight (MALDI-TOF) spectra data and artificial intelligence (AI) has been introduced for rapid prediction on antibiotic susceptibility testing (AST) of Staphylococcus aureus. Based on the AI predictive probability, cases with probabilities between the low and high cut-offs are defined as being in the "grey zone". We aimed to investigate the underlying reasons of unconfident (grey zone) or wrong predictive AST. In total, 479 S. aureus isolates were collected and analyzed by MALDI-TOF, and AST prediction and standard AST were obtained in a tertiary medical center. The predictions were categorized as correct-prediction group, wrong-prediction group, and grey-zone group. We analyzed the association between the predictive results and the demographic data, spectral data, and strain types. For methicillin-resistant S. aureus (MRSA), a larger cefoxitin zone size was found in the wrong-prediction group. Multilocus sequence typing of the MRSA isolates in the grey-zone group revealed that uncommon strain types comprised 80%. Of the methicillin-susceptible S. aureus (MSSA) isolates in the grey-zone group, the majority (60%) comprised over 10 different strain types. In predicting AST based on MALDI-TOF AI, uncommon strains and high diversity contribute to suboptimal predictive performance.

Energy Efficiency of Inference Algorithms for Clinical Laboratory Data Sets: Green Artificial Intelligence Study.

BACKGROUND: The use of artificial intelligence (AI) in the medical domain has attracted considerable research interest. Inference applications in the medical domain require energy-efficient AI models. In contrast to other types of data in visual AI, data from medical laboratories usually comprise features with strong signals. Numerous energy optimization techniques have been developed to relieve the burden on the hardware required to deploy a complex learning model. However, the energy efficiency levels of different AI models used for medical applications have not been studied. OBJECTIVE: The aim of this study was to explore and compare the energy efficiency levels of commonly used machine learning algorithms-logistic regression (LR), k-nearest neighbor, support vector machine, random forest (RF), and extreme gradient boosting (XGB) algorithms, as well as four different variants of neural network (NN) algorithms-when applied to clinical laboratory datasets. METHODS: We applied the aforementioned algorithms to two distinct clinical laboratory data sets: a mass spectrometry data set regarding Staphylococcus aureus for predicting methicillin resistance (3338 cases; 268 features) and a urinalysis data set for predicting Trichomonas vaginalis infection (839,164 cases; 9 features). We compared the performance of the nine inference algorithms in terms of accuracy, area under the receiver operating characteristic curve (AUROC), time consumption, and power consumption. The time and power consumption levels were determined using performance counter data from Intel Power Gadget 3.5. RESULTS: The experimental results indicated that the RF and XGB algorithms achieved the two highest AUROC values for both data sets (84.7% and 83.9%, respectively, for the mass spectrometry data set; 91.1% and 91.4%, respectively, for the urinalysis data set). The XGB and LR algorithms exhibited the shortest inference time for both data sets (0.47 milliseconds for both in the mass spectrometry data set; 0.39 and 0.47 milliseconds, respectively, for the urinalysis data set). Compared with the RF algorithm, the XGB and LR algorithms exhibited a 45% and 53%-60% reduction in inference time for the mass spectrometry and urinalysis data sets, respectively. In terms of energy efficiency, the XGB algorithm exhibited the lowest power consumption for the mass spectrometry data set (9.42 Watts) and the LR algorithm exhibited the lowest power consumption for the urinalysis data set (9.98 Watts). Compared with a five-hidden-layer NN, the XGB and LR algorithms achieved 16%-24% and 9%-13% lower power consumption levels for the mass spectrometry and urinalysis data sets, respectively. In all experiments, the XGB algorithm exhibited the best performance in terms of accuracy, run time, and energy efficiency. CONCLUSIONS: The XGB algorithm achieved balanced performance levels in terms of AUROC, run time, and energy efficiency for the two clinical laboratory data sets. Considering the energy constraints in real-world scenarios, the XGB algorithm is ideal for medical AI applications.

Rapid and Accurate Discrimination of Mycobacterium abscessus Subspecies Based on Matrix-Assisted Laser Desorption Ionization-Time of Flight Spectrum and Machine Learning Algorithms.

Mycobacterium abscessus complex (MABC) has been reported to cause complicated infections. Subspecies identification of MABC is crucial for adequate treatment due to different antimicrobial resistance properties amid subspecies. However, long incubation days are needed for the traditional antibiotic susceptibility testing (AST). Delayed effective antibiotics administration often causes unfavorable outcomes. Thus, we proposed a novel approach to identify subspecies and potential antibiotic resistance, guiding early and accurate treatment. Subspecies of MABC isolates were determined by secA1, rpoB, and hsp65. Matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) spectra were analyzed, and informative peaks were detected by random forest (RF) importance. Machine learning (ML) algorithms were used to build models for classifying MABC subspecies based on spectrum. The models were validated by repeated five-fold cross-validation to avoid over-fitting. In total, 102 MABC isolates (52 subspecies abscessus and 50 subspecies massiliense) were analyzed. Top informative peaks including m/z 6715, 4739, etc. were identified. RF model attained AUROC of 0.9166 (95% CI: 0.9072-0.9196) and outperformed other algorithms in discriminating abscessus from massiliense. We developed a MALDI-TOF based ML model for rapid and accurate MABC subspecies identification. Due to the significant correlation between subspecies and corresponding antibiotics resistance, this diagnostic tool guides a more precise and timelier MABC subspecies-specific treatment.

MDRSA: A Web Based-Tool for Rapid Identification of Multidrug Resistant Staphylococcus aureus Based on Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry.

As antibiotics resistance on superbugs has risen, more and more studies have focused on developing rapid antibiotics susceptibility tests (AST). Meanwhile, identification of multiple antibiotics resistance on Staphylococcus aureus provides instant information which can assist clinicians in administrating the appropriate prescriptions. In recent years, matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) has emerged as a powerful tool in clinical microbiology laboratories for the rapid identification of bacterial species. Yet, lack of study devoted on providing efficient methods to deal with the MS shifting problem, not to mention to providing tools incorporating the MALDI-TOF MS for the clinical use which deliver the instant administration of antibiotics to the clinicians. In this study, we developed a web tool, MDRSA, for the rapid identification of oxacillin-, clindamycin-, and erythromycin-resistant Staphylococcus aureus. Specifically, the kernel density estimation (KDE) was adopted to deal with the peak shifting problem, which is critical to analyze mass spectra data, and machine learning methods, including decision trees, random forests, and support vector machines, which were used to construct the classifiers to identify the antibiotic resistance. The areas under the receiver operating the characteristic curve attained 0.8 on the internal (10-fold cross validation) and external (independent testing) validation. The promising results can provide more confidence to apply these prediction models in the real world. Briefly, this study provides a web-based tool to provide rapid predictions for the resistance of antibiotics on Staphylococcus aureus based on the MALDI-TOF MS data. The web tool is available at: http://fdblab.csie.ncu.edu.tw/mdrsa/.